id
stringlengths 1
5
| prompt
listlengths 1
1
| completion
listlengths 1
1
| Label
stringclasses 3
values |
|---|---|---|---|
150
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Incidence of minor hypoglycaemia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
191
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Dysmenorrhea scores?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
113
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Patients reaching HbA1c goals less than 7.0% and equal or less than 6.5%?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
95
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Routine resite of peripheral intravenous devices every 3 days did not reduce complications compared with clinically indicated resite: a randomised controlled trial\n\n ABSTRACT.BACKGROUND:\nPeripheral intravenous device (IVD) complications were traditionally thought to be reduced by limiting dwell time. Current recommendations are to resite IVDs by 96 hours with the exception of children and patients with poor veins. Recent evidence suggests routine resite is unnecessary, at least if devices are inserted by a specialised IV team. The aim of this study was to compare the impact of peripheral IVD 'routine resite' with 'removal on clinical indication' on IVD complications in a general hospital without an IV team.\n\nABSTRACT.METHODS:\nA randomised, controlled trial was conducted in a regional teaching hospital. After ethics approval, 362 patients (603 IVDs) were randomised to have IVDs replaced on clinical indication (185 patients) or routine change every 3 days (177 patients). IVDs were inserted and managed by the general hospital medical and nursing staff; there was no IV team. The primary endpoint was a composite of IVD complications: phlebitis, infiltration, occlusion, accidental removal, local infection, and device-related bloodstream infection.\n\nABSTRACT.RESULTS:\nIVD complication rates were 68 per 1,000 IVD days (clinically indicated) and 66 per 1,000 IVD days (routine replacement) (P = 0.86; HR 1.03; 95% CI, 0.74-1.43). Time to first complication per patient did not differ between groups (KM with log rank, P = 0.53). There were no local infections or IVD-related bloodstream infections in either group. IV therapy duration did not differ between groups (P = 0.22), but more (P = 0.004) IVDs were placed per patient in the routine replacement (mean, 1.8) than the clinical indication group (mean, 1.5), with significantly higher hospital costs per patient (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nResite on clinical indication would allow one in two patients to have a single cannula per course of IV treatment, as opposed to one in five patients managed with routine resite; overall complication rates appear similar. Clinically indicated resite would achieve savings in equipment, staff time and patient discomfort. There is growing evidence to support the extended use of peripheral IVDs with removal only on clinical indication.\n\nABSTRACT.REGISTRATION NUMBER:\nAustralian New Zealand Clinical Trials Registry (ANZCTR) Number ACTRN12608000421336.\n\nBODY.BACKGROUND:\nPeripheral intravenous device (IVD) insertion is the most commonly performed invasive procedure in hospitalised patients, with an estimated 150 million peripheral intravenous devices placed each year in North America alone [1]. IVDs are vital for delivery of hydration, medicines and nutrition but are not without complications. Serious adverse outcomes are fortunately rare, with IVD-related bloodstream infection reported in a recent meta-analysis of 110 studies to occur in 0.1% of devices and 0.5 per 1,000 device days [2]. IVD treatment is more frequently interrupted by phlebitis, an irritation of the vein characterised by pain, tenderness on palpation, erythema, warmth, swelling, induration or palpable cord (thrombosis) of the cannulated vein; diagnostic algorithms usually require two or more of these conditions [3-5]. Phlebitis is in almost all cases a biochemical reaction to the mechanical irritation by the presence of the IVD and associated infusate [3], although phlebitis symptoms such as erythema may be misperceived as indicative of an infection. In fact, there is not a high correlation between phlebitis and device infection, and the Centers for Disease Control (CDC) states that infection is rarely associated with peripheral, as opposed to central, venous devices [3,6,7]. Fluid infiltration or 'tissuing' of devices is another common IVD complication which may also reflect the inflammatory (phlebitic) response of the vein, rather than simple misplacement of the device tip [8]. Early cohort studies noted an association between increased device time in situ and phlebitis [9,10]. This association was responded to with policies for routine device removal. Recommended timelines for routine resite have been extended over the past three decades from 24, to 48, then to 72 hours. Currently, 72- to 96-hour resite is recommended to reduce phlebitis by the CDC's 2002 Guidelines for the Prevention of Intravascular Device Infection, with the exemption that this is not required in children or those with poor veins [7]. Such policies cause increased workload in hospitals, where the task of removing and replacing well-functioning IVDs generally falls to busy nursing and junior medical staff. In addition, few patients welcome the prospect of additional venipuncture. Despite the general clinical acceptance of routine IVD replacement as a phlebitis and infection prevention measure, it has not been supported by recent data. It may be that the risk of complications during the entire IVD treatment episode is similar, regardless of whether multiple short-dwell or fewer longer-dwell IVDs are used over this time. Three small (n = 47-60) randomised, controlled trials (RCTs) suggested routine replacement at 12, 24 or 48 hours may reduce phlebitis compared to resite on clinical indication, although a systematic review for the Swedish Council on Technology Assessment in Healthcare assessed these as low- to medium-quality studies providing 'limited scientific evidence' [11-14]. More recently, two well-conducted RCTs found no evidence of effect when comparing IVD replacement every 3 days with replacement only on clinical indication for medical and surgical inpatients [15,16]. The largest of these studies reported findings from 755 general medical and surgical patients with 1,428 IVDs and found a 5% difference in combined phlebitis and infiltration rates per patient (38% clinically indicated resite, 33% routine resite), suggesting a potential small clinical benefit of 3-day resite [15]. However, this difference was not statistically significant (RR 1.15; 95% CI, 0.95-1.40) and disappeared when overall cannulation time was considered (59.8/1,000 IVD days clinically indicated resite, 60.9/1,000 IVD days routine resite; RR 0.98; 95% CI 0.78-1.24) [15]. In addition, no clinically important or statistically significant differences were observed in the secondary endpoints of phlebitis, infiltration, occlusion, local infection or suspected bloodstream infection rates between study groups [15]. Another recent RCT in the 'hospital in the home' community setting also found no important clinical or statistically significant difference in phlebitis, occlusion or bloodstream infection rates in 316 patients when resite every 3 days was compared with clinically indicated resite [17]. A 2010 Cochrane Collaboration review concluded there was 'no conclusive evidence of benefit' of routine IVD resite and suggested organisations could consider adopting a resite on clinical indication policy [18]. There is growing evidence that routine IVD replacement may be ineffective, although caution has been urged in light of the large number (74% in both groups in the largest study to date) of reported devices inserted by a specialised IV team, a factor known to reduce complications [19]. Device insertion (and reinsertion) is unpleasant for patients, requires skilled and available clinical staff, and has associated costs for the health sector. If replacement only on clinical indication is safe and effective, this would have important benefits for patients and the health system. We report a RCT of 3-day routine IVD resite versus clinically indicated replacement in a medical-surgical hospital where IVDs were inserted by the general medical and nursing staff; the insitution did not have a specialised IV service.\n\nBODY.METHODS.AIM:\nThe aim of the study was to compare the impact of 3-day routine resite, with clinically indicated resite, on peripheral IVD complications.\n\nBODY.METHODS.DESIGN:\nOpen (nonblinded), parallel group RCT.\n\nBODY.METHODS.ETHICS:\nThe study was approved by the Tasmanian State Human Research Ethics Committee. Written informed consent was obtained prospectively from all participants.\n\nBODY.METHODS.SETTING AND SAMPLE:\nThe study was undertaken at a large regional teaching hospital in Australia which functions as the tertiary referral centre for the northern half of the State of Tasmania. The hospital has more than 32,000 separations per annum, with a spectrum of medical and surgical specialties. Eligible patients were at least 18 years of age and scheduled or expected to have a peripheral IVD indwelling for at least 4 days, and they gave written informed consent. Exclusion criteria were immunosuppression, current bloodstream infection or an IVD already in situ for >48 hours. IVDs were inserted and cared for by the general nursing and medical staff; there was no special IV team or service.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size calculations were performed using PASS 2008 (Version 8.0.8; Kaysville, UT) to detect a change in rates by 30% (from 36% to 25%, two-tailed α = 0.05, 90% power) on the basis of the complication rates of routinely resited IVs in a previous study [16]. Although this indicated that n = 378 per group (total 756) were required, the study was ceased early (total n = 606 IVs) because all investigators left the employment of the institution. Consequently, study power was reduced, but remained over 80% (required minimum n = 282 per group).\n\nBODY.METHODS.RECRUITMENT:\nAll adult patients admitted to the inpatient acute medical and surgical wards of the study hospital were screened by a full-time research nurse. This excluded paediatric, day-surgery, mental health, obstetric, critical care and dialysis units.\n\nBODY.METHODS.STUDY PROCEDURES:\nPatients were randomly assigned (computer generated) in a 1:1 allocation ratio to either the 'routine replacement' (control) or 'clinically indicated replacement' (intervention) group. Assignment was concealed until randomisation by use of a telephone service. A tag was placed on the insertion site indicating the study group. All devices for the patient were managed as per randomised group. The intervention group did not have their IVD resited unless clinically indicated. This decision was made by the treating clinician (not the investigators), who ordered IVD resite if the device failed or phlebitis occurred and ongoing IV treatment was required. The control group had a new device relocated to a different site by the general medical or nursing staff every 3 days. Control devices could also be removed at any stage by the clinical staff if they were not required or if complications occurred. Clinical nursing and medical staff undertook insertion and follow-up care of all IVDs as per the CDC Guidelines [7]. Laboratory staff undertaking microbiological culture assessments were blinded to the study group. Due to the nature of the intervention, patients, research, and clinical staff were unable to be blinded. However, the investigators had no involvement in assessing or documenting complications. IVDs were assessed by the clinical nursing staff on each nursing shift for complications as part of standard clinical practice in the hospital. Times and dates of device insertion and removal were recorded along with the reason for device removal and any protocol deviations. A full-time research nurse collected data from the hospital chart and sought clarification from patients and clinical staff if necessary. Microbiological investigations (device tip, blood cultures and site cultures) were performed by the clinical staff on clinical suspicion of infection by the treating clinician. Demographic and clinical data were collected on age, sex, diagnosis at hospital admission, phlebitis risk based on Tagar et al.'s classification (low/medium/high risk) [20], past history of phlebitis, any comorbidities requiring active medical treatment (e.g., type 2 diabetes or congestive heart failure), haemoglobin, concurrent infection at other sites, antibiotic therapy, type of surgery, type of infusate and any additives (and their level of irritability), vein and skin quality assessment, size of device, insertion site, health professional inserting the device, and setting for insertion, presence of other vascular devices, wound drains and urinary catheters. Vein quality was assessed as good (vein easy to visualise and easy to palpate with tourniquet on), fair (not easily visible but can palpate with tourniquet), or poor (veins small, scarred or difficult to palpate with tourniquet; may require heat pack to aid vasodilation). Skin quality was assessed as good (healthy, well hydrated, elastic), fair (mildly dehydrated, reduced elasticity), or poor (papery, dehydrated, or reduced elasticity).\n\nBODY.METHODS.ANALYTIC APPROACH:\nThe primary outcome was a composite measure of any complication causing unplanned cannula removal prior to completion of IV treatment. The composite included phlebitis, infiltration, occlusion, accidental removal, local infection, and IV device-related bloodstream infection (IVD-BSI). These were also analysed individually as secondary endpoints. A composite measure was chosen due to the low rates of these conditions individually and to the assumption that they are comparable measures of 'infusion failure'; that is, the device can no longer be used to deliver treatment. This approach has been used in previous studies on the topic [15-17]. Phlebitis was defined as two or more of pain, erythema, purulence, streak formation, or a palpable venous cord [3]. Local infection IVD-BSI (bacteremia/fungemia with at least one positive blood culture obtained from a peripheral vein, clinical manifestations of infection, and no apparent source for the bloodstream infection (BSI) except the device with or without positive tip or entry site swab culture) were defined using CDC criteria [7]. Other secondary outcomes were time in situ (hours of catheterisation from insertion to removal, both per patient and per device) [7]; IVDs per patient (number of peripheral devices inserted to complete the course of treatment) [7]; costs (calculations based on 20 minutes nursing or medical insertion time at relevant rates [15], plus the cost of the required equipment (cannula, insertion pack including dressing and solution, gloves, saline, syringe, extension tubing and starter pack for all plus fluid bag, tubing and secondary tubing for medication administration for those patients requiring this) for insertions, nursing time and equipment to routinely remove IVDs that were otherwise functional, and the costs of treating any complications that occurred (e.g., IVD-BSI). Cost calculations were undertaken from the viewpoint of the hospital using negotiated wage costs and purchasing agreements for government hospitals in the State of Tasmania. Costs would be similar for other Australian hospitals. All randomised patients were analysed by intention to treat. Each patient was randomised once and could have multiple IVDs, with subsequent IVD resites managed as per the randomised group. Relative incidence complication rates per 1,000 IVD days and 95% confidence intervals were calculated to summarise the impact of clinically indicated replacement relative to 3-day replacement. Kaplan-Meier survival curves were drawn to compare time to first IVD complication between patients in the two study groups. To assess for any potential impact of protocol violations, a per protocol analysis was also undertaken. All clinical and demographic variables were subjected to univariate testing against the primary endpoint to guide selection of possible covariates for the multivariable model. Cox proportional hazards regression modelling was used to examine the impact of age, gender, oncology status, number of comorbidities (nil, one, two, or more than two), IV gauge, site, vein quality, skin quality, oral antibiotics, IV antibiotics, wound drain, inserter occupation, initial versus subsequent IVDs, phlebitis in a preceeding IVD, haemoglobin level, parenteral nutrition, continuous versus intermittent infusion, patient risk category and study group on the outcome of time to complication events using an additive model [3,5,7,20-25]. In addition, to adjust for any inherent correlations or codependencies in the failure times of IVDs (i.e., same patient multiple failure-time data) within the Cox model, we also used the Prentice-Williams-Peterson conditional risk-set method [26]. The Mann-Whitney test was used to compare various secondary outcomes between study groups. Cost differences were calculated using arithmetic means and the t-test [27]. P values <0.05 were considered significant. All statistical data were entered and analysed using SPSS (Version 15.0; Chicago, IL) and Stata (Version 8.2; College Station, TX).\n\nBODY.RESULTS.SAMPLE:\nOver a 10-month period, 1,954 patients were screened for eligibility. Of these, 788 were eligible, with 362 (46%) recruited into the study. The most frequent exclusion criterion was altered mental state that precluded consideration of consent as assessed by the research nurse. Altered mental state was generally related to older medical patients and the immediate postoperative phase for surgical patients. Reasons for exclusion are shown in Figure 1. The 362 patients were randomised into either the routine change group (n = 177 participants, 323 devices) or the clinically indicated replacement group (n = 185 participants, 280 devices). In total 50,173 IVD hours were studied (routine change group 23,288 hours, clinically indicated group 26,885 hours). More patients in the routine change group had an active infection (53% vs. 44%) and were receiving IV antibiotics (73% vs. 64%). However, as shown in Tables 1 and 2, the two groups were generally comparable at baseline for patient- and cannula-related factors. Figure 1Participant flowchart. Table 1 Baseline characteristics of study participants Variable 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) Sex - Male, n (%) 96 (54%) 103 (56%) Age, mean (SD) 65.1 (17.3) 62.7 (15.4) Reason for admission, n (%) • Gastrointestinal 46 (26%) 52 (28%) • Respiratory 37 (21%) 34 (18%) • Oncology 21 (12%) 21 (11%) • Orthopaedic 16 (9%) 22 (12%) • Cardiac 10 (6%) 10 (5%) • Neurological 9 (5%) 10 (5%) • Vascular 7 (4%) 7 (4%) • Renal 16 (9%) 9 (5%) • Other 15 (8%) 20 (11%) Number of comorbidities, n (%) • None 6 (3.4%) 10 (5.4%) • 1 22 (12.4%) 21 (11.4%) • 2 44 (24.9%) 54 (29.2%) • >2 105 (59.3%) 100 (54.1%) Type of surgery, n (%) • Nil 124 (70%) 132 (71%) • Gastrointestinal 22 (12%) 22 (12%) • Orthopaedic 8 (5%) 15 (8%) • Other 23 (13%) 16 (9%) Most recent Hb - Mean (SD) 124.8 (23.2) 126.2 (21.9) Table 2 Baseline infusion-related characteristics of study devices Variable 3-Day Routine Change Group (n = 323) , n (%) Clinically Indicated Change Group (n = 280) , n (%) IV cannula gauge • 22 43 (13%) 46 (16%) • 20 241 (75%) 201 (72%) • 18 27 (12%) 30 (11%) • Other 2 (1%) 3 (1%) Vein assessment • Good 143 (44.3%) 107 (38.2%) • Fair 160 (49.5%) 144 (51.4%) • Poor 20 (6.2%) 29 (10.4%) Skin integrity • Good 138 (43%) 104 (37%) • Fair 178 (55%) 164 (59%) • Poor 7 (2%) 12 (4%) Past history of phlebitis 2 (0.6%) 4 (1.4%) Insertion site • Hand 206 (64%) 187 (67%) • Forearm 59 (18%) 49 (18%) • Cubital fossa 51 (16%) 38 (14%) • Other 7 (2%) 6 (2%) Receiving infusate 241 (75%) 215 (77%) pH of infusate - Mean (SD) 6.0 (0.5) 6.0 (0.4) Receiving oral antibiotics 24 (7%) 24 (9%) Receiving IV antibiotics 236 (73%) 176 (63%) pH of IV antibiotics - Mean (SD) 6.9 (1.1) 6.9 (1.3) Receiving other IV meds 190 (59%) 179 (64%) pH of other IV meds - Mean (SD) 5.6 (2.6) 6.0 (2.8) Wound drain 50 (16%) 40 (14%) Urinary catheter 55 (17%) 41 (15%) Other vascular device 26 (8%) 24 (9%) Inserted by • Junior doctor 232 (72%) 207 (74%) • Registered Nurse 67 (21%) 57 (20%) • Senior doctor 24 (7%) 16 (6%) Where inserted • Ward 216 (67%) 188 (67%) • Emergency department 74 (23%) 70 (25%) • Other 33 (10%) 22 (8%) Current infection (site) • Respiratory 97 (30%) 49 (18%) • Urinary 24 (7%) 19 (7%) • Wound 16 (5%) 15 (5%) • Other 29 (9%) 37 (13%) • >1 site 5 (2%) 4 (1%) N/A (none) 152 (47%) 156 (56%) Risk of phlebitis (Tagar scale) • Low 174 (54%) 144 (51%) • Medium 149 (46%) 136 (49%) • High 0 0 \n\nBODY.RESULTS.EFFECT OF INTERVENTION ON PRIMARY OUTCOME:\nOutcome data were available for all patients. Table 3 shows the rates of primary and secondary outcomes. Differences in complication rates between groups were not significantly different (routine replacement 66.0 per 1,000 IVD days; clinical replacement 67.8 per 1,000 IVD days; HR 1.03; 95% CI, 0.74-1.43; P = 0.86). As shown in Figure 2, the time to first complication per patient was also not significantly different between groups (Kaplan Meier [KM] with log rank P = 0.53). On crude rate per IVD, the catheters replaced on clinical indication had higher complication rates (110/280 or 39% vs. 91/323 or 28%; P = 0.004). However, total complication rates per patient (to deliver the course of IV therapy) were not significantly different (P = 0.39) between clinically indicated (76/185, 41%) and routine resite patients (64/177, 36%). Table 3 Effect of intervention on primary and secondary endpoints Outcomes 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) RR (95% CI) , P Value Primary: IVD complications per patient, n (%) 64 (36%) 76 (41%) RR 1.14 (0.88, 1.47), p = 0.39 IVD complications per 1000 IVD days 66.0 (95% CI 49.8, 82.1) 67.8 (95% CI 52.6, 83.1) HR 1.03 (0.74, 1.43), p = 0.86 Secondary: Phlebitis, n (%) 12 (7%) 18 (10%) RR 1.44 (0.71, 2.89), p = 0.34 Infiltration, n (%) 53 (30%) 61 (33%) RR 1.10 (0.81, 1.49), p = 0.57 Occlusion, n (%) 5 (3%) 4 (2%) RR 0.77 (0.21, 2.80), p = 0.75 Accidental removal, n (%) 11 (6%) 16 (9%) RR 1.39 (0.66, 2.92), p = 0.43 Local infection 0 0 - IVD-related BSI, n (%) 0 0 - IVD costs per patient, AUD$ mean (SD) $55.42 ($35.26) $43.35 ($26.78) Mean difference $12.07 (95%CI $5.57, $18.56), p < 0.001 Figure 2Kaplan-Meier survival curve of time to first intravenous device complication per patient (log rank, P = 0.53). Patient- and device-related variables considered in the multivariable model were older age, number of comorbidities (nil, one, two or more than two), smaller cannula size, poor skin or vein integrity, IV antibiotics, insertion by medical staff and study group. None of these were found to be statistically significant. The final Cox proportional hazards model after adjusting for time found study group was not a significant factor (HR 1.02; 95% CI, 0.77-1.36; P = 0.89). Variance-adjustment testing for potential multiple-failures per patient (cannula data) found no inconsistency in significant results compared to the main Cox model.\n\nBODY.RESULTS.PROTOCOL COMPLIANCE:\nCompliance with the study intervention was achieved in 78% (251 of 323) of routinely replaced IVDs removed at Day 3 and 100% (280 of 280) of IVDs resited on clinical indication. Noncompliance in the routine resite group was generally related to high staff workloads on that day or to staff's perception that the patient was soon to be discharged or have therapy completed, and so the IVD remained in situ beyond Day 3. A per protocol analysis was performed including only those patients in the routine replacement group whose IVDs were all actually removed by 96 hours (n = 251). This found no significant difference (KM with log rank P = 0.16) in the rate of complications between groups (routine replacement 92 per 1,000 IVD days vs. clinically indicated 68 per 1,000 IVD days).\n\nBODY.RESULTS.EFFECT OF INTERVENTION ON SECONDARY OUTCOMES:\nThere was no statistically significant difference in group outcomes for any phlebitis (P = 0.34), infiltration (P = 0.57), occlusion (P = 0.75), or accidental removal (P = 0.43). No cases of local infection or IVD-related bloodstream infection occurred in either group. For overall IVD therapy (total cannulation time per patient for all devices), clinically indicated devices had a median therapy of 120 hours (quartiles 86.5 and 172.5 hours), and those replaced routinely had median therapy of 113 hours (quartiles 72 and 172 hours) (P = 0.21). For individual IVD dwell times, the clinically indicated group devices had a median dwell time of 85 hours (quartiles 51 and 121 hours), and those replaced routinely had a median dwell time of 71 hours (quartiles 48 and 90 hours) (P < 0.001). The maximum IVD dwell time was 1,023 hours (43 days) in the clinical replacement group, and this cannula was still working well on removal for completion of therapy. The overall number of IVDs per patient was significantly less (P = 0.004) for those replaced on clinical indication (mean 1.5, SD 0.8, median 1, quartiles 1 and 2) than for those routinely replaced (mean 1.8, SD 1.1, median 1, quartiles 1 and 2). A total of 22% of patients in the routinely replaced group had three or more IVDs compared with 9% in the clinical indication group. A total of 82 (28%) IVDs in the routine replacement group were resited after 3 days despite functioning well and ongoing treatment being required. (The remainder removed at this time were no longer required and so not resited, or infusion failure had already occurred.) Mean hospital costs per patient for the course of IV therapy were significantly higher (P < 0.001) for those managed with routine resite (mean $55.42, SD $35.26) compared with resite on clinical indication (mean $43.35, SD $26.78).\n\nBODY.DISCUSSION:\nThe finding that 3-day routine resite was not an effective intervention was consistent across the intention-to-treat primary analysis and the per protocol analysis. There remained no effect when events were expressed per patient or per 1,000 IVD days. Neither composite nor individual complication rates differed between groups, and there were no cases of local or device-related bloodstream infection. It appears safe and practical to leave IVDs in situ as long as they are functioning well and are still needed for clinical treatments. All IVDs will fail eventually, but this study shows that artificially shortening the lifespan of individual catheters does not reduce the overall complication rates over the course of therapy. Our results indicate that the average duration of IV therapy is 5-6 days and that many catheters can remain complication-free for this period. If catheters are not routinely resited, the median dwell time would remain within the 72-96 hours recommended by the CDC, but about 10% would remain in situ for longer (in this study up to 43 days with no complications). Our data show that a policy of resite on clinical indication would mean that one of every two patients would need a single cannula to receive treatment, whereas a 3-day change policy would result in only one in five patients having this scenario, with the rest requiring multiple cannulations and therefore additional pain and inconvenience. The results are consistent with the findings of recent RCTs in both hospitals and the community that have found no benefit in routinely resiting IVDs every 3 days [15-17]. In these studies, many cannulae were inserted by an expert IVD team [15-17], which may have minimised complications in both groups [19]. Our study confirms and extends these findings into the general medical/surgical setting without an IV team where IVDs were inserted by a variety of nursing and medical staff. Data from this study were included in a 2010 Cochrane Collaboration systematic review and meta-analysis on the topic [18]. This review included six trials (n = 3,455) and reported no clinically important or statistically significant difference in catheter-related bloodstream infection or phlebitis between IVDs that were routinely resited (at 48-96 hours) or resited on clinical indication, yet there were significantly lower costs in the group resited on clinical indication [18]. The belief that routine resite of IVDs will prevent complications appears to stem from early observational studies that noted longer-dwelling IVDs had more complications than shorter-dwelling IVDs [9,10]. This is intuitively true, given, for example, that an IVD in situ for 6 days has twice the time exposure of risk than an IVD in situ for 3 days. However, this does not prove that two sequentially inserted IVDs (in the same patient), both used for 3 days, have a combined lower risk over time than the 6-day dwell device. Indeed, this and other recent trials strongly suggest that the risk for the patient over the 6-day period is similar. Well-designed cohort studies with modern catheter materials suggest that the daily risk of phlebitis is relatively stable after the first 24 or 48 hours [3,21,28-31]. The peak in phlebitis between 24 and 48 hours is likely associated with the time taken by the body to mount a biological response after the instigation of therapy; those most likely to develop phlebitis will do so at this time. The results support the extension of the use of peripheral IVDs beyond the 72-96 hours currently recommended by the CDC [7]. There is incongruity in the CDC recommendations; they recommend not to routinely resite IVDs in children or in those with limited venous access. If it is safe in these populations, it is unclear why it would be necessary to routinely resite adults or those with better veins. Higher-risk cannulae such as central venous devices are no longer recommended by the CDC for routine replacement, because trials showed this was not of benefit [7]. Our study also confirms that the CDC guidelines are not always complied with; one fifth of IVDs in the routine change group were not replaced by this time. However, the per protocol analysis showed that the intervention remained ineffective even for those who truly had their IVDs resited every 3 days. Limitations of the study included a 9% higher frequency of IV antibiotics and concurrent infection in the routine resite group. This may have put the group at higher risk due to vein irritation, or conversely it protected against bacterial entry. Neither variable was significant in the multivariable model. The unblinded study design was unavoidable, but also a limitation. Our use of clear outcome measures, a full-time research nurse and laboratory staff blinded to culture assessments should have reduced the risk for potential bias. Resource constraints prematurely ended recruitment, thus reducing the anticipated power of the study from 90% to 80%. Routine IVD resite involves pain for patients, staff procedural time, equipment costs and environmental waste. Contemporary evidence suggests the current policy for routine resite by 72-96 hours is ineffective and should be replaced with a 'resite on clinical indication' policy. It remains imperative that clinical staff monitor IVDs closely and that a daily review of the need for continuing therapy be made, with cessation as soon as possible; the only no-risk IVD is no IVD. Of the 4.3 million acute hospital admissions in Australia each year (excluding day cases), over half have IV treatment [15,32]. Conservatively, if even 2 million courses of IV therapy were managed with clinically indicated rather than routine resite, this would save the unnecessary insertion of approximately 660,000 IVDs and free 280,000 hours of staff insertion time. Assuming our costs are similar to those in other Australian hospitals, a change to resite on clinical indication would save approximately AUD$24 million nationally each year.\n\nBODY.CONCLUSIONS:\nAlthough larger, multisite trials are required, evidence to date suggests that routine resite of peripheral IVDs increases patient discomfort and healthcare costs, but does not reduce IVD complications as has traditionally been thought.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCMR designed the study, applied for funding and drafted the manuscript. DM participated in study design and manuscript preparation, and managed the study. JM recruited patients, ensured protocol integrity and collected data. MRM undertook statistical analyses and assisted with drafting the manuscript. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nCMR, PhD is Professor, Research Centre for Clinical and Community Practice Innovation, Griffith University, Australia. DM holds a Masters by Research and is Senior Lecturer, University of Tasmania, Australia. JM is an RN and Nurse Unit Manager, Calvary Tasmania, Australia. MRM is a PhD qualified Biostatistician, Gippsland Medical School, Monash University, Australia.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1741-7015/8/53/prepub\n\n**Question:** Compared to routine replacement what was the result of staff inclination replacement on IVD dwell times?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
163
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on Berg Balance Scale score?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
140
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on HOMA-IR?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
106
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on HbA1c level at 26 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
169
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Parasite clearance at day 2?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
162
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on Physical performance battery scores?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
142
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Reductions in systolic blood pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
178
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Parasitaemias associated with gametocytaemia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
149
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Pulse variations?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
196
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Midwife-led unit on Pain relief: Epidural anesthesia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
148
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Pulse variations?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
152
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Incidence of minor hypoglycaemia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
92
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Routine resite of peripheral intravenous devices every 3 days did not reduce complications compared with clinically indicated resite: a randomised controlled trial\n\n ABSTRACT.BACKGROUND:\nPeripheral intravenous device (IVD) complications were traditionally thought to be reduced by limiting dwell time. Current recommendations are to resite IVDs by 96 hours with the exception of children and patients with poor veins. Recent evidence suggests routine resite is unnecessary, at least if devices are inserted by a specialised IV team. The aim of this study was to compare the impact of peripheral IVD 'routine resite' with 'removal on clinical indication' on IVD complications in a general hospital without an IV team.\n\nABSTRACT.METHODS:\nA randomised, controlled trial was conducted in a regional teaching hospital. After ethics approval, 362 patients (603 IVDs) were randomised to have IVDs replaced on clinical indication (185 patients) or routine change every 3 days (177 patients). IVDs were inserted and managed by the general hospital medical and nursing staff; there was no IV team. The primary endpoint was a composite of IVD complications: phlebitis, infiltration, occlusion, accidental removal, local infection, and device-related bloodstream infection.\n\nABSTRACT.RESULTS:\nIVD complication rates were 68 per 1,000 IVD days (clinically indicated) and 66 per 1,000 IVD days (routine replacement) (P = 0.86; HR 1.03; 95% CI, 0.74-1.43). Time to first complication per patient did not differ between groups (KM with log rank, P = 0.53). There were no local infections or IVD-related bloodstream infections in either group. IV therapy duration did not differ between groups (P = 0.22), but more (P = 0.004) IVDs were placed per patient in the routine replacement (mean, 1.8) than the clinical indication group (mean, 1.5), with significantly higher hospital costs per patient (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nResite on clinical indication would allow one in two patients to have a single cannula per course of IV treatment, as opposed to one in five patients managed with routine resite; overall complication rates appear similar. Clinically indicated resite would achieve savings in equipment, staff time and patient discomfort. There is growing evidence to support the extended use of peripheral IVDs with removal only on clinical indication.\n\nABSTRACT.REGISTRATION NUMBER:\nAustralian New Zealand Clinical Trials Registry (ANZCTR) Number ACTRN12608000421336.\n\nBODY.BACKGROUND:\nPeripheral intravenous device (IVD) insertion is the most commonly performed invasive procedure in hospitalised patients, with an estimated 150 million peripheral intravenous devices placed each year in North America alone [1]. IVDs are vital for delivery of hydration, medicines and nutrition but are not without complications. Serious adverse outcomes are fortunately rare, with IVD-related bloodstream infection reported in a recent meta-analysis of 110 studies to occur in 0.1% of devices and 0.5 per 1,000 device days [2]. IVD treatment is more frequently interrupted by phlebitis, an irritation of the vein characterised by pain, tenderness on palpation, erythema, warmth, swelling, induration or palpable cord (thrombosis) of the cannulated vein; diagnostic algorithms usually require two or more of these conditions [3-5]. Phlebitis is in almost all cases a biochemical reaction to the mechanical irritation by the presence of the IVD and associated infusate [3], although phlebitis symptoms such as erythema may be misperceived as indicative of an infection. In fact, there is not a high correlation between phlebitis and device infection, and the Centers for Disease Control (CDC) states that infection is rarely associated with peripheral, as opposed to central, venous devices [3,6,7]. Fluid infiltration or 'tissuing' of devices is another common IVD complication which may also reflect the inflammatory (phlebitic) response of the vein, rather than simple misplacement of the device tip [8]. Early cohort studies noted an association between increased device time in situ and phlebitis [9,10]. This association was responded to with policies for routine device removal. Recommended timelines for routine resite have been extended over the past three decades from 24, to 48, then to 72 hours. Currently, 72- to 96-hour resite is recommended to reduce phlebitis by the CDC's 2002 Guidelines for the Prevention of Intravascular Device Infection, with the exemption that this is not required in children or those with poor veins [7]. Such policies cause increased workload in hospitals, where the task of removing and replacing well-functioning IVDs generally falls to busy nursing and junior medical staff. In addition, few patients welcome the prospect of additional venipuncture. Despite the general clinical acceptance of routine IVD replacement as a phlebitis and infection prevention measure, it has not been supported by recent data. It may be that the risk of complications during the entire IVD treatment episode is similar, regardless of whether multiple short-dwell or fewer longer-dwell IVDs are used over this time. Three small (n = 47-60) randomised, controlled trials (RCTs) suggested routine replacement at 12, 24 or 48 hours may reduce phlebitis compared to resite on clinical indication, although a systematic review for the Swedish Council on Technology Assessment in Healthcare assessed these as low- to medium-quality studies providing 'limited scientific evidence' [11-14]. More recently, two well-conducted RCTs found no evidence of effect when comparing IVD replacement every 3 days with replacement only on clinical indication for medical and surgical inpatients [15,16]. The largest of these studies reported findings from 755 general medical and surgical patients with 1,428 IVDs and found a 5% difference in combined phlebitis and infiltration rates per patient (38% clinically indicated resite, 33% routine resite), suggesting a potential small clinical benefit of 3-day resite [15]. However, this difference was not statistically significant (RR 1.15; 95% CI, 0.95-1.40) and disappeared when overall cannulation time was considered (59.8/1,000 IVD days clinically indicated resite, 60.9/1,000 IVD days routine resite; RR 0.98; 95% CI 0.78-1.24) [15]. In addition, no clinically important or statistically significant differences were observed in the secondary endpoints of phlebitis, infiltration, occlusion, local infection or suspected bloodstream infection rates between study groups [15]. Another recent RCT in the 'hospital in the home' community setting also found no important clinical or statistically significant difference in phlebitis, occlusion or bloodstream infection rates in 316 patients when resite every 3 days was compared with clinically indicated resite [17]. A 2010 Cochrane Collaboration review concluded there was 'no conclusive evidence of benefit' of routine IVD resite and suggested organisations could consider adopting a resite on clinical indication policy [18]. There is growing evidence that routine IVD replacement may be ineffective, although caution has been urged in light of the large number (74% in both groups in the largest study to date) of reported devices inserted by a specialised IV team, a factor known to reduce complications [19]. Device insertion (and reinsertion) is unpleasant for patients, requires skilled and available clinical staff, and has associated costs for the health sector. If replacement only on clinical indication is safe and effective, this would have important benefits for patients and the health system. We report a RCT of 3-day routine IVD resite versus clinically indicated replacement in a medical-surgical hospital where IVDs were inserted by the general medical and nursing staff; the insitution did not have a specialised IV service.\n\nBODY.METHODS.AIM:\nThe aim of the study was to compare the impact of 3-day routine resite, with clinically indicated resite, on peripheral IVD complications.\n\nBODY.METHODS.DESIGN:\nOpen (nonblinded), parallel group RCT.\n\nBODY.METHODS.ETHICS:\nThe study was approved by the Tasmanian State Human Research Ethics Committee. Written informed consent was obtained prospectively from all participants.\n\nBODY.METHODS.SETTING AND SAMPLE:\nThe study was undertaken at a large regional teaching hospital in Australia which functions as the tertiary referral centre for the northern half of the State of Tasmania. The hospital has more than 32,000 separations per annum, with a spectrum of medical and surgical specialties. Eligible patients were at least 18 years of age and scheduled or expected to have a peripheral IVD indwelling for at least 4 days, and they gave written informed consent. Exclusion criteria were immunosuppression, current bloodstream infection or an IVD already in situ for >48 hours. IVDs were inserted and cared for by the general nursing and medical staff; there was no special IV team or service.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size calculations were performed using PASS 2008 (Version 8.0.8; Kaysville, UT) to detect a change in rates by 30% (from 36% to 25%, two-tailed α = 0.05, 90% power) on the basis of the complication rates of routinely resited IVs in a previous study [16]. Although this indicated that n = 378 per group (total 756) were required, the study was ceased early (total n = 606 IVs) because all investigators left the employment of the institution. Consequently, study power was reduced, but remained over 80% (required minimum n = 282 per group).\n\nBODY.METHODS.RECRUITMENT:\nAll adult patients admitted to the inpatient acute medical and surgical wards of the study hospital were screened by a full-time research nurse. This excluded paediatric, day-surgery, mental health, obstetric, critical care and dialysis units.\n\nBODY.METHODS.STUDY PROCEDURES:\nPatients were randomly assigned (computer generated) in a 1:1 allocation ratio to either the 'routine replacement' (control) or 'clinically indicated replacement' (intervention) group. Assignment was concealed until randomisation by use of a telephone service. A tag was placed on the insertion site indicating the study group. All devices for the patient were managed as per randomised group. The intervention group did not have their IVD resited unless clinically indicated. This decision was made by the treating clinician (not the investigators), who ordered IVD resite if the device failed or phlebitis occurred and ongoing IV treatment was required. The control group had a new device relocated to a different site by the general medical or nursing staff every 3 days. Control devices could also be removed at any stage by the clinical staff if they were not required or if complications occurred. Clinical nursing and medical staff undertook insertion and follow-up care of all IVDs as per the CDC Guidelines [7]. Laboratory staff undertaking microbiological culture assessments were blinded to the study group. Due to the nature of the intervention, patients, research, and clinical staff were unable to be blinded. However, the investigators had no involvement in assessing or documenting complications. IVDs were assessed by the clinical nursing staff on each nursing shift for complications as part of standard clinical practice in the hospital. Times and dates of device insertion and removal were recorded along with the reason for device removal and any protocol deviations. A full-time research nurse collected data from the hospital chart and sought clarification from patients and clinical staff if necessary. Microbiological investigations (device tip, blood cultures and site cultures) were performed by the clinical staff on clinical suspicion of infection by the treating clinician. Demographic and clinical data were collected on age, sex, diagnosis at hospital admission, phlebitis risk based on Tagar et al.'s classification (low/medium/high risk) [20], past history of phlebitis, any comorbidities requiring active medical treatment (e.g., type 2 diabetes or congestive heart failure), haemoglobin, concurrent infection at other sites, antibiotic therapy, type of surgery, type of infusate and any additives (and their level of irritability), vein and skin quality assessment, size of device, insertion site, health professional inserting the device, and setting for insertion, presence of other vascular devices, wound drains and urinary catheters. Vein quality was assessed as good (vein easy to visualise and easy to palpate with tourniquet on), fair (not easily visible but can palpate with tourniquet), or poor (veins small, scarred or difficult to palpate with tourniquet; may require heat pack to aid vasodilation). Skin quality was assessed as good (healthy, well hydrated, elastic), fair (mildly dehydrated, reduced elasticity), or poor (papery, dehydrated, or reduced elasticity).\n\nBODY.METHODS.ANALYTIC APPROACH:\nThe primary outcome was a composite measure of any complication causing unplanned cannula removal prior to completion of IV treatment. The composite included phlebitis, infiltration, occlusion, accidental removal, local infection, and IV device-related bloodstream infection (IVD-BSI). These were also analysed individually as secondary endpoints. A composite measure was chosen due to the low rates of these conditions individually and to the assumption that they are comparable measures of 'infusion failure'; that is, the device can no longer be used to deliver treatment. This approach has been used in previous studies on the topic [15-17]. Phlebitis was defined as two or more of pain, erythema, purulence, streak formation, or a palpable venous cord [3]. Local infection IVD-BSI (bacteremia/fungemia with at least one positive blood culture obtained from a peripheral vein, clinical manifestations of infection, and no apparent source for the bloodstream infection (BSI) except the device with or without positive tip or entry site swab culture) were defined using CDC criteria [7]. Other secondary outcomes were time in situ (hours of catheterisation from insertion to removal, both per patient and per device) [7]; IVDs per patient (number of peripheral devices inserted to complete the course of treatment) [7]; costs (calculations based on 20 minutes nursing or medical insertion time at relevant rates [15], plus the cost of the required equipment (cannula, insertion pack including dressing and solution, gloves, saline, syringe, extension tubing and starter pack for all plus fluid bag, tubing and secondary tubing for medication administration for those patients requiring this) for insertions, nursing time and equipment to routinely remove IVDs that were otherwise functional, and the costs of treating any complications that occurred (e.g., IVD-BSI). Cost calculations were undertaken from the viewpoint of the hospital using negotiated wage costs and purchasing agreements for government hospitals in the State of Tasmania. Costs would be similar for other Australian hospitals. All randomised patients were analysed by intention to treat. Each patient was randomised once and could have multiple IVDs, with subsequent IVD resites managed as per the randomised group. Relative incidence complication rates per 1,000 IVD days and 95% confidence intervals were calculated to summarise the impact of clinically indicated replacement relative to 3-day replacement. Kaplan-Meier survival curves were drawn to compare time to first IVD complication between patients in the two study groups. To assess for any potential impact of protocol violations, a per protocol analysis was also undertaken. All clinical and demographic variables were subjected to univariate testing against the primary endpoint to guide selection of possible covariates for the multivariable model. Cox proportional hazards regression modelling was used to examine the impact of age, gender, oncology status, number of comorbidities (nil, one, two, or more than two), IV gauge, site, vein quality, skin quality, oral antibiotics, IV antibiotics, wound drain, inserter occupation, initial versus subsequent IVDs, phlebitis in a preceeding IVD, haemoglobin level, parenteral nutrition, continuous versus intermittent infusion, patient risk category and study group on the outcome of time to complication events using an additive model [3,5,7,20-25]. In addition, to adjust for any inherent correlations or codependencies in the failure times of IVDs (i.e., same patient multiple failure-time data) within the Cox model, we also used the Prentice-Williams-Peterson conditional risk-set method [26]. The Mann-Whitney test was used to compare various secondary outcomes between study groups. Cost differences were calculated using arithmetic means and the t-test [27]. P values <0.05 were considered significant. All statistical data were entered and analysed using SPSS (Version 15.0; Chicago, IL) and Stata (Version 8.2; College Station, TX).\n\nBODY.RESULTS.SAMPLE:\nOver a 10-month period, 1,954 patients were screened for eligibility. Of these, 788 were eligible, with 362 (46%) recruited into the study. The most frequent exclusion criterion was altered mental state that precluded consideration of consent as assessed by the research nurse. Altered mental state was generally related to older medical patients and the immediate postoperative phase for surgical patients. Reasons for exclusion are shown in Figure 1. The 362 patients were randomised into either the routine change group (n = 177 participants, 323 devices) or the clinically indicated replacement group (n = 185 participants, 280 devices). In total 50,173 IVD hours were studied (routine change group 23,288 hours, clinically indicated group 26,885 hours). More patients in the routine change group had an active infection (53% vs. 44%) and were receiving IV antibiotics (73% vs. 64%). However, as shown in Tables 1 and 2, the two groups were generally comparable at baseline for patient- and cannula-related factors. Figure 1Participant flowchart. Table 1 Baseline characteristics of study participants Variable 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) Sex - Male, n (%) 96 (54%) 103 (56%) Age, mean (SD) 65.1 (17.3) 62.7 (15.4) Reason for admission, n (%) • Gastrointestinal 46 (26%) 52 (28%) • Respiratory 37 (21%) 34 (18%) • Oncology 21 (12%) 21 (11%) • Orthopaedic 16 (9%) 22 (12%) • Cardiac 10 (6%) 10 (5%) • Neurological 9 (5%) 10 (5%) • Vascular 7 (4%) 7 (4%) • Renal 16 (9%) 9 (5%) • Other 15 (8%) 20 (11%) Number of comorbidities, n (%) • None 6 (3.4%) 10 (5.4%) • 1 22 (12.4%) 21 (11.4%) • 2 44 (24.9%) 54 (29.2%) • >2 105 (59.3%) 100 (54.1%) Type of surgery, n (%) • Nil 124 (70%) 132 (71%) • Gastrointestinal 22 (12%) 22 (12%) • Orthopaedic 8 (5%) 15 (8%) • Other 23 (13%) 16 (9%) Most recent Hb - Mean (SD) 124.8 (23.2) 126.2 (21.9) Table 2 Baseline infusion-related characteristics of study devices Variable 3-Day Routine Change Group (n = 323) , n (%) Clinically Indicated Change Group (n = 280) , n (%) IV cannula gauge • 22 43 (13%) 46 (16%) • 20 241 (75%) 201 (72%) • 18 27 (12%) 30 (11%) • Other 2 (1%) 3 (1%) Vein assessment • Good 143 (44.3%) 107 (38.2%) • Fair 160 (49.5%) 144 (51.4%) • Poor 20 (6.2%) 29 (10.4%) Skin integrity • Good 138 (43%) 104 (37%) • Fair 178 (55%) 164 (59%) • Poor 7 (2%) 12 (4%) Past history of phlebitis 2 (0.6%) 4 (1.4%) Insertion site • Hand 206 (64%) 187 (67%) • Forearm 59 (18%) 49 (18%) • Cubital fossa 51 (16%) 38 (14%) • Other 7 (2%) 6 (2%) Receiving infusate 241 (75%) 215 (77%) pH of infusate - Mean (SD) 6.0 (0.5) 6.0 (0.4) Receiving oral antibiotics 24 (7%) 24 (9%) Receiving IV antibiotics 236 (73%) 176 (63%) pH of IV antibiotics - Mean (SD) 6.9 (1.1) 6.9 (1.3) Receiving other IV meds 190 (59%) 179 (64%) pH of other IV meds - Mean (SD) 5.6 (2.6) 6.0 (2.8) Wound drain 50 (16%) 40 (14%) Urinary catheter 55 (17%) 41 (15%) Other vascular device 26 (8%) 24 (9%) Inserted by • Junior doctor 232 (72%) 207 (74%) • Registered Nurse 67 (21%) 57 (20%) • Senior doctor 24 (7%) 16 (6%) Where inserted • Ward 216 (67%) 188 (67%) • Emergency department 74 (23%) 70 (25%) • Other 33 (10%) 22 (8%) Current infection (site) • Respiratory 97 (30%) 49 (18%) • Urinary 24 (7%) 19 (7%) • Wound 16 (5%) 15 (5%) • Other 29 (9%) 37 (13%) • >1 site 5 (2%) 4 (1%) N/A (none) 152 (47%) 156 (56%) Risk of phlebitis (Tagar scale) • Low 174 (54%) 144 (51%) • Medium 149 (46%) 136 (49%) • High 0 0 \n\nBODY.RESULTS.EFFECT OF INTERVENTION ON PRIMARY OUTCOME:\nOutcome data were available for all patients. Table 3 shows the rates of primary and secondary outcomes. Differences in complication rates between groups were not significantly different (routine replacement 66.0 per 1,000 IVD days; clinical replacement 67.8 per 1,000 IVD days; HR 1.03; 95% CI, 0.74-1.43; P = 0.86). As shown in Figure 2, the time to first complication per patient was also not significantly different between groups (Kaplan Meier [KM] with log rank P = 0.53). On crude rate per IVD, the catheters replaced on clinical indication had higher complication rates (110/280 or 39% vs. 91/323 or 28%; P = 0.004). However, total complication rates per patient (to deliver the course of IV therapy) were not significantly different (P = 0.39) between clinically indicated (76/185, 41%) and routine resite patients (64/177, 36%). Table 3 Effect of intervention on primary and secondary endpoints Outcomes 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) RR (95% CI) , P Value Primary: IVD complications per patient, n (%) 64 (36%) 76 (41%) RR 1.14 (0.88, 1.47), p = 0.39 IVD complications per 1000 IVD days 66.0 (95% CI 49.8, 82.1) 67.8 (95% CI 52.6, 83.1) HR 1.03 (0.74, 1.43), p = 0.86 Secondary: Phlebitis, n (%) 12 (7%) 18 (10%) RR 1.44 (0.71, 2.89), p = 0.34 Infiltration, n (%) 53 (30%) 61 (33%) RR 1.10 (0.81, 1.49), p = 0.57 Occlusion, n (%) 5 (3%) 4 (2%) RR 0.77 (0.21, 2.80), p = 0.75 Accidental removal, n (%) 11 (6%) 16 (9%) RR 1.39 (0.66, 2.92), p = 0.43 Local infection 0 0 - IVD-related BSI, n (%) 0 0 - IVD costs per patient, AUD$ mean (SD) $55.42 ($35.26) $43.35 ($26.78) Mean difference $12.07 (95%CI $5.57, $18.56), p < 0.001 Figure 2Kaplan-Meier survival curve of time to first intravenous device complication per patient (log rank, P = 0.53). Patient- and device-related variables considered in the multivariable model were older age, number of comorbidities (nil, one, two or more than two), smaller cannula size, poor skin or vein integrity, IV antibiotics, insertion by medical staff and study group. None of these were found to be statistically significant. The final Cox proportional hazards model after adjusting for time found study group was not a significant factor (HR 1.02; 95% CI, 0.77-1.36; P = 0.89). Variance-adjustment testing for potential multiple-failures per patient (cannula data) found no inconsistency in significant results compared to the main Cox model.\n\nBODY.RESULTS.PROTOCOL COMPLIANCE:\nCompliance with the study intervention was achieved in 78% (251 of 323) of routinely replaced IVDs removed at Day 3 and 100% (280 of 280) of IVDs resited on clinical indication. Noncompliance in the routine resite group was generally related to high staff workloads on that day or to staff's perception that the patient was soon to be discharged or have therapy completed, and so the IVD remained in situ beyond Day 3. A per protocol analysis was performed including only those patients in the routine replacement group whose IVDs were all actually removed by 96 hours (n = 251). This found no significant difference (KM with log rank P = 0.16) in the rate of complications between groups (routine replacement 92 per 1,000 IVD days vs. clinically indicated 68 per 1,000 IVD days).\n\nBODY.RESULTS.EFFECT OF INTERVENTION ON SECONDARY OUTCOMES:\nThere was no statistically significant difference in group outcomes for any phlebitis (P = 0.34), infiltration (P = 0.57), occlusion (P = 0.75), or accidental removal (P = 0.43). No cases of local infection or IVD-related bloodstream infection occurred in either group. For overall IVD therapy (total cannulation time per patient for all devices), clinically indicated devices had a median therapy of 120 hours (quartiles 86.5 and 172.5 hours), and those replaced routinely had median therapy of 113 hours (quartiles 72 and 172 hours) (P = 0.21). For individual IVD dwell times, the clinically indicated group devices had a median dwell time of 85 hours (quartiles 51 and 121 hours), and those replaced routinely had a median dwell time of 71 hours (quartiles 48 and 90 hours) (P < 0.001). The maximum IVD dwell time was 1,023 hours (43 days) in the clinical replacement group, and this cannula was still working well on removal for completion of therapy. The overall number of IVDs per patient was significantly less (P = 0.004) for those replaced on clinical indication (mean 1.5, SD 0.8, median 1, quartiles 1 and 2) than for those routinely replaced (mean 1.8, SD 1.1, median 1, quartiles 1 and 2). A total of 22% of patients in the routinely replaced group had three or more IVDs compared with 9% in the clinical indication group. A total of 82 (28%) IVDs in the routine replacement group were resited after 3 days despite functioning well and ongoing treatment being required. (The remainder removed at this time were no longer required and so not resited, or infusion failure had already occurred.) Mean hospital costs per patient for the course of IV therapy were significantly higher (P < 0.001) for those managed with routine resite (mean $55.42, SD $35.26) compared with resite on clinical indication (mean $43.35, SD $26.78).\n\nBODY.DISCUSSION:\nThe finding that 3-day routine resite was not an effective intervention was consistent across the intention-to-treat primary analysis and the per protocol analysis. There remained no effect when events were expressed per patient or per 1,000 IVD days. Neither composite nor individual complication rates differed between groups, and there were no cases of local or device-related bloodstream infection. It appears safe and practical to leave IVDs in situ as long as they are functioning well and are still needed for clinical treatments. All IVDs will fail eventually, but this study shows that artificially shortening the lifespan of individual catheters does not reduce the overall complication rates over the course of therapy. Our results indicate that the average duration of IV therapy is 5-6 days and that many catheters can remain complication-free for this period. If catheters are not routinely resited, the median dwell time would remain within the 72-96 hours recommended by the CDC, but about 10% would remain in situ for longer (in this study up to 43 days with no complications). Our data show that a policy of resite on clinical indication would mean that one of every two patients would need a single cannula to receive treatment, whereas a 3-day change policy would result in only one in five patients having this scenario, with the rest requiring multiple cannulations and therefore additional pain and inconvenience. The results are consistent with the findings of recent RCTs in both hospitals and the community that have found no benefit in routinely resiting IVDs every 3 days [15-17]. In these studies, many cannulae were inserted by an expert IVD team [15-17], which may have minimised complications in both groups [19]. Our study confirms and extends these findings into the general medical/surgical setting without an IV team where IVDs were inserted by a variety of nursing and medical staff. Data from this study were included in a 2010 Cochrane Collaboration systematic review and meta-analysis on the topic [18]. This review included six trials (n = 3,455) and reported no clinically important or statistically significant difference in catheter-related bloodstream infection or phlebitis between IVDs that were routinely resited (at 48-96 hours) or resited on clinical indication, yet there were significantly lower costs in the group resited on clinical indication [18]. The belief that routine resite of IVDs will prevent complications appears to stem from early observational studies that noted longer-dwelling IVDs had more complications than shorter-dwelling IVDs [9,10]. This is intuitively true, given, for example, that an IVD in situ for 6 days has twice the time exposure of risk than an IVD in situ for 3 days. However, this does not prove that two sequentially inserted IVDs (in the same patient), both used for 3 days, have a combined lower risk over time than the 6-day dwell device. Indeed, this and other recent trials strongly suggest that the risk for the patient over the 6-day period is similar. Well-designed cohort studies with modern catheter materials suggest that the daily risk of phlebitis is relatively stable after the first 24 or 48 hours [3,21,28-31]. The peak in phlebitis between 24 and 48 hours is likely associated with the time taken by the body to mount a biological response after the instigation of therapy; those most likely to develop phlebitis will do so at this time. The results support the extension of the use of peripheral IVDs beyond the 72-96 hours currently recommended by the CDC [7]. There is incongruity in the CDC recommendations; they recommend not to routinely resite IVDs in children or in those with limited venous access. If it is safe in these populations, it is unclear why it would be necessary to routinely resite adults or those with better veins. Higher-risk cannulae such as central venous devices are no longer recommended by the CDC for routine replacement, because trials showed this was not of benefit [7]. Our study also confirms that the CDC guidelines are not always complied with; one fifth of IVDs in the routine change group were not replaced by this time. However, the per protocol analysis showed that the intervention remained ineffective even for those who truly had their IVDs resited every 3 days. Limitations of the study included a 9% higher frequency of IV antibiotics and concurrent infection in the routine resite group. This may have put the group at higher risk due to vein irritation, or conversely it protected against bacterial entry. Neither variable was significant in the multivariable model. The unblinded study design was unavoidable, but also a limitation. Our use of clear outcome measures, a full-time research nurse and laboratory staff blinded to culture assessments should have reduced the risk for potential bias. Resource constraints prematurely ended recruitment, thus reducing the anticipated power of the study from 90% to 80%. Routine IVD resite involves pain for patients, staff procedural time, equipment costs and environmental waste. Contemporary evidence suggests the current policy for routine resite by 72-96 hours is ineffective and should be replaced with a 'resite on clinical indication' policy. It remains imperative that clinical staff monitor IVDs closely and that a daily review of the need for continuing therapy be made, with cessation as soon as possible; the only no-risk IVD is no IVD. Of the 4.3 million acute hospital admissions in Australia each year (excluding day cases), over half have IV treatment [15,32]. Conservatively, if even 2 million courses of IV therapy were managed with clinically indicated rather than routine resite, this would save the unnecessary insertion of approximately 660,000 IVDs and free 280,000 hours of staff insertion time. Assuming our costs are similar to those in other Australian hospitals, a change to resite on clinical indication would save approximately AUD$24 million nationally each year.\n\nBODY.CONCLUSIONS:\nAlthough larger, multisite trials are required, evidence to date suggests that routine resite of peripheral IVDs increases patient discomfort and healthcare costs, but does not reduce IVD complications as has traditionally been thought.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCMR designed the study, applied for funding and drafted the manuscript. DM participated in study design and manuscript preparation, and managed the study. JM recruited patients, ensured protocol integrity and collected data. MRM undertook statistical analyses and assisted with drafting the manuscript. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nCMR, PhD is Professor, Research Centre for Clinical and Community Practice Innovation, Griffith University, Australia. DM holds a Masters by Research and is Senior Lecturer, University of Tasmania, Australia. JM is an RN and Nurse Unit Manager, Calvary Tasmania, Australia. MRM is a PhD qualified Biostatistician, Gippsland Medical School, Monash University, Australia.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1741-7015/8/53/prepub\n\n**Question:** Compared to staff inclination replacement what was the result of routine replacement on phlebitis?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
154
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on Changes in calcitonin at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
125
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Postprandial plasma glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
121
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on ADA fasting plasma glucose goals between 5.0 mmol/l and less than 7.2 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
207
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Immunogenicity and Smoking Cessation Outcomes for a Novel Nicotine Immunotherapeutic\n\n ABSTRACT:\nNicVAX®, a nicotine vaccine (3'AmNic-rEPA), has been clinically evaluated to determine if higher antibody concentrations are associated with higher smoking abstinence rates and if doses and frequency of administration are associated with increased antibody response. This randomized, double-blinded, placebo-controlled multicenter clinical trial (N=301 smokers) tested 200 and 400 μg doses administered 4 or 5 times over 6 months compared to placebo. 3'AmNic-rEPA recipients with the highest serum anti-nicotine antibody response (top 30% by AUC) were significantly more likely to attain 8 weeks continuous abstinence from weeks 19 through 26 than the placebo recipients (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). The 5 injection 400 μg dose regimen had the greatest antibody response and had significantly higher abstinence rates than placebo. This study demonstrates proof-of-concept that 3'AmNic-rEPA elicits antibodies to nicotine and is associated with higher continuous abstinence rates, justifying its further development as a treatment for nicotine dependence.\n\nBODY.INTRODUCTION:\nWorldwide, smoking prevalence is 1.2 billion and approximately 5 million people die each year of smoking caused illnesses [1]. The global rate of smoking and smoking related deaths is anticipated to increase over the next 20 years unless significant public health measures are instituted. These include effective cessation interventions such as pharmacological treatments, which improve cessation rates by 1.5 to 3 fold over placebo intervention [2, 3]. Approved pharmacotherapies (e.g., nicotine replacements, bupropion SR, varenicline) for smoking cessation act on the central nervous system, each with a different mechanism of action. Other novel medications are being developed including immunotherapeutics targeting nicotine. Nicotine conjugate vaccines stimulate the immune system to develop nicotine specific antibodies (Abs) using an immunogen comprised of nicotine covalently linked to a larger carrier protein. Conceptually, the mechanism of action is that anti-nicotine antibodies bind nicotine molecules and the resulting complex is too large to cross the blood-brain barrier. With increasing Ab levels more nicotine is captured and sequestered in the blood and prevented from entering the brain, leading to less reinforcing effects from nicotine. Animal studies have demonstrated that passive or active immunization results in approximately 30% to 90% less nicotine entering the brain compared to control rats [4–7] and attenuated locomotor [4, 5] and behavioral [8, 9] responses to nicotine. Furthermore, vaccination reduced nicotine elimination from the body in a study with rats [10, 11], which may also contribute to reduced smoking. Although human studies are limited, published data evaluating different nicotine vaccines support the general concept that nicotine vaccines can be effective for smoking cessation in some smokers [12, 13]. Unfortunately, these studies either had small sample sizes [12], did not use an intent-to-treat population of smokers [13] or did not perform statistical analysis of the data [14]. The primary aim of the present study was to establish the proof-of-concept that (i) anti-nicotine antibodies are useful as an aid to smoking cessation and (ii) higher serum anti-nicotine antibody concentrations are associated with higher abstinence rates in an intent-to-treat population of smokers. One of the challenges with immunotherapeutics, such as vaccines, is attainment of therapeutic levels of antibody in most people. Therefore, this study tested two different doses of 3'-aminomethylnicotine P. aeruginosa r-exoprotein A - NicVAX (3'AmNic-rEPA) to identify a dose and schedule for further development: 200 and 400 μg across two different schedules (4 or 5 injections) compared to placebo for immunogenicity, efficacy and safety.\n\nBODY.RESULTS:\nA total of 301 subjects were randomized. Figure 2 shows the disposition and number of subjects within each treatment group. No significant group differences were observed in the demographic or smoking history by treatment or antibody levels (see Table 1).\n\nBODY.RESULTS.COMPLIANCE:\nAll 301 subjects received injection 1, 96.7%, 84.1%, 72.4% and 61.2% received injections 2, 3, 4 and 5 (Schedule 2 subjects only), respectively. No significant differences were observed across treatment groups for subjects receiving injections 2 through 4 for Schedules 1 and 2. Mean in-study duration was 286 ± 121 days.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON ABSTINENCE:\nHigh Ab responders to 3'AmNic-rEPA were defined as the top 30% of responders by AUC (0 to 26 weeks) and the low Ab group as the remaining bottom 70% of responders. 3'AmNic-rEPA recipients in the high Ab group were significantly more likely to attain 8 weeks of continuous abstinence from weeks 19 through 26 than placebo (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). No significant differences were observed between the 3'AmNic-rEPA low Ab group vs. placebo (9.3% vs. 12.0%., p=0.46). As a secondary outcome, continuous abstinence rate (CAR) to 52 weeks were evaluated from weeks 19 to 52 and were significantly higher for the high Ab group vs. placebo (19.7% vs. 10.0%, p=0.044, OR=2.64, 95% CI, 1.03–6.79) with no significant difference between the low Ab group and placebo (7.1% vs. 10.0%, p=0.43). 7-day point prevalence abstinence results show that subjects with high Ab levels were significantly more likely to abstain compared to placebo at 26 weeks (36.1% vs. 16.0%, p=0.0024, OR=3.30, 95% CI, 1.53–7.13) and 52 weeks (31.1% vs. 12.0%, p=0.0021, OR=3.69, 95% CI, 0.42–2.14). No significant differences were observed in the point prevalence abstinence rates between the low Ab group and placebo at 26 and 52 weeks (12.9% vs. 16.0%, p=0.51 and 11.4% vs. 12.0%, p=0.89, respectively). As shown in Figure 3A, abstinence rates remained essentially the same following the target quit date (TQD) for the duration of the study. To further validate the proof-of-concept, the relationship between abstinence during the final eight weeks of the study and anti-nicotine Ab concentrations (AUC) is shown in Figure 3B for all subjects receiving the vaccine. Continuous abstinence rates from week 45–52 are displayed for each 10th percentile increase in AUC. The proportion of abstinent subjects increased with increasing AUC percentile, and the ordered ranking maintained.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON TIME TO CONTINUOUS ABSTINENCE:\nAn exploratory analysis examined the rate and time to continuous abstinence through study end (Figure 3C). Most smokers quit soon after the TQD, with a clear divergence of the high Ab group from the placebo and low Ab group. Among the 18 high Ab continuous abstainers, 12 initiated abstinence prior to the primary endpoint while 6 initiated their abstinence after the start of the primary endpoint. Furthermore, 3 of the 15 subjects who abstained during the primary endpoint relapsed by the end of the study. Cox proportional hazards analysis demonstrated superiority of the high Ab group compared to placebo (p=0.0069, hazard ratio of 2.76).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EVALUATION OF LONG-TERM ABSTINENCE:\nAs most subjects achieved abstinence shortly after their TQD, additional analyses were undertaken to evaluate prolonged abstinence to 6 and 12 months allowing for a 2 week grace period after the TQD [15]. (Prolonged abstinence is defined as not a single puff during the period from 2 weeks after the TQD for 20 weeks and 44 weeks, respectively). Prolonged abstinence rates to 6 months were significantly higher in the high Ab group vs. placebo (19.7% vs. 6.0%, p=0.0060, OR=4.41, 95% CI, 1.53–12.71) with no significant differences between the placebo and low Ab groups (7.9% vs. 6.0%, p=0.60). Subjects with high Ab were also significantly more likely to be abstinent for 12 months compared to placebo (18.0% vs. 6.0%, p=0.014; OR of 3.84; 95% CI, 1.32–11.20). The low Ab group did not differ significantly from placebo (7.1% vs. 6.0%, p=0.67).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.CIGARETTE SMOKING IN NON-QUITTERS:\nStatistically significant differences were observed in reduction of daily cigarette consumption and cotinine between non-abstainers (weeks 19–52) with high Ab levels and non-abstainers in the placebo group (p=0.0015 and 0.019, respectively; see Figures 4A and 4C. The difference in the median reduction in cigarette consumption, following the TQD, between the high Ab non-abstainers and placebo non-abstainers was on average 4.6 cigarettes per day. Similarly, cotinine geometric mean concentrations (GMCs) were 19.0% lower on average following the target quit date in the high Ab non-abstainers as compared to placebo non-abstainers. Median cigarettes per day and cotinine GMC for placebo and low Ab group are nearly identical over the study period. Differences in mean CO were not observed across all three groups (see Figure 4B). 15 out of the 301 subjects smoked more than a 2-fold higher number of cigarettes following the TQD as compared to baseline with no significant difference between the placebo (n=4/100) and 3'AmNic-rEPA (n=11/201) groups. The highest smoking levels observed post-TQD were 5-fold baseline in the placebo and 4-fold baseline in the 3'AmNic-rEPA groups. Elevated smoking levels for 11 of these 15 subjects returned to below 2-fold baseline by study end. Subjects with remaining elevated levels were similar between the 3'AmNic-rEPA group (n=3/201) and placebo (n=1/100). Individual subjects with CO levels elevated by 2-fold or higher than baseline were also assessed and results were similar with no significant difference between the placebo (n=5/100) and 3'AmNic-rEPA (n=13/201) groups.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.WITHDRAWAL SYMPTOMS:\nSignificant differences were not observed in overall withdrawal severity between placebo and the high and low Ab groups (p >0.22).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.IMMUNOGENICITY AND EFFICACY BY STUDY GROUP:\nFigure 5 depicts immune response by study group from baseline to week 52. Anti-nicotine Ab GMCs increased across all active treatment groups after each vaccination, with each subsequent dose resulting in a higher Ab response than the previous dose. Schedule 2 showed a higher initial increase in Ab concentrations. The 400 μg/Schedule 2 group demonstrated the highest Ab concentrations. However, no significant differences (p >0.05) were observed in AUC, Cmax and Cavg across the treatment groups to 26 or 52 weeks likely because the study was not powered to detect such difference. An intent-to-treat analysis demonstrated that the Schedule 2, 400 μg dose group had significantly higher prolonged abstinence to 6 months as compared to placebo (17.6% vs. 6.0%; p=0.015; OR of 4.14; 95% CI, 1.32–13.02), although not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0%, p=0.054; OR=3.23; 95% CI, 0.98–10.67) or between placebo and Schedule 1 for each of the doses (p >0.84). The Schedule 2, 400 μg dose group also had the highest rates of prolonged abstinence to 12-months, significantly higher than placebo (15.7% vs. 6.0%, p=0.038; OR=3.44; 95% CI, 1.07–11.04), but not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0% for 200 (p=0.056; OR=3.21; 95% CI, 0.97–10.63) or between placebo and Schedule 1 for each dose (p >0.88).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.SAFETY:\nTable 2 lists the number of subjects experiencing local and systemic reactogenicity. Reactogenicity events were aggregated over all injections. Overall, ache and tenderness were the most commonly reported local events, with at least one report by nearly all subjects (86% to 98%) in each treatment group. Myalgia, malaise, and headache were the most commonly reported systemic events (64% to 88% of subjects). Swelling, heat, burning, erythema, and nausea were reported by about half the subjects. Fever and vomiting were less common (4% to 16%). A total of 1184 treatment-emergent adverse events (AEs), predominantly rated mild or moderate, were reported by 266 of 301 subjects; 87.1% of 3'AmNic-rEPA recipients and 91.0% of placebo recipients. On average, 3.7 and 4.3 events were observed per person in the vaccinated and placebo groups, respectively, including subjects with no events. The distribution of 161 physician-determined treatment-related AEs, according to severity and relationship to treatment, was similar for the 3'AmNic-rEPA and placebo arms. Seven 3'AmNic-rEPA recipients (3.5%) and 2 subjects in the placebo arm (2.0%) withdrew from the study due to adverse events. 18 Serious AEs were reported: 8 events in the 3'AmNic-rEPA treatment groups among 7 subjects (3.5% of the 3'AmNic-rEPA recipients) and 10 events in the placebo group among 5 subjects (5.0% of the placebo recipients). Only one of these SAEs (anaphylactic reaction in a 3'AmNic-rEPA 400 μg/Schedule 2 recipient) was considered by the Investigator to be treatment related. This subject, who had a history of urticaria to penicillin and seasonal allergies, experienced difficulty breathing, throat tightness, facial erythema and urticaria 70 minutes after the initial vaccination. The subject was treated with a single injection of subcutaneous epinephrine and diphenhydramine, which resolved the symptoms. Herpes Zoster was reported in 6 subjects; one occurring within 3–5 hours after the first vaccination which would be impossible to link to vaccination. Of the remaining cases, 4 (2%) occurred in 3'AmNic-rEPA recipients; while 1 occurred in placebo (1%). In contrast, the related herpes virus, simplex infection was reported in 4 3'AmNic-rEPA recipients (1%) and 3 placebo recipients (2%).\n\nBODY.DISCUSSION:\nResults demonstrated the proof-of-concept that smokers who achieved higher anti-nicotine Ab concentrations were more likely to quit and remain abstinent from smoking. The high Ab group demonstrated the highest abstinence rates independent of the time period of ascertainment. Similarly, in a separate study conducted by Cornuz and coworkers [13] testing a different nicotine vaccine (nicotine derivative conjugated to a virus-like particle derived from bacteriophage Qβ), post hoc analysis showed subjects stratified to the highest Ab group had a significantly higher quit rate than placebo. However, unlike the current study, which used the intent-to-treat (ITT) population to establish proof of concept, the reported finding by Cornuz et al. [13] was observed after eliminating about a third of the subjects who used nicotine replacement therapies during the course of the study or who had incomplete Ab titer values. In the present 3'AmNic study, subjects in the high Ab group had observed odds ratios of 4.4 (95% CI 1.5–12.7) and 3.9 (95% CI 1.3–11.2) for prolonged abstinence rates to 6 and 12 months versus placebo. Although no direct comparisons can be made, these odds ratios are not unlike ones observed in the meta-analyses conducted for the U.S. Clinical Practice Guideline where the reported odds-ratios ranged from 1.5 (95% CI 1.2–1.7) for nicotine gum to 3.1 (95% CI 2.5–3.8) for varenicline at 6 months post-quit [3]. If current study findings are confirmed in larger studies, imunotherapeutics are likely to emerge as an important aid to smoking cessation. No significant compensatory smoking in response to the presence of anti-nicotine antibodies, as determined by the number of cigarettes smoked per day, carbon monoxide levels or cotinine levels, was observed in this study. This result is consistent with observations from other studies [12, 13]. In the current study, subjects in the high Ab group who did not abstain smoked significantly lower number of cigarettes (median reduction of ~5 cigarettes/day) and experienced lower cotinine levels (~20%) than placebo subjects along with no differences observed between the low Ab and placebo groups. However, a small number of individual subjects (N=15/301) smoked more than 2-fold the number of cigarettes at baseline with no significant differences between the active treatment and placebo groups. A major challenge for immunotherapeutics is to stimulate high Ab levels in the vast majority of smokers trying to quit. Vaccine dose and frequency of vaccination have an impact on the Ab levels attained. The 5 injection/400 μg dose was associated with the highest Ab response, although not statistically significant, possibly due to the small sample size. Importantly, this dose and schedule demonstrated statistically significant improved 44-week CAR compared to placebo. Because the 4 injection/400 μg dose was not associated with higher abstinence rates, this result demonstrates that consideration of both dose and schedule of injection are critical. In an independent, follow-up immunogenicity study to examine if peak Ab levels could be elevated, a total of 74 subjects received 6 injections of 400 μg 3'AmNic-rEPA at week 0, 4, 8, 12, 16, and 26. More than 80% of subjects receiving the 6-dose immunization regimen exceeded a target level of Ab (25 μg/ml) by week 14. In contrast, only 50% of subjects receiving 5 injections of the 400 μg dose achieved this level by week 14 in the current study and, only 7% of subjects attained this level by the target quit date. This finding suggests that more frequent injections and a later quit date may increase treatment success. In general, 3'AmNic-rEPA was well-tolerated. The frequencies of local and systemic vaccine reactogenicity events were similar in the vaccine and placebo groups and similar to licensed adult vaccines containing Alum adjuvant [16]. The slight increase in cases of herpes zoster observed in this study may be spurious, but continued monitoring is necessary to determine if a causal relationship exists. The occurrence of a single anaphylactic reaction would suggest a need for continued monitoring and follow-up, even considering the subjects' history of prior drug allergy to penicillin.1 In summary, results from this study support the concept that high anti-nicotine Ab levels are associated with higher rates of abstinence. These findings suggest that vaccines attaining high Ab levels by the target quit date may be more effective. Other future strategies may include examining additional ways to increase Ab levels across all individuals. Nonetheless, this study demonstrates that 3'AmNic-rEPA has significant potential as a smoking cessation, and perhaps a relapse prevention aid.\n\nBODY.METHODS.STUDY POPULATION:\nSmokers were recruited via advertisement across nine geographically diverse U.S. sites. Interested subjects were screened over the telephone and more extensively screened at the first Screening Visit. Subject informed consent was obtained prior to screening. Subjects were 18 years of age or older, smoked ≥15 cigarettes/day, had exhaled CO ≥10 ppm; wanted to quit smoking, and were in good general physical and mental health. Exclusion criteria included recent use of any medications or drugs that might interfere with immune response, interact with the vaccine, and pharmacotherapies or other treatments for smoking cessation. For females, a negative urine pregnancy test at enrollment and active use of acceptable birth control or documentation of surgical sterility was required.\n\nBODY.METHODS.STUDY DESIGN:\nThis Phase 2 study was a randomized double-blind, placebo-controlled, parallel-arm trial design (see Figure 1). Four treatment groups varied the dose and/or schedule of intramuscular vaccination: 200 or 400 μg of 3'AmNic-rEPA or placebo according to Schedule 1 (weeks 0, 6, 12, and 26) or Schedule 2 (weeks 0, 4, 8, 16, and 26). Subjects (N=150) were first randomized within Schedule 1 groups in a 1:1:1 ratio (200 μg: 400 μg: placebo) and then 151 subjects randomized within Schedule 2 groups in the same ratio. The TQD was 1 week after the second injection (end of week 7 for Schedule 1 and end of week 5 for Schedule 2). If the subjects relapsed (seven consecutive days of smoking) after the quit date, a second quit date coinciding with a future clinic visit was allowed between time of relapse and week 18. Cessation counseling (based on the USDHHS Clinical Practice Guidelines [17]) for the first quit attempt involved 5 standardized face-to-face sessions (≤10 minutes) and for the second quit attempt, a face-to-face session plus 2 post-quit telephone counseling sessions. Subjects were followed for 52 weeks after randomization and the first injection on Day 0 for a total of 21 visits. During the injection day, subjects remained at the study site for 30 to 60 minutes for observation and attended a visit 24 hours after each injection to assess side effects. Otherwise, visits ranged from weekly to bi-weekly and were less frequent after later injections. Subjects who failed to quit smoking on their TQDs were encouraged to remain in the study and continue to attempt to achieve abstinence. Subjects who terminated from the study were not replaced and presumed to be smokers. Institutional Review Board approval was obtained from all institutions involved in the study. A Data and Safety Monitoring Board (DSMB) met four times during the study.\n\nBODY.METHODS.INVESTIGATIONAL PRODUCT:\nThe active investigational product was purified 3'-aminomethylnicotine conjugated to P. aeruginosa r-exoprotein A. For the 200 and 400 μg/mL dose, each single-use syringe contained 3'-aminomethylnicotine conjugated to 200 or 400 μg rEPA, respectively, adsorbed to 1.2 mg aluminum hydroxide adjuvant (Alhydrogel 85) in 1 mL phosphate buffered saline (0.15 M NaCl, 0.002 M NaPO4, pH 7.2, 0.01% polysorbate 80; PBS). For the placebo dose, PBS with 1.2 mg Alhydrogel 85 was included in a 1 mL single-use syringe.\n\nBODY.METHODS.MEASURES:\nCigarette use was recorded daily on an electronic diary for 182 days, and then weekly for the remainder of the study. Exhaled CO and urine cotinine were measured at each study visit, except for visits within 24 hours of vaccination. Questionnaires were collected via electronic diary: Fagerström Test for Nicotine Dependence [18] (administered days 0, 210, 364), Minnesota Nicotine Withdrawal Scale [MNWS, 19] (administered weekly until Month 6) and data on other tobacco usage. Sera were collected for immunogenicity measurements at 16–17 time points (schedule-dependent) from baseline to week 52. Anti-nicotine antibody concentrations were measured using ELISA (Enzyme-linked Immunosorbent Assay) [12]. Subjects recorded standard local and systemic reactogenicity events for 7 days after each injection. All reactogenicity events were followed until resolution or study completion. Treatment emergent AEs were recorded until 4 weeks after the last dose, with the exception of SAEs, which were collected through week 52. Subjects were also periodically monitored at clinic visits for vital signs, weight, hematology, chemistry and urinalysis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Intent-to-Treat (ITT) population was used for evaluation of efficacy, safety and immunogenicity. The ITT population was defined as all subjects who were randomized to treatment. The primary endpoint was continuous smoking abstinence for a total of 8 weeks measured from the beginning of week 19 to the end of week 26 (determined from subject diaries confirmed by exhaled CO ≤8 ppm). The analysis for proof-of-concept stratified the active-treatment recipients into high (top 30% AUC from weeks 0 to 26) and low (bottom 70% AUC from weeks 0 to 26) Ab responders, regardless of treatment group. An a priori decision was made to establish the antibody cutoff between 50% and 25%. Top 30% by AUC group was selected as the largest group of high antibody responders between the 25% and 50% cutoffs that demonstrated statistical significance as compared to placebo. Smoking outcomes were compared between subjects with high Ab and pooled placebo recipients using logistic regression. Secondary aims of this study were to assess a) 7-day point prevalence abstinence at various times, CARs during 52 weeks and time to sustained abstinence defined as attaining 8 weeks of continuous abstinence at anytime prior to week 46 and maintaining continuous abstinence through 52 weeks; b) impact on compensatory smoking amongst non-abstainers; c) withdrawal symptoms and d) immunogenicity, efficacy and safety of administration of either 4 or 5 of the 200 and 400 μg doses. Secondary smoking cessation analyses used logistic regression for binary outcomes and Cox proportional hazards regression models and log-rank tests for time-to-sustained abstinence analyses. Mixed-effects repeated-measures analyses of the number of cigarettes smoked, CO and cotinine adjusted for baseline were utilized in assessing compensatory smoking among non-abstainers or in assessing withdrawal symptoms. Anti-nicotine Ab responses were summarized as GMC with 95% confidence intervals. Safety was assessed throughout this study primarily using reactogenicity and adverse events (AEs). Reactogenicity data for 7 days after each injection were tabulated, and the proportions of subjects with any post-vaccination reactogenicity, aggregated over all injections, among the five treatment groups were compared using the Generalized Cochran-Mantel-Haenszel test. When a subject dropped out of the study, they were assigned presumed to be smokers. Otherwise, all missing diary data related to cigarette use were imputed utilizing the Last Observation Carried Forward principle. No imputation was carried out for CO level. The missing serology data were imputed by first defining a set of injection windows for each schedule. The missing serology was imputed by using the next available measured serology in its corresponding window; if the next value was not available the value of the nearest previous time point in that window was used. The AUC for anti-nicotine Ab was calculated based on imputed data. For Ab values one week after the target quit date, the value at week 9 was used for Schedule 1 as sera were not collected at week 8.\n\n**Question:** Compared to placebo group what was the result of recipients with the highest serum anti-nicotine antibody response (top 30% by AUC) on attain 8 weeks continuous abstinence from weeks 19 through 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
124
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on Postprandial plasma glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
157
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Slow treadmill speed what was the result of Fast treadmill speed on Locomotor-training effects?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
107
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on HbA1c level at 26 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
170
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Recurrent infections at day 56?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
173
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Baseline white blood cell count?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
156
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Manually-assisted body-weight supported treadmill training what was the result of Body-weight supported treadmill training combined with Lokomat on Paretic step length ratio?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
171
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Superiority of treatment given by survival curves?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
176
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Headache?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
91
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Routine resite of peripheral intravenous devices every 3 days did not reduce complications compared with clinically indicated resite: a randomised controlled trial\n\n ABSTRACT.BACKGROUND:\nPeripheral intravenous device (IVD) complications were traditionally thought to be reduced by limiting dwell time. Current recommendations are to resite IVDs by 96 hours with the exception of children and patients with poor veins. Recent evidence suggests routine resite is unnecessary, at least if devices are inserted by a specialised IV team. The aim of this study was to compare the impact of peripheral IVD 'routine resite' with 'removal on clinical indication' on IVD complications in a general hospital without an IV team.\n\nABSTRACT.METHODS:\nA randomised, controlled trial was conducted in a regional teaching hospital. After ethics approval, 362 patients (603 IVDs) were randomised to have IVDs replaced on clinical indication (185 patients) or routine change every 3 days (177 patients). IVDs were inserted and managed by the general hospital medical and nursing staff; there was no IV team. The primary endpoint was a composite of IVD complications: phlebitis, infiltration, occlusion, accidental removal, local infection, and device-related bloodstream infection.\n\nABSTRACT.RESULTS:\nIVD complication rates were 68 per 1,000 IVD days (clinically indicated) and 66 per 1,000 IVD days (routine replacement) (P = 0.86; HR 1.03; 95% CI, 0.74-1.43). Time to first complication per patient did not differ between groups (KM with log rank, P = 0.53). There were no local infections or IVD-related bloodstream infections in either group. IV therapy duration did not differ between groups (P = 0.22), but more (P = 0.004) IVDs were placed per patient in the routine replacement (mean, 1.8) than the clinical indication group (mean, 1.5), with significantly higher hospital costs per patient (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nResite on clinical indication would allow one in two patients to have a single cannula per course of IV treatment, as opposed to one in five patients managed with routine resite; overall complication rates appear similar. Clinically indicated resite would achieve savings in equipment, staff time and patient discomfort. There is growing evidence to support the extended use of peripheral IVDs with removal only on clinical indication.\n\nABSTRACT.REGISTRATION NUMBER:\nAustralian New Zealand Clinical Trials Registry (ANZCTR) Number ACTRN12608000421336.\n\nBODY.BACKGROUND:\nPeripheral intravenous device (IVD) insertion is the most commonly performed invasive procedure in hospitalised patients, with an estimated 150 million peripheral intravenous devices placed each year in North America alone [1]. IVDs are vital for delivery of hydration, medicines and nutrition but are not without complications. Serious adverse outcomes are fortunately rare, with IVD-related bloodstream infection reported in a recent meta-analysis of 110 studies to occur in 0.1% of devices and 0.5 per 1,000 device days [2]. IVD treatment is more frequently interrupted by phlebitis, an irritation of the vein characterised by pain, tenderness on palpation, erythema, warmth, swelling, induration or palpable cord (thrombosis) of the cannulated vein; diagnostic algorithms usually require two or more of these conditions [3-5]. Phlebitis is in almost all cases a biochemical reaction to the mechanical irritation by the presence of the IVD and associated infusate [3], although phlebitis symptoms such as erythema may be misperceived as indicative of an infection. In fact, there is not a high correlation between phlebitis and device infection, and the Centers for Disease Control (CDC) states that infection is rarely associated with peripheral, as opposed to central, venous devices [3,6,7]. Fluid infiltration or 'tissuing' of devices is another common IVD complication which may also reflect the inflammatory (phlebitic) response of the vein, rather than simple misplacement of the device tip [8]. Early cohort studies noted an association between increased device time in situ and phlebitis [9,10]. This association was responded to with policies for routine device removal. Recommended timelines for routine resite have been extended over the past three decades from 24, to 48, then to 72 hours. Currently, 72- to 96-hour resite is recommended to reduce phlebitis by the CDC's 2002 Guidelines for the Prevention of Intravascular Device Infection, with the exemption that this is not required in children or those with poor veins [7]. Such policies cause increased workload in hospitals, where the task of removing and replacing well-functioning IVDs generally falls to busy nursing and junior medical staff. In addition, few patients welcome the prospect of additional venipuncture. Despite the general clinical acceptance of routine IVD replacement as a phlebitis and infection prevention measure, it has not been supported by recent data. It may be that the risk of complications during the entire IVD treatment episode is similar, regardless of whether multiple short-dwell or fewer longer-dwell IVDs are used over this time. Three small (n = 47-60) randomised, controlled trials (RCTs) suggested routine replacement at 12, 24 or 48 hours may reduce phlebitis compared to resite on clinical indication, although a systematic review for the Swedish Council on Technology Assessment in Healthcare assessed these as low- to medium-quality studies providing 'limited scientific evidence' [11-14]. More recently, two well-conducted RCTs found no evidence of effect when comparing IVD replacement every 3 days with replacement only on clinical indication for medical and surgical inpatients [15,16]. The largest of these studies reported findings from 755 general medical and surgical patients with 1,428 IVDs and found a 5% difference in combined phlebitis and infiltration rates per patient (38% clinically indicated resite, 33% routine resite), suggesting a potential small clinical benefit of 3-day resite [15]. However, this difference was not statistically significant (RR 1.15; 95% CI, 0.95-1.40) and disappeared when overall cannulation time was considered (59.8/1,000 IVD days clinically indicated resite, 60.9/1,000 IVD days routine resite; RR 0.98; 95% CI 0.78-1.24) [15]. In addition, no clinically important or statistically significant differences were observed in the secondary endpoints of phlebitis, infiltration, occlusion, local infection or suspected bloodstream infection rates between study groups [15]. Another recent RCT in the 'hospital in the home' community setting also found no important clinical or statistically significant difference in phlebitis, occlusion or bloodstream infection rates in 316 patients when resite every 3 days was compared with clinically indicated resite [17]. A 2010 Cochrane Collaboration review concluded there was 'no conclusive evidence of benefit' of routine IVD resite and suggested organisations could consider adopting a resite on clinical indication policy [18]. There is growing evidence that routine IVD replacement may be ineffective, although caution has been urged in light of the large number (74% in both groups in the largest study to date) of reported devices inserted by a specialised IV team, a factor known to reduce complications [19]. Device insertion (and reinsertion) is unpleasant for patients, requires skilled and available clinical staff, and has associated costs for the health sector. If replacement only on clinical indication is safe and effective, this would have important benefits for patients and the health system. We report a RCT of 3-day routine IVD resite versus clinically indicated replacement in a medical-surgical hospital where IVDs were inserted by the general medical and nursing staff; the insitution did not have a specialised IV service.\n\nBODY.METHODS.AIM:\nThe aim of the study was to compare the impact of 3-day routine resite, with clinically indicated resite, on peripheral IVD complications.\n\nBODY.METHODS.DESIGN:\nOpen (nonblinded), parallel group RCT.\n\nBODY.METHODS.ETHICS:\nThe study was approved by the Tasmanian State Human Research Ethics Committee. Written informed consent was obtained prospectively from all participants.\n\nBODY.METHODS.SETTING AND SAMPLE:\nThe study was undertaken at a large regional teaching hospital in Australia which functions as the tertiary referral centre for the northern half of the State of Tasmania. The hospital has more than 32,000 separations per annum, with a spectrum of medical and surgical specialties. Eligible patients were at least 18 years of age and scheduled or expected to have a peripheral IVD indwelling for at least 4 days, and they gave written informed consent. Exclusion criteria were immunosuppression, current bloodstream infection or an IVD already in situ for >48 hours. IVDs were inserted and cared for by the general nursing and medical staff; there was no special IV team or service.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size calculations were performed using PASS 2008 (Version 8.0.8; Kaysville, UT) to detect a change in rates by 30% (from 36% to 25%, two-tailed α = 0.05, 90% power) on the basis of the complication rates of routinely resited IVs in a previous study [16]. Although this indicated that n = 378 per group (total 756) were required, the study was ceased early (total n = 606 IVs) because all investigators left the employment of the institution. Consequently, study power was reduced, but remained over 80% (required minimum n = 282 per group).\n\nBODY.METHODS.RECRUITMENT:\nAll adult patients admitted to the inpatient acute medical and surgical wards of the study hospital were screened by a full-time research nurse. This excluded paediatric, day-surgery, mental health, obstetric, critical care and dialysis units.\n\nBODY.METHODS.STUDY PROCEDURES:\nPatients were randomly assigned (computer generated) in a 1:1 allocation ratio to either the 'routine replacement' (control) or 'clinically indicated replacement' (intervention) group. Assignment was concealed until randomisation by use of a telephone service. A tag was placed on the insertion site indicating the study group. All devices for the patient were managed as per randomised group. The intervention group did not have their IVD resited unless clinically indicated. This decision was made by the treating clinician (not the investigators), who ordered IVD resite if the device failed or phlebitis occurred and ongoing IV treatment was required. The control group had a new device relocated to a different site by the general medical or nursing staff every 3 days. Control devices could also be removed at any stage by the clinical staff if they were not required or if complications occurred. Clinical nursing and medical staff undertook insertion and follow-up care of all IVDs as per the CDC Guidelines [7]. Laboratory staff undertaking microbiological culture assessments were blinded to the study group. Due to the nature of the intervention, patients, research, and clinical staff were unable to be blinded. However, the investigators had no involvement in assessing or documenting complications. IVDs were assessed by the clinical nursing staff on each nursing shift for complications as part of standard clinical practice in the hospital. Times and dates of device insertion and removal were recorded along with the reason for device removal and any protocol deviations. A full-time research nurse collected data from the hospital chart and sought clarification from patients and clinical staff if necessary. Microbiological investigations (device tip, blood cultures and site cultures) were performed by the clinical staff on clinical suspicion of infection by the treating clinician. Demographic and clinical data were collected on age, sex, diagnosis at hospital admission, phlebitis risk based on Tagar et al.'s classification (low/medium/high risk) [20], past history of phlebitis, any comorbidities requiring active medical treatment (e.g., type 2 diabetes or congestive heart failure), haemoglobin, concurrent infection at other sites, antibiotic therapy, type of surgery, type of infusate and any additives (and their level of irritability), vein and skin quality assessment, size of device, insertion site, health professional inserting the device, and setting for insertion, presence of other vascular devices, wound drains and urinary catheters. Vein quality was assessed as good (vein easy to visualise and easy to palpate with tourniquet on), fair (not easily visible but can palpate with tourniquet), or poor (veins small, scarred or difficult to palpate with tourniquet; may require heat pack to aid vasodilation). Skin quality was assessed as good (healthy, well hydrated, elastic), fair (mildly dehydrated, reduced elasticity), or poor (papery, dehydrated, or reduced elasticity).\n\nBODY.METHODS.ANALYTIC APPROACH:\nThe primary outcome was a composite measure of any complication causing unplanned cannula removal prior to completion of IV treatment. The composite included phlebitis, infiltration, occlusion, accidental removal, local infection, and IV device-related bloodstream infection (IVD-BSI). These were also analysed individually as secondary endpoints. A composite measure was chosen due to the low rates of these conditions individually and to the assumption that they are comparable measures of 'infusion failure'; that is, the device can no longer be used to deliver treatment. This approach has been used in previous studies on the topic [15-17]. Phlebitis was defined as two or more of pain, erythema, purulence, streak formation, or a palpable venous cord [3]. Local infection IVD-BSI (bacteremia/fungemia with at least one positive blood culture obtained from a peripheral vein, clinical manifestations of infection, and no apparent source for the bloodstream infection (BSI) except the device with or without positive tip or entry site swab culture) were defined using CDC criteria [7]. Other secondary outcomes were time in situ (hours of catheterisation from insertion to removal, both per patient and per device) [7]; IVDs per patient (number of peripheral devices inserted to complete the course of treatment) [7]; costs (calculations based on 20 minutes nursing or medical insertion time at relevant rates [15], plus the cost of the required equipment (cannula, insertion pack including dressing and solution, gloves, saline, syringe, extension tubing and starter pack for all plus fluid bag, tubing and secondary tubing for medication administration for those patients requiring this) for insertions, nursing time and equipment to routinely remove IVDs that were otherwise functional, and the costs of treating any complications that occurred (e.g., IVD-BSI). Cost calculations were undertaken from the viewpoint of the hospital using negotiated wage costs and purchasing agreements for government hospitals in the State of Tasmania. Costs would be similar for other Australian hospitals. All randomised patients were analysed by intention to treat. Each patient was randomised once and could have multiple IVDs, with subsequent IVD resites managed as per the randomised group. Relative incidence complication rates per 1,000 IVD days and 95% confidence intervals were calculated to summarise the impact of clinically indicated replacement relative to 3-day replacement. Kaplan-Meier survival curves were drawn to compare time to first IVD complication between patients in the two study groups. To assess for any potential impact of protocol violations, a per protocol analysis was also undertaken. All clinical and demographic variables were subjected to univariate testing against the primary endpoint to guide selection of possible covariates for the multivariable model. Cox proportional hazards regression modelling was used to examine the impact of age, gender, oncology status, number of comorbidities (nil, one, two, or more than two), IV gauge, site, vein quality, skin quality, oral antibiotics, IV antibiotics, wound drain, inserter occupation, initial versus subsequent IVDs, phlebitis in a preceeding IVD, haemoglobin level, parenteral nutrition, continuous versus intermittent infusion, patient risk category and study group on the outcome of time to complication events using an additive model [3,5,7,20-25]. In addition, to adjust for any inherent correlations or codependencies in the failure times of IVDs (i.e., same patient multiple failure-time data) within the Cox model, we also used the Prentice-Williams-Peterson conditional risk-set method [26]. The Mann-Whitney test was used to compare various secondary outcomes between study groups. Cost differences were calculated using arithmetic means and the t-test [27]. P values <0.05 were considered significant. All statistical data were entered and analysed using SPSS (Version 15.0; Chicago, IL) and Stata (Version 8.2; College Station, TX).\n\nBODY.RESULTS.SAMPLE:\nOver a 10-month period, 1,954 patients were screened for eligibility. Of these, 788 were eligible, with 362 (46%) recruited into the study. The most frequent exclusion criterion was altered mental state that precluded consideration of consent as assessed by the research nurse. Altered mental state was generally related to older medical patients and the immediate postoperative phase for surgical patients. Reasons for exclusion are shown in Figure 1. The 362 patients were randomised into either the routine change group (n = 177 participants, 323 devices) or the clinically indicated replacement group (n = 185 participants, 280 devices). In total 50,173 IVD hours were studied (routine change group 23,288 hours, clinically indicated group 26,885 hours). More patients in the routine change group had an active infection (53% vs. 44%) and were receiving IV antibiotics (73% vs. 64%). However, as shown in Tables 1 and 2, the two groups were generally comparable at baseline for patient- and cannula-related factors. Figure 1Participant flowchart. Table 1 Baseline characteristics of study participants Variable 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) Sex - Male, n (%) 96 (54%) 103 (56%) Age, mean (SD) 65.1 (17.3) 62.7 (15.4) Reason for admission, n (%) • Gastrointestinal 46 (26%) 52 (28%) • Respiratory 37 (21%) 34 (18%) • Oncology 21 (12%) 21 (11%) • Orthopaedic 16 (9%) 22 (12%) • Cardiac 10 (6%) 10 (5%) • Neurological 9 (5%) 10 (5%) • Vascular 7 (4%) 7 (4%) • Renal 16 (9%) 9 (5%) • Other 15 (8%) 20 (11%) Number of comorbidities, n (%) • None 6 (3.4%) 10 (5.4%) • 1 22 (12.4%) 21 (11.4%) • 2 44 (24.9%) 54 (29.2%) • >2 105 (59.3%) 100 (54.1%) Type of surgery, n (%) • Nil 124 (70%) 132 (71%) • Gastrointestinal 22 (12%) 22 (12%) • Orthopaedic 8 (5%) 15 (8%) • Other 23 (13%) 16 (9%) Most recent Hb - Mean (SD) 124.8 (23.2) 126.2 (21.9) Table 2 Baseline infusion-related characteristics of study devices Variable 3-Day Routine Change Group (n = 323) , n (%) Clinically Indicated Change Group (n = 280) , n (%) IV cannula gauge • 22 43 (13%) 46 (16%) • 20 241 (75%) 201 (72%) • 18 27 (12%) 30 (11%) • Other 2 (1%) 3 (1%) Vein assessment • Good 143 (44.3%) 107 (38.2%) • Fair 160 (49.5%) 144 (51.4%) • Poor 20 (6.2%) 29 (10.4%) Skin integrity • Good 138 (43%) 104 (37%) • Fair 178 (55%) 164 (59%) • Poor 7 (2%) 12 (4%) Past history of phlebitis 2 (0.6%) 4 (1.4%) Insertion site • Hand 206 (64%) 187 (67%) • Forearm 59 (18%) 49 (18%) • Cubital fossa 51 (16%) 38 (14%) • Other 7 (2%) 6 (2%) Receiving infusate 241 (75%) 215 (77%) pH of infusate - Mean (SD) 6.0 (0.5) 6.0 (0.4) Receiving oral antibiotics 24 (7%) 24 (9%) Receiving IV antibiotics 236 (73%) 176 (63%) pH of IV antibiotics - Mean (SD) 6.9 (1.1) 6.9 (1.3) Receiving other IV meds 190 (59%) 179 (64%) pH of other IV meds - Mean (SD) 5.6 (2.6) 6.0 (2.8) Wound drain 50 (16%) 40 (14%) Urinary catheter 55 (17%) 41 (15%) Other vascular device 26 (8%) 24 (9%) Inserted by • Junior doctor 232 (72%) 207 (74%) • Registered Nurse 67 (21%) 57 (20%) • Senior doctor 24 (7%) 16 (6%) Where inserted • Ward 216 (67%) 188 (67%) • Emergency department 74 (23%) 70 (25%) • Other 33 (10%) 22 (8%) Current infection (site) • Respiratory 97 (30%) 49 (18%) • Urinary 24 (7%) 19 (7%) • Wound 16 (5%) 15 (5%) • Other 29 (9%) 37 (13%) • >1 site 5 (2%) 4 (1%) N/A (none) 152 (47%) 156 (56%) Risk of phlebitis (Tagar scale) • Low 174 (54%) 144 (51%) • Medium 149 (46%) 136 (49%) • High 0 0 \n\nBODY.RESULTS.EFFECT OF INTERVENTION ON PRIMARY OUTCOME:\nOutcome data were available for all patients. Table 3 shows the rates of primary and secondary outcomes. Differences in complication rates between groups were not significantly different (routine replacement 66.0 per 1,000 IVD days; clinical replacement 67.8 per 1,000 IVD days; HR 1.03; 95% CI, 0.74-1.43; P = 0.86). As shown in Figure 2, the time to first complication per patient was also not significantly different between groups (Kaplan Meier [KM] with log rank P = 0.53). On crude rate per IVD, the catheters replaced on clinical indication had higher complication rates (110/280 or 39% vs. 91/323 or 28%; P = 0.004). However, total complication rates per patient (to deliver the course of IV therapy) were not significantly different (P = 0.39) between clinically indicated (76/185, 41%) and routine resite patients (64/177, 36%). Table 3 Effect of intervention on primary and secondary endpoints Outcomes 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) RR (95% CI) , P Value Primary: IVD complications per patient, n (%) 64 (36%) 76 (41%) RR 1.14 (0.88, 1.47), p = 0.39 IVD complications per 1000 IVD days 66.0 (95% CI 49.8, 82.1) 67.8 (95% CI 52.6, 83.1) HR 1.03 (0.74, 1.43), p = 0.86 Secondary: Phlebitis, n (%) 12 (7%) 18 (10%) RR 1.44 (0.71, 2.89), p = 0.34 Infiltration, n (%) 53 (30%) 61 (33%) RR 1.10 (0.81, 1.49), p = 0.57 Occlusion, n (%) 5 (3%) 4 (2%) RR 0.77 (0.21, 2.80), p = 0.75 Accidental removal, n (%) 11 (6%) 16 (9%) RR 1.39 (0.66, 2.92), p = 0.43 Local infection 0 0 - IVD-related BSI, n (%) 0 0 - IVD costs per patient, AUD$ mean (SD) $55.42 ($35.26) $43.35 ($26.78) Mean difference $12.07 (95%CI $5.57, $18.56), p < 0.001 Figure 2Kaplan-Meier survival curve of time to first intravenous device complication per patient (log rank, P = 0.53). Patient- and device-related variables considered in the multivariable model were older age, number of comorbidities (nil, one, two or more than two), smaller cannula size, poor skin or vein integrity, IV antibiotics, insertion by medical staff and study group. None of these were found to be statistically significant. The final Cox proportional hazards model after adjusting for time found study group was not a significant factor (HR 1.02; 95% CI, 0.77-1.36; P = 0.89). Variance-adjustment testing for potential multiple-failures per patient (cannula data) found no inconsistency in significant results compared to the main Cox model.\n\nBODY.RESULTS.PROTOCOL COMPLIANCE:\nCompliance with the study intervention was achieved in 78% (251 of 323) of routinely replaced IVDs removed at Day 3 and 100% (280 of 280) of IVDs resited on clinical indication. Noncompliance in the routine resite group was generally related to high staff workloads on that day or to staff's perception that the patient was soon to be discharged or have therapy completed, and so the IVD remained in situ beyond Day 3. A per protocol analysis was performed including only those patients in the routine replacement group whose IVDs were all actually removed by 96 hours (n = 251). This found no significant difference (KM with log rank P = 0.16) in the rate of complications between groups (routine replacement 92 per 1,000 IVD days vs. clinically indicated 68 per 1,000 IVD days).\n\nBODY.RESULTS.EFFECT OF INTERVENTION ON SECONDARY OUTCOMES:\nThere was no statistically significant difference in group outcomes for any phlebitis (P = 0.34), infiltration (P = 0.57), occlusion (P = 0.75), or accidental removal (P = 0.43). No cases of local infection or IVD-related bloodstream infection occurred in either group. For overall IVD therapy (total cannulation time per patient for all devices), clinically indicated devices had a median therapy of 120 hours (quartiles 86.5 and 172.5 hours), and those replaced routinely had median therapy of 113 hours (quartiles 72 and 172 hours) (P = 0.21). For individual IVD dwell times, the clinically indicated group devices had a median dwell time of 85 hours (quartiles 51 and 121 hours), and those replaced routinely had a median dwell time of 71 hours (quartiles 48 and 90 hours) (P < 0.001). The maximum IVD dwell time was 1,023 hours (43 days) in the clinical replacement group, and this cannula was still working well on removal for completion of therapy. The overall number of IVDs per patient was significantly less (P = 0.004) for those replaced on clinical indication (mean 1.5, SD 0.8, median 1, quartiles 1 and 2) than for those routinely replaced (mean 1.8, SD 1.1, median 1, quartiles 1 and 2). A total of 22% of patients in the routinely replaced group had three or more IVDs compared with 9% in the clinical indication group. A total of 82 (28%) IVDs in the routine replacement group were resited after 3 days despite functioning well and ongoing treatment being required. (The remainder removed at this time were no longer required and so not resited, or infusion failure had already occurred.) Mean hospital costs per patient for the course of IV therapy were significantly higher (P < 0.001) for those managed with routine resite (mean $55.42, SD $35.26) compared with resite on clinical indication (mean $43.35, SD $26.78).\n\nBODY.DISCUSSION:\nThe finding that 3-day routine resite was not an effective intervention was consistent across the intention-to-treat primary analysis and the per protocol analysis. There remained no effect when events were expressed per patient or per 1,000 IVD days. Neither composite nor individual complication rates differed between groups, and there were no cases of local or device-related bloodstream infection. It appears safe and practical to leave IVDs in situ as long as they are functioning well and are still needed for clinical treatments. All IVDs will fail eventually, but this study shows that artificially shortening the lifespan of individual catheters does not reduce the overall complication rates over the course of therapy. Our results indicate that the average duration of IV therapy is 5-6 days and that many catheters can remain complication-free for this period. If catheters are not routinely resited, the median dwell time would remain within the 72-96 hours recommended by the CDC, but about 10% would remain in situ for longer (in this study up to 43 days with no complications). Our data show that a policy of resite on clinical indication would mean that one of every two patients would need a single cannula to receive treatment, whereas a 3-day change policy would result in only one in five patients having this scenario, with the rest requiring multiple cannulations and therefore additional pain and inconvenience. The results are consistent with the findings of recent RCTs in both hospitals and the community that have found no benefit in routinely resiting IVDs every 3 days [15-17]. In these studies, many cannulae were inserted by an expert IVD team [15-17], which may have minimised complications in both groups [19]. Our study confirms and extends these findings into the general medical/surgical setting without an IV team where IVDs were inserted by a variety of nursing and medical staff. Data from this study were included in a 2010 Cochrane Collaboration systematic review and meta-analysis on the topic [18]. This review included six trials (n = 3,455) and reported no clinically important or statistically significant difference in catheter-related bloodstream infection or phlebitis between IVDs that were routinely resited (at 48-96 hours) or resited on clinical indication, yet there were significantly lower costs in the group resited on clinical indication [18]. The belief that routine resite of IVDs will prevent complications appears to stem from early observational studies that noted longer-dwelling IVDs had more complications than shorter-dwelling IVDs [9,10]. This is intuitively true, given, for example, that an IVD in situ for 6 days has twice the time exposure of risk than an IVD in situ for 3 days. However, this does not prove that two sequentially inserted IVDs (in the same patient), both used for 3 days, have a combined lower risk over time than the 6-day dwell device. Indeed, this and other recent trials strongly suggest that the risk for the patient over the 6-day period is similar. Well-designed cohort studies with modern catheter materials suggest that the daily risk of phlebitis is relatively stable after the first 24 or 48 hours [3,21,28-31]. The peak in phlebitis between 24 and 48 hours is likely associated with the time taken by the body to mount a biological response after the instigation of therapy; those most likely to develop phlebitis will do so at this time. The results support the extension of the use of peripheral IVDs beyond the 72-96 hours currently recommended by the CDC [7]. There is incongruity in the CDC recommendations; they recommend not to routinely resite IVDs in children or in those with limited venous access. If it is safe in these populations, it is unclear why it would be necessary to routinely resite adults or those with better veins. Higher-risk cannulae such as central venous devices are no longer recommended by the CDC for routine replacement, because trials showed this was not of benefit [7]. Our study also confirms that the CDC guidelines are not always complied with; one fifth of IVDs in the routine change group were not replaced by this time. However, the per protocol analysis showed that the intervention remained ineffective even for those who truly had their IVDs resited every 3 days. Limitations of the study included a 9% higher frequency of IV antibiotics and concurrent infection in the routine resite group. This may have put the group at higher risk due to vein irritation, or conversely it protected against bacterial entry. Neither variable was significant in the multivariable model. The unblinded study design was unavoidable, but also a limitation. Our use of clear outcome measures, a full-time research nurse and laboratory staff blinded to culture assessments should have reduced the risk for potential bias. Resource constraints prematurely ended recruitment, thus reducing the anticipated power of the study from 90% to 80%. Routine IVD resite involves pain for patients, staff procedural time, equipment costs and environmental waste. Contemporary evidence suggests the current policy for routine resite by 72-96 hours is ineffective and should be replaced with a 'resite on clinical indication' policy. It remains imperative that clinical staff monitor IVDs closely and that a daily review of the need for continuing therapy be made, with cessation as soon as possible; the only no-risk IVD is no IVD. Of the 4.3 million acute hospital admissions in Australia each year (excluding day cases), over half have IV treatment [15,32]. Conservatively, if even 2 million courses of IV therapy were managed with clinically indicated rather than routine resite, this would save the unnecessary insertion of approximately 660,000 IVDs and free 280,000 hours of staff insertion time. Assuming our costs are similar to those in other Australian hospitals, a change to resite on clinical indication would save approximately AUD$24 million nationally each year.\n\nBODY.CONCLUSIONS:\nAlthough larger, multisite trials are required, evidence to date suggests that routine resite of peripheral IVDs increases patient discomfort and healthcare costs, but does not reduce IVD complications as has traditionally been thought.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCMR designed the study, applied for funding and drafted the manuscript. DM participated in study design and manuscript preparation, and managed the study. JM recruited patients, ensured protocol integrity and collected data. MRM undertook statistical analyses and assisted with drafting the manuscript. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nCMR, PhD is Professor, Research Centre for Clinical and Community Practice Innovation, Griffith University, Australia. DM holds a Masters by Research and is Senior Lecturer, University of Tasmania, Australia. JM is an RN and Nurse Unit Manager, Calvary Tasmania, Australia. MRM is a PhD qualified Biostatistician, Gippsland Medical School, Monash University, Australia.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1741-7015/8/53/prepub\n\n**Question:** Compared to staff inclination replacement what was the result of routine replacement on IVD complications per person?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
90
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Routine resite of peripheral intravenous devices every 3 days did not reduce complications compared with clinically indicated resite: a randomised controlled trial\n\n ABSTRACT.BACKGROUND:\nPeripheral intravenous device (IVD) complications were traditionally thought to be reduced by limiting dwell time. Current recommendations are to resite IVDs by 96 hours with the exception of children and patients with poor veins. Recent evidence suggests routine resite is unnecessary, at least if devices are inserted by a specialised IV team. The aim of this study was to compare the impact of peripheral IVD 'routine resite' with 'removal on clinical indication' on IVD complications in a general hospital without an IV team.\n\nABSTRACT.METHODS:\nA randomised, controlled trial was conducted in a regional teaching hospital. After ethics approval, 362 patients (603 IVDs) were randomised to have IVDs replaced on clinical indication (185 patients) or routine change every 3 days (177 patients). IVDs were inserted and managed by the general hospital medical and nursing staff; there was no IV team. The primary endpoint was a composite of IVD complications: phlebitis, infiltration, occlusion, accidental removal, local infection, and device-related bloodstream infection.\n\nABSTRACT.RESULTS:\nIVD complication rates were 68 per 1,000 IVD days (clinically indicated) and 66 per 1,000 IVD days (routine replacement) (P = 0.86; HR 1.03; 95% CI, 0.74-1.43). Time to first complication per patient did not differ between groups (KM with log rank, P = 0.53). There were no local infections or IVD-related bloodstream infections in either group. IV therapy duration did not differ between groups (P = 0.22), but more (P = 0.004) IVDs were placed per patient in the routine replacement (mean, 1.8) than the clinical indication group (mean, 1.5), with significantly higher hospital costs per patient (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nResite on clinical indication would allow one in two patients to have a single cannula per course of IV treatment, as opposed to one in five patients managed with routine resite; overall complication rates appear similar. Clinically indicated resite would achieve savings in equipment, staff time and patient discomfort. There is growing evidence to support the extended use of peripheral IVDs with removal only on clinical indication.\n\nABSTRACT.REGISTRATION NUMBER:\nAustralian New Zealand Clinical Trials Registry (ANZCTR) Number ACTRN12608000421336.\n\nBODY.BACKGROUND:\nPeripheral intravenous device (IVD) insertion is the most commonly performed invasive procedure in hospitalised patients, with an estimated 150 million peripheral intravenous devices placed each year in North America alone [1]. IVDs are vital for delivery of hydration, medicines and nutrition but are not without complications. Serious adverse outcomes are fortunately rare, with IVD-related bloodstream infection reported in a recent meta-analysis of 110 studies to occur in 0.1% of devices and 0.5 per 1,000 device days [2]. IVD treatment is more frequently interrupted by phlebitis, an irritation of the vein characterised by pain, tenderness on palpation, erythema, warmth, swelling, induration or palpable cord (thrombosis) of the cannulated vein; diagnostic algorithms usually require two or more of these conditions [3-5]. Phlebitis is in almost all cases a biochemical reaction to the mechanical irritation by the presence of the IVD and associated infusate [3], although phlebitis symptoms such as erythema may be misperceived as indicative of an infection. In fact, there is not a high correlation between phlebitis and device infection, and the Centers for Disease Control (CDC) states that infection is rarely associated with peripheral, as opposed to central, venous devices [3,6,7]. Fluid infiltration or 'tissuing' of devices is another common IVD complication which may also reflect the inflammatory (phlebitic) response of the vein, rather than simple misplacement of the device tip [8]. Early cohort studies noted an association between increased device time in situ and phlebitis [9,10]. This association was responded to with policies for routine device removal. Recommended timelines for routine resite have been extended over the past three decades from 24, to 48, then to 72 hours. Currently, 72- to 96-hour resite is recommended to reduce phlebitis by the CDC's 2002 Guidelines for the Prevention of Intravascular Device Infection, with the exemption that this is not required in children or those with poor veins [7]. Such policies cause increased workload in hospitals, where the task of removing and replacing well-functioning IVDs generally falls to busy nursing and junior medical staff. In addition, few patients welcome the prospect of additional venipuncture. Despite the general clinical acceptance of routine IVD replacement as a phlebitis and infection prevention measure, it has not been supported by recent data. It may be that the risk of complications during the entire IVD treatment episode is similar, regardless of whether multiple short-dwell or fewer longer-dwell IVDs are used over this time. Three small (n = 47-60) randomised, controlled trials (RCTs) suggested routine replacement at 12, 24 or 48 hours may reduce phlebitis compared to resite on clinical indication, although a systematic review for the Swedish Council on Technology Assessment in Healthcare assessed these as low- to medium-quality studies providing 'limited scientific evidence' [11-14]. More recently, two well-conducted RCTs found no evidence of effect when comparing IVD replacement every 3 days with replacement only on clinical indication for medical and surgical inpatients [15,16]. The largest of these studies reported findings from 755 general medical and surgical patients with 1,428 IVDs and found a 5% difference in combined phlebitis and infiltration rates per patient (38% clinically indicated resite, 33% routine resite), suggesting a potential small clinical benefit of 3-day resite [15]. However, this difference was not statistically significant (RR 1.15; 95% CI, 0.95-1.40) and disappeared when overall cannulation time was considered (59.8/1,000 IVD days clinically indicated resite, 60.9/1,000 IVD days routine resite; RR 0.98; 95% CI 0.78-1.24) [15]. In addition, no clinically important or statistically significant differences were observed in the secondary endpoints of phlebitis, infiltration, occlusion, local infection or suspected bloodstream infection rates between study groups [15]. Another recent RCT in the 'hospital in the home' community setting also found no important clinical or statistically significant difference in phlebitis, occlusion or bloodstream infection rates in 316 patients when resite every 3 days was compared with clinically indicated resite [17]. A 2010 Cochrane Collaboration review concluded there was 'no conclusive evidence of benefit' of routine IVD resite and suggested organisations could consider adopting a resite on clinical indication policy [18]. There is growing evidence that routine IVD replacement may be ineffective, although caution has been urged in light of the large number (74% in both groups in the largest study to date) of reported devices inserted by a specialised IV team, a factor known to reduce complications [19]. Device insertion (and reinsertion) is unpleasant for patients, requires skilled and available clinical staff, and has associated costs for the health sector. If replacement only on clinical indication is safe and effective, this would have important benefits for patients and the health system. We report a RCT of 3-day routine IVD resite versus clinically indicated replacement in a medical-surgical hospital where IVDs were inserted by the general medical and nursing staff; the insitution did not have a specialised IV service.\n\nBODY.METHODS.AIM:\nThe aim of the study was to compare the impact of 3-day routine resite, with clinically indicated resite, on peripheral IVD complications.\n\nBODY.METHODS.DESIGN:\nOpen (nonblinded), parallel group RCT.\n\nBODY.METHODS.ETHICS:\nThe study was approved by the Tasmanian State Human Research Ethics Committee. Written informed consent was obtained prospectively from all participants.\n\nBODY.METHODS.SETTING AND SAMPLE:\nThe study was undertaken at a large regional teaching hospital in Australia which functions as the tertiary referral centre for the northern half of the State of Tasmania. The hospital has more than 32,000 separations per annum, with a spectrum of medical and surgical specialties. Eligible patients were at least 18 years of age and scheduled or expected to have a peripheral IVD indwelling for at least 4 days, and they gave written informed consent. Exclusion criteria were immunosuppression, current bloodstream infection or an IVD already in situ for >48 hours. IVDs were inserted and cared for by the general nursing and medical staff; there was no special IV team or service.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size calculations were performed using PASS 2008 (Version 8.0.8; Kaysville, UT) to detect a change in rates by 30% (from 36% to 25%, two-tailed α = 0.05, 90% power) on the basis of the complication rates of routinely resited IVs in a previous study [16]. Although this indicated that n = 378 per group (total 756) were required, the study was ceased early (total n = 606 IVs) because all investigators left the employment of the institution. Consequently, study power was reduced, but remained over 80% (required minimum n = 282 per group).\n\nBODY.METHODS.RECRUITMENT:\nAll adult patients admitted to the inpatient acute medical and surgical wards of the study hospital were screened by a full-time research nurse. This excluded paediatric, day-surgery, mental health, obstetric, critical care and dialysis units.\n\nBODY.METHODS.STUDY PROCEDURES:\nPatients were randomly assigned (computer generated) in a 1:1 allocation ratio to either the 'routine replacement' (control) or 'clinically indicated replacement' (intervention) group. Assignment was concealed until randomisation by use of a telephone service. A tag was placed on the insertion site indicating the study group. All devices for the patient were managed as per randomised group. The intervention group did not have their IVD resited unless clinically indicated. This decision was made by the treating clinician (not the investigators), who ordered IVD resite if the device failed or phlebitis occurred and ongoing IV treatment was required. The control group had a new device relocated to a different site by the general medical or nursing staff every 3 days. Control devices could also be removed at any stage by the clinical staff if they were not required or if complications occurred. Clinical nursing and medical staff undertook insertion and follow-up care of all IVDs as per the CDC Guidelines [7]. Laboratory staff undertaking microbiological culture assessments were blinded to the study group. Due to the nature of the intervention, patients, research, and clinical staff were unable to be blinded. However, the investigators had no involvement in assessing or documenting complications. IVDs were assessed by the clinical nursing staff on each nursing shift for complications as part of standard clinical practice in the hospital. Times and dates of device insertion and removal were recorded along with the reason for device removal and any protocol deviations. A full-time research nurse collected data from the hospital chart and sought clarification from patients and clinical staff if necessary. Microbiological investigations (device tip, blood cultures and site cultures) were performed by the clinical staff on clinical suspicion of infection by the treating clinician. Demographic and clinical data were collected on age, sex, diagnosis at hospital admission, phlebitis risk based on Tagar et al.'s classification (low/medium/high risk) [20], past history of phlebitis, any comorbidities requiring active medical treatment (e.g., type 2 diabetes or congestive heart failure), haemoglobin, concurrent infection at other sites, antibiotic therapy, type of surgery, type of infusate and any additives (and their level of irritability), vein and skin quality assessment, size of device, insertion site, health professional inserting the device, and setting for insertion, presence of other vascular devices, wound drains and urinary catheters. Vein quality was assessed as good (vein easy to visualise and easy to palpate with tourniquet on), fair (not easily visible but can palpate with tourniquet), or poor (veins small, scarred or difficult to palpate with tourniquet; may require heat pack to aid vasodilation). Skin quality was assessed as good (healthy, well hydrated, elastic), fair (mildly dehydrated, reduced elasticity), or poor (papery, dehydrated, or reduced elasticity).\n\nBODY.METHODS.ANALYTIC APPROACH:\nThe primary outcome was a composite measure of any complication causing unplanned cannula removal prior to completion of IV treatment. The composite included phlebitis, infiltration, occlusion, accidental removal, local infection, and IV device-related bloodstream infection (IVD-BSI). These were also analysed individually as secondary endpoints. A composite measure was chosen due to the low rates of these conditions individually and to the assumption that they are comparable measures of 'infusion failure'; that is, the device can no longer be used to deliver treatment. This approach has been used in previous studies on the topic [15-17]. Phlebitis was defined as two or more of pain, erythema, purulence, streak formation, or a palpable venous cord [3]. Local infection IVD-BSI (bacteremia/fungemia with at least one positive blood culture obtained from a peripheral vein, clinical manifestations of infection, and no apparent source for the bloodstream infection (BSI) except the device with or without positive tip or entry site swab culture) were defined using CDC criteria [7]. Other secondary outcomes were time in situ (hours of catheterisation from insertion to removal, both per patient and per device) [7]; IVDs per patient (number of peripheral devices inserted to complete the course of treatment) [7]; costs (calculations based on 20 minutes nursing or medical insertion time at relevant rates [15], plus the cost of the required equipment (cannula, insertion pack including dressing and solution, gloves, saline, syringe, extension tubing and starter pack for all plus fluid bag, tubing and secondary tubing for medication administration for those patients requiring this) for insertions, nursing time and equipment to routinely remove IVDs that were otherwise functional, and the costs of treating any complications that occurred (e.g., IVD-BSI). Cost calculations were undertaken from the viewpoint of the hospital using negotiated wage costs and purchasing agreements for government hospitals in the State of Tasmania. Costs would be similar for other Australian hospitals. All randomised patients were analysed by intention to treat. Each patient was randomised once and could have multiple IVDs, with subsequent IVD resites managed as per the randomised group. Relative incidence complication rates per 1,000 IVD days and 95% confidence intervals were calculated to summarise the impact of clinically indicated replacement relative to 3-day replacement. Kaplan-Meier survival curves were drawn to compare time to first IVD complication between patients in the two study groups. To assess for any potential impact of protocol violations, a per protocol analysis was also undertaken. All clinical and demographic variables were subjected to univariate testing against the primary endpoint to guide selection of possible covariates for the multivariable model. Cox proportional hazards regression modelling was used to examine the impact of age, gender, oncology status, number of comorbidities (nil, one, two, or more than two), IV gauge, site, vein quality, skin quality, oral antibiotics, IV antibiotics, wound drain, inserter occupation, initial versus subsequent IVDs, phlebitis in a preceeding IVD, haemoglobin level, parenteral nutrition, continuous versus intermittent infusion, patient risk category and study group on the outcome of time to complication events using an additive model [3,5,7,20-25]. In addition, to adjust for any inherent correlations or codependencies in the failure times of IVDs (i.e., same patient multiple failure-time data) within the Cox model, we also used the Prentice-Williams-Peterson conditional risk-set method [26]. The Mann-Whitney test was used to compare various secondary outcomes between study groups. Cost differences were calculated using arithmetic means and the t-test [27]. P values <0.05 were considered significant. All statistical data were entered and analysed using SPSS (Version 15.0; Chicago, IL) and Stata (Version 8.2; College Station, TX).\n\nBODY.RESULTS.SAMPLE:\nOver a 10-month period, 1,954 patients were screened for eligibility. Of these, 788 were eligible, with 362 (46%) recruited into the study. The most frequent exclusion criterion was altered mental state that precluded consideration of consent as assessed by the research nurse. Altered mental state was generally related to older medical patients and the immediate postoperative phase for surgical patients. Reasons for exclusion are shown in Figure 1. The 362 patients were randomised into either the routine change group (n = 177 participants, 323 devices) or the clinically indicated replacement group (n = 185 participants, 280 devices). In total 50,173 IVD hours were studied (routine change group 23,288 hours, clinically indicated group 26,885 hours). More patients in the routine change group had an active infection (53% vs. 44%) and were receiving IV antibiotics (73% vs. 64%). However, as shown in Tables 1 and 2, the two groups were generally comparable at baseline for patient- and cannula-related factors. Figure 1Participant flowchart. Table 1 Baseline characteristics of study participants Variable 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) Sex - Male, n (%) 96 (54%) 103 (56%) Age, mean (SD) 65.1 (17.3) 62.7 (15.4) Reason for admission, n (%) • Gastrointestinal 46 (26%) 52 (28%) • Respiratory 37 (21%) 34 (18%) • Oncology 21 (12%) 21 (11%) • Orthopaedic 16 (9%) 22 (12%) • Cardiac 10 (6%) 10 (5%) • Neurological 9 (5%) 10 (5%) • Vascular 7 (4%) 7 (4%) • Renal 16 (9%) 9 (5%) • Other 15 (8%) 20 (11%) Number of comorbidities, n (%) • None 6 (3.4%) 10 (5.4%) • 1 22 (12.4%) 21 (11.4%) • 2 44 (24.9%) 54 (29.2%) • >2 105 (59.3%) 100 (54.1%) Type of surgery, n (%) • Nil 124 (70%) 132 (71%) • Gastrointestinal 22 (12%) 22 (12%) • Orthopaedic 8 (5%) 15 (8%) • Other 23 (13%) 16 (9%) Most recent Hb - Mean (SD) 124.8 (23.2) 126.2 (21.9) Table 2 Baseline infusion-related characteristics of study devices Variable 3-Day Routine Change Group (n = 323) , n (%) Clinically Indicated Change Group (n = 280) , n (%) IV cannula gauge • 22 43 (13%) 46 (16%) • 20 241 (75%) 201 (72%) • 18 27 (12%) 30 (11%) • Other 2 (1%) 3 (1%) Vein assessment • Good 143 (44.3%) 107 (38.2%) • Fair 160 (49.5%) 144 (51.4%) • Poor 20 (6.2%) 29 (10.4%) Skin integrity • Good 138 (43%) 104 (37%) • Fair 178 (55%) 164 (59%) • Poor 7 (2%) 12 (4%) Past history of phlebitis 2 (0.6%) 4 (1.4%) Insertion site • Hand 206 (64%) 187 (67%) • Forearm 59 (18%) 49 (18%) • Cubital fossa 51 (16%) 38 (14%) • Other 7 (2%) 6 (2%) Receiving infusate 241 (75%) 215 (77%) pH of infusate - Mean (SD) 6.0 (0.5) 6.0 (0.4) Receiving oral antibiotics 24 (7%) 24 (9%) Receiving IV antibiotics 236 (73%) 176 (63%) pH of IV antibiotics - Mean (SD) 6.9 (1.1) 6.9 (1.3) Receiving other IV meds 190 (59%) 179 (64%) pH of other IV meds - Mean (SD) 5.6 (2.6) 6.0 (2.8) Wound drain 50 (16%) 40 (14%) Urinary catheter 55 (17%) 41 (15%) Other vascular device 26 (8%) 24 (9%) Inserted by • Junior doctor 232 (72%) 207 (74%) • Registered Nurse 67 (21%) 57 (20%) • Senior doctor 24 (7%) 16 (6%) Where inserted • Ward 216 (67%) 188 (67%) • Emergency department 74 (23%) 70 (25%) • Other 33 (10%) 22 (8%) Current infection (site) • Respiratory 97 (30%) 49 (18%) • Urinary 24 (7%) 19 (7%) • Wound 16 (5%) 15 (5%) • Other 29 (9%) 37 (13%) • >1 site 5 (2%) 4 (1%) N/A (none) 152 (47%) 156 (56%) Risk of phlebitis (Tagar scale) • Low 174 (54%) 144 (51%) • Medium 149 (46%) 136 (49%) • High 0 0 \n\nBODY.RESULTS.EFFECT OF INTERVENTION ON PRIMARY OUTCOME:\nOutcome data were available for all patients. Table 3 shows the rates of primary and secondary outcomes. Differences in complication rates between groups were not significantly different (routine replacement 66.0 per 1,000 IVD days; clinical replacement 67.8 per 1,000 IVD days; HR 1.03; 95% CI, 0.74-1.43; P = 0.86). As shown in Figure 2, the time to first complication per patient was also not significantly different between groups (Kaplan Meier [KM] with log rank P = 0.53). On crude rate per IVD, the catheters replaced on clinical indication had higher complication rates (110/280 or 39% vs. 91/323 or 28%; P = 0.004). However, total complication rates per patient (to deliver the course of IV therapy) were not significantly different (P = 0.39) between clinically indicated (76/185, 41%) and routine resite patients (64/177, 36%). Table 3 Effect of intervention on primary and secondary endpoints Outcomes 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) RR (95% CI) , P Value Primary: IVD complications per patient, n (%) 64 (36%) 76 (41%) RR 1.14 (0.88, 1.47), p = 0.39 IVD complications per 1000 IVD days 66.0 (95% CI 49.8, 82.1) 67.8 (95% CI 52.6, 83.1) HR 1.03 (0.74, 1.43), p = 0.86 Secondary: Phlebitis, n (%) 12 (7%) 18 (10%) RR 1.44 (0.71, 2.89), p = 0.34 Infiltration, n (%) 53 (30%) 61 (33%) RR 1.10 (0.81, 1.49), p = 0.57 Occlusion, n (%) 5 (3%) 4 (2%) RR 0.77 (0.21, 2.80), p = 0.75 Accidental removal, n (%) 11 (6%) 16 (9%) RR 1.39 (0.66, 2.92), p = 0.43 Local infection 0 0 - IVD-related BSI, n (%) 0 0 - IVD costs per patient, AUD$ mean (SD) $55.42 ($35.26) $43.35 ($26.78) Mean difference $12.07 (95%CI $5.57, $18.56), p < 0.001 Figure 2Kaplan-Meier survival curve of time to first intravenous device complication per patient (log rank, P = 0.53). Patient- and device-related variables considered in the multivariable model were older age, number of comorbidities (nil, one, two or more than two), smaller cannula size, poor skin or vein integrity, IV antibiotics, insertion by medical staff and study group. None of these were found to be statistically significant. The final Cox proportional hazards model after adjusting for time found study group was not a significant factor (HR 1.02; 95% CI, 0.77-1.36; P = 0.89). Variance-adjustment testing for potential multiple-failures per patient (cannula data) found no inconsistency in significant results compared to the main Cox model.\n\nBODY.RESULTS.PROTOCOL COMPLIANCE:\nCompliance with the study intervention was achieved in 78% (251 of 323) of routinely replaced IVDs removed at Day 3 and 100% (280 of 280) of IVDs resited on clinical indication. Noncompliance in the routine resite group was generally related to high staff workloads on that day or to staff's perception that the patient was soon to be discharged or have therapy completed, and so the IVD remained in situ beyond Day 3. A per protocol analysis was performed including only those patients in the routine replacement group whose IVDs were all actually removed by 96 hours (n = 251). This found no significant difference (KM with log rank P = 0.16) in the rate of complications between groups (routine replacement 92 per 1,000 IVD days vs. clinically indicated 68 per 1,000 IVD days).\n\nBODY.RESULTS.EFFECT OF INTERVENTION ON SECONDARY OUTCOMES:\nThere was no statistically significant difference in group outcomes for any phlebitis (P = 0.34), infiltration (P = 0.57), occlusion (P = 0.75), or accidental removal (P = 0.43). No cases of local infection or IVD-related bloodstream infection occurred in either group. For overall IVD therapy (total cannulation time per patient for all devices), clinically indicated devices had a median therapy of 120 hours (quartiles 86.5 and 172.5 hours), and those replaced routinely had median therapy of 113 hours (quartiles 72 and 172 hours) (P = 0.21). For individual IVD dwell times, the clinically indicated group devices had a median dwell time of 85 hours (quartiles 51 and 121 hours), and those replaced routinely had a median dwell time of 71 hours (quartiles 48 and 90 hours) (P < 0.001). The maximum IVD dwell time was 1,023 hours (43 days) in the clinical replacement group, and this cannula was still working well on removal for completion of therapy. The overall number of IVDs per patient was significantly less (P = 0.004) for those replaced on clinical indication (mean 1.5, SD 0.8, median 1, quartiles 1 and 2) than for those routinely replaced (mean 1.8, SD 1.1, median 1, quartiles 1 and 2). A total of 22% of patients in the routinely replaced group had three or more IVDs compared with 9% in the clinical indication group. A total of 82 (28%) IVDs in the routine replacement group were resited after 3 days despite functioning well and ongoing treatment being required. (The remainder removed at this time were no longer required and so not resited, or infusion failure had already occurred.) Mean hospital costs per patient for the course of IV therapy were significantly higher (P < 0.001) for those managed with routine resite (mean $55.42, SD $35.26) compared with resite on clinical indication (mean $43.35, SD $26.78).\n\nBODY.DISCUSSION:\nThe finding that 3-day routine resite was not an effective intervention was consistent across the intention-to-treat primary analysis and the per protocol analysis. There remained no effect when events were expressed per patient or per 1,000 IVD days. Neither composite nor individual complication rates differed between groups, and there were no cases of local or device-related bloodstream infection. It appears safe and practical to leave IVDs in situ as long as they are functioning well and are still needed for clinical treatments. All IVDs will fail eventually, but this study shows that artificially shortening the lifespan of individual catheters does not reduce the overall complication rates over the course of therapy. Our results indicate that the average duration of IV therapy is 5-6 days and that many catheters can remain complication-free for this period. If catheters are not routinely resited, the median dwell time would remain within the 72-96 hours recommended by the CDC, but about 10% would remain in situ for longer (in this study up to 43 days with no complications). Our data show that a policy of resite on clinical indication would mean that one of every two patients would need a single cannula to receive treatment, whereas a 3-day change policy would result in only one in five patients having this scenario, with the rest requiring multiple cannulations and therefore additional pain and inconvenience. The results are consistent with the findings of recent RCTs in both hospitals and the community that have found no benefit in routinely resiting IVDs every 3 days [15-17]. In these studies, many cannulae were inserted by an expert IVD team [15-17], which may have minimised complications in both groups [19]. Our study confirms and extends these findings into the general medical/surgical setting without an IV team where IVDs were inserted by a variety of nursing and medical staff. Data from this study were included in a 2010 Cochrane Collaboration systematic review and meta-analysis on the topic [18]. This review included six trials (n = 3,455) and reported no clinically important or statistically significant difference in catheter-related bloodstream infection or phlebitis between IVDs that were routinely resited (at 48-96 hours) or resited on clinical indication, yet there were significantly lower costs in the group resited on clinical indication [18]. The belief that routine resite of IVDs will prevent complications appears to stem from early observational studies that noted longer-dwelling IVDs had more complications than shorter-dwelling IVDs [9,10]. This is intuitively true, given, for example, that an IVD in situ for 6 days has twice the time exposure of risk than an IVD in situ for 3 days. However, this does not prove that two sequentially inserted IVDs (in the same patient), both used for 3 days, have a combined lower risk over time than the 6-day dwell device. Indeed, this and other recent trials strongly suggest that the risk for the patient over the 6-day period is similar. Well-designed cohort studies with modern catheter materials suggest that the daily risk of phlebitis is relatively stable after the first 24 or 48 hours [3,21,28-31]. The peak in phlebitis between 24 and 48 hours is likely associated with the time taken by the body to mount a biological response after the instigation of therapy; those most likely to develop phlebitis will do so at this time. The results support the extension of the use of peripheral IVDs beyond the 72-96 hours currently recommended by the CDC [7]. There is incongruity in the CDC recommendations; they recommend not to routinely resite IVDs in children or in those with limited venous access. If it is safe in these populations, it is unclear why it would be necessary to routinely resite adults or those with better veins. Higher-risk cannulae such as central venous devices are no longer recommended by the CDC for routine replacement, because trials showed this was not of benefit [7]. Our study also confirms that the CDC guidelines are not always complied with; one fifth of IVDs in the routine change group were not replaced by this time. However, the per protocol analysis showed that the intervention remained ineffective even for those who truly had their IVDs resited every 3 days. Limitations of the study included a 9% higher frequency of IV antibiotics and concurrent infection in the routine resite group. This may have put the group at higher risk due to vein irritation, or conversely it protected against bacterial entry. Neither variable was significant in the multivariable model. The unblinded study design was unavoidable, but also a limitation. Our use of clear outcome measures, a full-time research nurse and laboratory staff blinded to culture assessments should have reduced the risk for potential bias. Resource constraints prematurely ended recruitment, thus reducing the anticipated power of the study from 90% to 80%. Routine IVD resite involves pain for patients, staff procedural time, equipment costs and environmental waste. Contemporary evidence suggests the current policy for routine resite by 72-96 hours is ineffective and should be replaced with a 'resite on clinical indication' policy. It remains imperative that clinical staff monitor IVDs closely and that a daily review of the need for continuing therapy be made, with cessation as soon as possible; the only no-risk IVD is no IVD. Of the 4.3 million acute hospital admissions in Australia each year (excluding day cases), over half have IV treatment [15,32]. Conservatively, if even 2 million courses of IV therapy were managed with clinically indicated rather than routine resite, this would save the unnecessary insertion of approximately 660,000 IVDs and free 280,000 hours of staff insertion time. Assuming our costs are similar to those in other Australian hospitals, a change to resite on clinical indication would save approximately AUD$24 million nationally each year.\n\nBODY.CONCLUSIONS:\nAlthough larger, multisite trials are required, evidence to date suggests that routine resite of peripheral IVDs increases patient discomfort and healthcare costs, but does not reduce IVD complications as has traditionally been thought.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCMR designed the study, applied for funding and drafted the manuscript. DM participated in study design and manuscript preparation, and managed the study. JM recruited patients, ensured protocol integrity and collected data. MRM undertook statistical analyses and assisted with drafting the manuscript. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nCMR, PhD is Professor, Research Centre for Clinical and Community Practice Innovation, Griffith University, Australia. DM holds a Masters by Research and is Senior Lecturer, University of Tasmania, Australia. JM is an RN and Nurse Unit Manager, Calvary Tasmania, Australia. MRM is a PhD qualified Biostatistician, Gippsland Medical School, Monash University, Australia.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1741-7015/8/53/prepub\n\n**Question:** Compared to staff inclination replacement what was the result of routine replacement on cost per patient?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
105
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on HbA1c level at 26 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
187
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Bleeding during surgery?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
133
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Proinsulin : insulin ratio?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
103
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Postprandial plasma glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
158
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on Self-selected overground walk velocity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
174
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Fever resolution by day 1?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
179
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Pruritus?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
126
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on ADA postprandial plasma glucose goals less than 10.0 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
118
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on ADA fasting plasma glucose goals between 5.0 mmol/l and less than 7.2 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
132
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Proinsulin : insulin ratio?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
194
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Midwife-led unit on Labour dystocia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
190
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Pain killers intake?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
122
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on ADA fasting plasma glucose goals between 5.0 mmol/l and less than 7.2 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
198
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Midwife-led unit on Postpartum haemorrhage?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
172
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Serious adverse events?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
167
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Trends in Use of Referral Hospital Services for Care of Sick Newborns in a Community-based Intervention in Tangail District, Bangladesh\n\n ABSTRACT:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district), Tangail district, Bangladesh, is promoting care-seeking for sick newborns through health education of families, identification and referral of sick newborns in the community by community health workers (CHWs), and strengthening of neonatal care in Kumudini Hospital, Mirzapur. Data were drawn from records maintained by the CHWs, referral hospital registers, a baseline household survey of recently-delivered women conducted from March to June 2003, and two interim household surveys in January and September 2005. Increases were observed in self-referral of sick newborns for care, compliance after referral by the CHWs, and care-seeking from qualified providers and from the Kumudini Hospital, and decreases were observed in care-seeking from unqualified providers in the intervention arm. An active surveillance for illness by the CHWs in the home, education of families by them on recognition of danger signs and counselling to seek immediate care for serious illness, and improved linkages between the community and the hospital can produce substantial increases in care-seeking for sick newborns.\n\nBODY.INTRODUCTION:\nThe timely and appropriate use of health services is crucial to reduce maternal and child mortality (1–4). Many lifesaving interventions, such as caesarean section, blood transfusion, oxygen, and intravenous antibiotics, can only be made available through health facilities. Evidence suggests that bringing women and children to facilities to receive these services is associated with reductions in mortality (1, 4). Countries that have achieved high rates of deliveries in facilities for basic or comprehensive essential obstetric care have witnessed significant and sustained decreases in maternal mortality (4), while countries, such as Sri Lanka, with elevated rates of care-seeking for sick children, have much lower rates of mortality among children aged less than five years (under-five mortality) than would be predicted from their per-capita income (1). Numerous studies have examined community-based interventions to improve care-seeking and referral for maternal emergencies from the community to first- and second-level facilities (3–8). Murray and Pearson have recently published a systematic review and proposed a research agendum to identify how programmes can better promote timely and appropriate maternal referral (9). Sibley has reviewed the effectiveness of traditional birth attendants (TBAs) in promoting referral from the community to facilities offering emergency obstetric care (10). Much less is known about referral of sick newborns from the community to health facilities. While several studies have examined referral of children, aged less than five-years, from first-level to second-level facilities (11–13), few studies have specifically examined referral from the community to facilities (14), and even less is known about referral of newborns from the community to facilities. Many factors affecting referral and care-seeking for maternal conditions from the community to health facilities could be applicable to promoting care for sick newborns. First, there is a need to act rapidly for certain maternal and newborn conditions, such as severe postpartum haemorrhage and birth asphyxia. So, research needs to examine not only recognition of danger signs, but also how long it takes for recognition of the problem to occur. The constraints on rapid action by families, such as distance, poor conditions of road, lack of transport, and lack of money, are common to both. Macintyre and Hotchkiss have developed a conceptual framework of factors at the individual, household, and community levels affecting referral in Africa which is equally applicable to other regions of the world (15). Second, in both mothers and newborns, many important causes of morbidity and mortality have signs and symptoms that \"lie on a continuum, from normal to abnormal\" (16). For such signs and symptoms, there can be both over-reporting of non-serious conditions, such as transient tachypnoea of the newborn or upper respiratory viral infection, or under-reporting of truly serious conditions, as happens when families fail to recognize excessive loss of maternal blood after delivery (16). Finally, patterns of decision-making within the household may lead to a significant delay, especially when permission of the husband is needed before seeking care but he is away, or when it is not clear to the family where to seek care from among a range of formal and informal sector providers (17–19). While there is much to learn from previous research on care-seeking and referral for older children, there are also obstacles to promoting early and appropriate care that are specific to newborns. In many cultures, families practise a period of postpartum confinement of both mother and newborn lasting from one to six week(s) or more (20). Additional efforts may be needed during this period to convince families to seek care outside the home. Sometimes, it is also difficult to detect danger signs in sick newborns, and families may not understand the significance of signs, such as hypothermia, feeding problems, or lethargy (21). This paper describes the trends in compliance by families with referrals when sick newborns were identified by community health workers (CHWs) and were referred to the Kumudini Hospital for care. In this project, families are educated about danger signs, and the CHWs visit the home during the postpartum period and examine newborns for any signs indicating the need for urgent medical care. Actions to increase the rate of compliance with referrals and their effects are also described.\n\nBODY.MATERIALS AND METHODS.STUDY SITE:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district) of Tangail district in central Bangladesh is implementing an intervention aimed at improving maternal and newborn-care practices and care-seeking for maternal and newborn conditions through: (a) behaviour change communication, (b) identification and referral of sick newborns in the community, and (c) strengthening of neonatal care in health facilities. The cluster-randomized trial has two arms: an intervention arm with CHWs delivering a package of maternal and newborn-care interventions in the home and a comparison arm. Mirzapur upazila has 13 unions, with a population of around 24,000 each; of these, six were randomly allocated to each study arm, excluding the one urban union. Given the need to have sick neonates assessed and treated in the hospital to identify aetiology of infections, a major focus of the problem is to identify barriers to care-seeking and design of strategies to address those barriers. The Kumudini Hospital, a 750-bed private hospital run by the Kumudini Welfare Trust, is situated at the centre of the project area. The hospital has a large paediatric unit (total 65 beds, including one separate neonatal ward) with two full-time consultants and 7–8 regular physicians.\n\nBODY.MATERIALS AND METHODS.DESCRIPTION OF THE INTERVENTION MODEL:\nIn the Projahnmo-II project, 36 CHWs were recruited and provided one month of initial training to equip them to provide a package of maternal and newborn care. These CHWs had a minimum of 10th grade education and resided in the population they would serve. Each CHW was responsible for about 4,000 people. The CHWs carried out bi-monthly pregnancy surveillance and registration of married women of reproductive age (MWRA) and made home-visits in the third and the eighth month of pregnancy to counsel families on birth and neonatal care preparedness (BNCP). After delivery, the CHWs made home-visits to promote evidence-based domiciliary newborn care and to identify and refer sick newborns and mothers on day 0 (day of birth), 3, 6, and 9. Improvements were made in maternal and neonatal healthcare at the designated referral facility (Kumudini Hospital), and the CHWs facilitated referrals of sick newborns they identified during home-visits to this hospital. For families that refused referral and for babies who had at least one danger sign of very severe disease, or any two from possible very severe disease, the CHWs carried out home-treatment of cases with suspected serious infection with oral co-trimoxazole. The Field Supervisors supervised the daily activities of CHWs in the community and also reviewed the key performance and process indicators relating to coverage and quality every fortnight and provided feedback to the CHWs. Figure 1 is a model that shows how the intervention package helps promote hospital care for sick newborns. During the antenatal period, families were educated about signs indicating the need to seek care and sources of care by health workers during antenatal care visits at health facilities and by CHWs during antenatal home-visits (left side of Fig. 1). This should lead to an increased recognition by families of danger signs in newborns. This, in turn, should lead them either to seek care directly (self-referral) from the Kumudini Hospital and other appropriate sources of care, or notify the CHW to come to the house and assess the child. The CHW may also come in contact with a sick newborn during the course of her routine postnatal home-visits, and all findings are recorded in a Visit Record Form (VRF). The criteria for referral of sick newborns are: (a) in the case of birth asphyxia: if breathing difficulty continues 20 minutes after birth despite resuscitation efforts; (b) if there is one or more signs/symptoms of very severe disease, such as fever or lethargy; (c) jaundice—any where in the body within 24 hours of birth; (d) eyes discharging pus (possible gonococcal eye infection); and/or (e) diarrhoea with blood in stool and/or dehydration. Fig. 1.Intervention model: promotion by community health workers of care for sick newborns at Kumudini Hospital between April 2004 and September 2005 (Table 1) Dotted arrow indicates action not anticipated in the intervention model\n*Coverage estimates from the second adequacy survey, September 2005\nSources of data: Project management information system (records maintained by CHWs and hospital registers) and household survey (second adequacy survey in September 2005)\nANC=Antenatal care;\nBNCP=Birth and neonatal care preparedness;\nCHWs=Community health workers A standard algorithm adapted from integrated management of childhood illness (IMCI) for use in the community by the CHWs is followed to assess and classify sickness in newborns. If the newborn requires referral, the CHW facilitates referral to the Kumudini Hospital. The community-based system of facilitated referral was in place by 19 February 2004 and initially consisted of the following elements, in addition to home-visits by the CHWs: (a) referral slips for the CHWs to fill in when referring a sick newborn to the hospital; (b) Birth and Neonatal Care Preparedness (BNCP) Cards, with an identification number, are supplied to families during antenatal home-visits by the CHWs. Families can carry the BNCP Card with them to the Kumudini Hospital in the event that the CHW is not available to issue a referral slip to the family when the newborn falls ill; (c) a referral-tracking form; (d) free inpatient care at the Kumudini Hospital for newborns arriving with a referral slip; (e) a system of emergency transport; and (f) training of TBAs, so that they could also promote referral to hospital for newborns with danger signs. If referral to the Kumudini Hospital fails, additional follow-up visits in the home are made to follow the condition of the child and treat presumptively with antibiotics, if appropriate. The CHW makes a final visit—called a graduation visit—as soon as the baby crosses 28 days of life. At that time, the completed VRF goes to the Mirzapur field office for review and is then sent to the main project office in Dhaka for data entry and further review.\n\nBODY.MATERIALS AND METHODS.MODIFICATIONS TO THE INTERVENTION MODEL:\nThe CHWs helped families to arrange transportation, convinced family members to have the newborn treated outside the home, and provided a transport allowance to the poorest families to reach the Kumudini Hospital. After three months of initial implementation of the programme, further changes were made to improve coverage with home-visits and compliance with referrals. A referral-tracking form was introduced in April 2004, and every two weeks, the number of newborns referred and the outcome of referral were reviewed in a meeting with the supervisors and CHWs. In early 2005, a decision was made to emphasize more the management and referral of birth asphyxia and low-birth-weight newborns. The CHWs started to use digital weighing machines in February 2005 to obtain the weight of the newborn at first contact. In April 2005, the CHWs received refresher training on how to counsel families during antenatal home-visits on low birth-weight and birth asphyxia.\n\nBODY.MATERIALS AND METHODS.MONITORING OF FUNCTIONING OF THE REFERRAL SYSTEM:\nData are presented from the project management information system (MIS) for the April 2004–September 2005 period, which includes the records maintained by the CHWs and registers maintained in the referral hospital (Kumudini Hospital). In addition, in-depth interviews were undertaken at baseline and during implementation to investigate the factors affecting compliance. Results of the interviews with parents appearing at the Kumudini Hospital and from those who did not comply with referral advice were shared with the CHWs and Field Supervisors to identify ways to improve counselling on referral.\n\nBODY.MATERIALS AND METHODS.SAMPLING AND SAMPLE SIZE:\nA baseline household survey among recently-delivered women was conducted in early 2003. Demographic and socioeconomic information of the listed households was collected, and information on birth-history and neonatal mortality was collected from all 14,526 women who had a pregnancy outcome in the 36 months preceding the survey. Information on knowledge, practices, and coverage of pregnancy, childbirth, and postpartum/postnatal care of mothers and newborns was collected from a randomly-selected sub-set of 4,611 recently-delivered women who had a pregnancy outcome in the last one year. Two interim household adequacy surveys were conducted in January and September 2005 to measure the adequacy of project inputs and selected process indicators to assess progress in early changes in behavioural patterns, including care-seeking. Identified through a systematic random-sampling method, in total, 1,200 women who had a pregnancy outcome in the last 7–8 months in each of the intervention and comparison arms were interviewed in each of the interim household surveys. Eighty-four randomly-selected parents arriving in the Outpatient Department of the Kumudini Hospital during January-June 2005 were asked why they had come to the hospital. Reasons for non-compliance with referral were analyzed on a continual basis and contributed to fine-tuning of the system of facilitated referral. Randomly-selected parents of 162 newborns who were referred for care but did not comply with referral during the same period mentioned above were interviewed regarding their reasons for non-compliance. Structured brief questionnaires were used in both instances.\n\nBODY.RESULTS.FUNCTIONING OF THE REFERRAL SYSTEM:\nResults of the second adequacy survey conducted in September 2005 showed that 72.5% of the recently-delivered women had attended at least one antenatal care visit, and 87.6% had received at least one antenatal BNCP visit by a CHW. Table 1 shows the trends between April 2004 and September 2005 in assessment, referral, and admission of sick newborns in the study intervention arm. Figure 1 presents data for the entire period. Although the project staff judged that the CHWs succeeded in identifying most pregnant women, the CHWs documented deliveries for only 3,354 (74.4%) of the 4,508 women estimated to have their due date during this period. The primary reason for this lower-than-expected figure was that significant numbers of women, particularly primigravidae, migrated at some point prior to delivery to live in another household located outside the intervention arm of the study. In most cases, they left the household of their husband's family (shashurbari) to reside in their natal home (baperbari), a phenomenon also observed in other sites in Bangladesh (20). Of 3,354 women who did not change residence, 3,228 (96.2%) received at least one home-visit by the CHW during the first 28 days of life of the baby. Table 1. Trends over time in assessment, referral, and admission of sick newborns in Mirzapur sub-district, Tangail district, Bangladesh between April 2004 and September 2005 (*indicates that figures are also displayed in Fig. 1 ) Variable and statistical assessment of trends Apr-Jun 2004 Jul-Sep 2004 Oct-Dec 2004 Jan-Mar 2005 Apr-Jun 2005 Jul-Sep 2005 Total Apr 2004-Sept 2005* Assessment and referral of sick newborns in the community by CHWs Home-deliveries 417 574 870 541 433 519 3,354* CHW-visit within first 28 days 324 443 862 659 436 504 3,228* Newborns assessed as sick 134 156 190 84 111 119 794* Referred to Kumudini Hospital 115 148 161 71 87 102 684* Percentage of sick newborns who were referred 85.8 94.9 84.7 84.5 78.4 85.7 86.1 Chi-square for linear trend=NS Arrival and admission at outpatient/emergency department of Kumudini Hospital Neonates reaching Kumudini Hospital OPD/emergency after self-referral or referral by CHWs 89 146 211 128 159 188 921* Neonates reaching Kumudini OPD/emergency after self-referral 25 55 82 75 95 111 443* Neonates reaching Kumudini Hospital OPD/emergency with CHW referral slip 64 91 129 53 64 77 478* Chi-square for linear trend=43.5, df=1, p<0.00001 71.9 62.3 61.1 41.4 40.3 41.0 51.9 Percentage of newborns referred by CHWs who arrived at Kumudini Hospital OPD/emergency 55.7 61.5 80.1 74.6 73.6 75.5 69.9 Chi-square for linear trend=12.97, df=1, p=0.00032 CHW=Community health worker; df=Degree of freedom; NS=Not significant; OPD=Outpatient department The CHWs identified 794 newborns as sick during this period, excluding newborns with feeding problems. Of these, 684 (86.1%) were referred by the CHWs to the Kumudini Hospital for care. The proportion of sick newborns who were referred stayed essentially constant between April 2004 and September 2005 (non-significant chi-square test for linear trend). Newborns arriving from households located in the intervention arm could either (a) have been referred by the CHW after she examined the child during a home-visit and issued a referral slip, or (b) the family could have taken the decision to seek care directly without first contacting the CHW, a situation we refer to as self-referral. Overall, of the 921 newborns arriving at the outpatient or emergency departments of the Kumudini Hospital during this period, 443 (48.1%) arrived after self-referral, and 478 (51.9%) arrived with a referral slip issued by the CHWs. The proportion of all cases who arrived with a referral slip declined continuously during this period (Row 8 of Table 1), from 71.9% at the beginning of implementation between April and June 2004 to 41.0% between July and September 2005, a trend which was highly significant (chi-square for linear trend=43.5, df=1, p<0.00001). Compliance with referral to the Kumudini Hospital by the CHWs increased from 55.7% during the first three-month period of implementation to 80.1% during the third three-month period of implementation (Row 9 of Table 1) and was thereafter maintained at 75–80%. The overall trend was significant (p=0.00032).\n\nBODY.RESULTS.INTERVIEWS ON FACTORS AFFECTING COMPLIANCE:\nEighty-four parents arriving in the Outpatient Department of the Kumudini Hospital were asked why they had come to the hospital. They mentioned (multiple responses allowed) that the CHWs advised them to visit the Kumudini Hospital because treatment was available (65.5%), treatment was of high quality (34.5%) and free of charge (21.4%), the hospital was the nearest one to their home (2.4%), and other reasons (4.8%). Parents of 162 newborns who were referred for care but did not comply with referral were interviewed. The reasons cited for non-compliance (multiple responses allowed) included: nobody was available to accompany the child (and the mother) to the health facility (24.7%); the child was given a traditional treatment instead (19.1%); bad weather or general strikes (17.9%); the family disliked hospital treatment (12.3%); symptoms resolved on their own (7.4%); unwillingness of the family or the TBA to refer the baby for other reasons (6.2%); and other issues (12.3%), such as illness of the mother; the child was too young to be taken for outside care; and lack of transport. Although distance was a commonly-cited reason for failure to seek care from the health facilities, the proportion of cases referred by the CHWs in the farthest unions in the intervention arm, Warsi (2 hours away), Ajgana (1.5 hours away), and Bahuria (1.5 hours away) were at approximately the same level (79.3%, 80.6%, and 82.7% respectively) as the closest unions that were 0.5 hours away from the Kumudini Hospital, Banail (87.9%), and Bhatgram (81.6%).\n\nBODY.RESULTS.EVALUATION OF TRENDS IN CARE-SEEKING:\nTable 2 demonstrates the changes in care-seeking/self-referral to the Kumudini Hospital and other providers between the baseline survey (January 2003) and the first (January 2005) and the second (September 2005) adequacy survey. Caution is necessary in assigning significance to the observed trends as the two adequacy surveys are based on much smaller samples than the baseline survey. At the time of the baseline household survey in January 2003, there was no significant difference between the intervention arm and the comparison arm of the study in the proportion of sick newborns who were taken outside the home for care from any qualified provider (including Kumudini Hospital), to the Kumudini Hospital specifically, or to an unqualified provider, most commonly an unlicensed 'village doctor'. Table 2. Trends in care-seeking for sick newborns from Kumudini Hospital and other providers based on population-based household surveys Measures of care-seeking Baseline survey: January 2003 First adequacy ssurvey: January 2005 Second adequacy survey: September 2005 Intervention arm Comparison arm Intervention arm Comparison arm Intervention arm Comparison arm Reported sickness among newborns in the sample Total number of newborns in the sample 2,053 2,290 523 550 520 548 Number of newborns reported to have been sick (%) 818 (37.5) 780 (37.6) 255 (48.8) 279 (50.7) 207 (39.8) 257 (46.9) Reported care-seeking outside home Proportion of sick newborns reported to have been given any care in or outside home 92.9 93.7 93.3 93.2 93.2 95.3 Proportion of sick newborns for whom care was sought from outside home 66.1 66.4 82.8 81.4 82.6 77.4 Reported care-seeking from qualified providers ( Fig. 2 ) Proportion of sick newborns for whom care was sought from qualified providers 31.2 29.6 55.7 38.4 60.4 33.9 Odds ratio for care from qualified providers, intervention vs comparison (95% CI) 1.08 (0.86–1.34) (p=0.499) 2.02 (1.41–2.90) (p<0.0001) 2.98 (2.00–4.44) (p<0.0001) Chi-square trend test for care from qualified providers, intervention group Chi-square for linear trend=80.13, df=1, p<0.00001 Chi-square trend test for care from qualified providers, comparison group Chi-square for linear trend=3.42, df=1, p=0.065 Reported care-seeking from Kumudini Hospital ( Fig. 3 ) Proportion of sick newborns for whom care was sought from Kumudini Hospital 17.9 17.6 42.0 21.9 46.4 23.0 Odds ratio for care from Kumudini Hospital, intervention vs comparison (95% CI) 1.02 (0.78–1.33) (p<0.882) 2.58 (1.74–3.84) (p<0.0001) 2.90 (1.91–4.41) (p<0.0001) Chi-square trend test for care from Kumudini Hospital, intervention Group Chi-square for linear trend=93.40, df=1, p<0.00001 Chi-square trend test for care from Kumudini Hospital, comparison Group Chi-square for linear trend=4.47, df=1, p=0.035 Reported care-seeking from unqualified providers ( Fig. 4 ) Proportion of sick newborns for whom care was sought from unqualified providers 66.7 67.9 49.8 66.0 36.7 65.0 Odds ratio for care from unqualified providers, intervention vs comparison (95% CI) 0.95 (0.76–1.17) (p<0.609) 0.51 (0.36–0.74) (p=0.0002) 0.31 (0.21–0.47) (p<0.0001) Chi-square trend test for care from unqualified providers, intervention group Chi-square for linear trend=71.01, df=1, p<0.00001 Chi-square trend test for care from unqualified providers, comparison group Chi-square for linear trend=0.90, df=1, p=0.34 CI=Confidence interval; df=Degree of freedom Between the time of the baseline and the first adequacy survey, there was a significant increase in care-seeking in both intervention and comparison arms of the study (Row 4 of Table 2). This difference could be due to both increased awareness of the newborn's health problems and/or changes in how the survey was administered. Figure 2 demonstrates that there was a highly significant (p<0.00001) increase in the proportion of families that sought care from qualified providers for sick newborns in the intervention arm (Fig. 2 and Rows 5 and 7 of Table 2) and a non-significant increase in the comparison arm (Rows 5 and 8). Figure 3 shows that care-seeking for sick newborns specifically from the Kumudini Hospital increased significantly in both intervention and comparison arms, but the increase was of a much greater magnitude in the intervention arm (Fig. 3 and Row 9–12 of Table 2). Finally, Figure 4 demonstrates that the proportion of families who sought care from unqualified providers, such as unlicensed village doctors, remained unchanged in the comparison arm, but declined significantly in the intervention arm (Fig. 4 and Row 13–16 of Table 2). Fig. 2.Trend in proportion of sick newborns for whom care was sought from qualified providers*p<0.0001; Chi-square for linear trend (intervention) 80.13 (p<0.00001)\nOR=Odds ration Fig. 3.Trend in proportion of sick newborns for whom care was sought from Kumudini Hospital*p<0.0001; Chi-square for linear trend (intervention) 93.4 (p<0.00001)\nOR=Odds ratio Fig. 4.Trend in proportion of sick newborns for whom care was sought from unqualified providers*p<0.0001; Chi-square for linear trend (intervention) 71.01 (p<0.00001)\nOR=Odds ratio\n\nBODY.DISCUSSION:\nSignificant reductions in neonatal mortality must be made to reach the Millennium Development Goal for under-five mortality. One key to reducing neonatal mortality is to ensure that sick newborns are assessed and treated quickly either in the home (22, 23) or in a health facility. Practices of postpartum confinement of mothers and newborns found in many cultures, difficulties in transport, and patterns of household decision-making are among the factors that can delay or prevent care-seeking outside the home. Data presented in this paper demonstrate that it is possible to achieve high rates of care-seeking from hospitals or other qualified providers and to significantly decrease care-seeking from unqualified providers, even in a low-income rural area where all these factors are present. The trends observed in the intervention arm included increased care-seeking, increased proportion of sick newborns arriving at the Kumudini Hospital after self-referral rather than referral by a CHW, increased compliance after referral by the CHWs, increased care-seeking from the qualified providers (Fig. 2) and from the Kumudini Hospital (Fig. 3), and decreases in care-seeking from the unqualified providers (Fig. 4). In the comparison arm, an increase in care-seeking from the Kumudini Hospital was also observed, but the proportions seeking care from the qualified and unqualified providers did not change significantly. Reasons for the increasing trend in the proportion of cases in the intervention arm arriving at the Kumudini Hospital after self-referral have not yet been fully elucidated, but include increasing awareness of the signs of illness in newborns and experience with the services offered by the Kumudini Hospital. There also appeared to be some cases where the CHWs judged that the newborns did not require referral, but the family decided to seek care from the Kumudini Hospital anyway. In a number of these cases, the child had physiologic jaundice, a condition which the family felt warranted further investigation, despite reassurances provided by the CHWs. The project investigators are currently investigating this situation further. Substantial increases in referral compliance for newborn illness were likely related to (a) education of families on danger signs by the CHWs; (b) active surveillance for illness by the CHWs during routine postnatal home-visits; (c) facilitated referral by the CHWs, including counselling, use of referral slips along with improved linkages between community and hospital; (d) incentives for labour/birth notification; (e) enhanced capacity at the referral-care centre to manage sick newborns; and (f) availability of subsidized treatment. Sustained community-level education enhanced the empowerment of families towards decision-making for self-referral. In low-income countries with high rates of neonatal mortality, sick newborns can either be treated presumptively in the home (22, 23) or referred to health facilities. This paper demonstrates that it is possible to achieve high rates of compliance with referral, but to do this requires an extensive infrastructure of CHWs or other community contact persons (8) to assess newborns and facilitate referrals. Alternatively, an increased emphasis could be placed on community mobilization, education on danger signs, and facilitation of self-referral, perhaps with similar results. This paper is one of the only studies to provide data on levels of referral compliance achieved through facilitated referral (12, 14). Whether the emphasis is on treatment in facilities or treatment in the community, substantial investments will need to be made in the creation of demand with the community, community and family education, and facilitation of referral.\n\nBODY.ACKNOWLEDGEMENTS:\nThis study was supported primarily through the generous support of the Infectious Disease Initiative of the Wellcome Trust–Burroughs Wellcome Fund. Additional support was provided by the Department for International Development (DFID), UK; the United States Agency for International Development, Office of Health, Infectious Diseases, and Nutrition, Global Bureau through the Global Research Activity Cooperative Agreement (No. GHS-A-00-03-00019-00); the Government of Bangladesh (Improved Health for the Poor); and Save the Children-USA through a grant from the Bill and Melinda Gates Foundation. The authors thank the study participants in Mirzapur upazila, Bangladesh, who were generous with their time and patience with interviewers through the several rounds of interviews.\n\n**Question:** Compared to Comparison arm what was the result of Promotion by CHWs of maternal and newborn-care interventions on Care-seeking from unqualified providers (such as village doctors) for ill newborns ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
202
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Immunogenicity and Smoking Cessation Outcomes for a Novel Nicotine Immunotherapeutic\n\n ABSTRACT:\nNicVAX®, a nicotine vaccine (3'AmNic-rEPA), has been clinically evaluated to determine if higher antibody concentrations are associated with higher smoking abstinence rates and if doses and frequency of administration are associated with increased antibody response. This randomized, double-blinded, placebo-controlled multicenter clinical trial (N=301 smokers) tested 200 and 400 μg doses administered 4 or 5 times over 6 months compared to placebo. 3'AmNic-rEPA recipients with the highest serum anti-nicotine antibody response (top 30% by AUC) were significantly more likely to attain 8 weeks continuous abstinence from weeks 19 through 26 than the placebo recipients (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). The 5 injection 400 μg dose regimen had the greatest antibody response and had significantly higher abstinence rates than placebo. This study demonstrates proof-of-concept that 3'AmNic-rEPA elicits antibodies to nicotine and is associated with higher continuous abstinence rates, justifying its further development as a treatment for nicotine dependence.\n\nBODY.INTRODUCTION:\nWorldwide, smoking prevalence is 1.2 billion and approximately 5 million people die each year of smoking caused illnesses [1]. The global rate of smoking and smoking related deaths is anticipated to increase over the next 20 years unless significant public health measures are instituted. These include effective cessation interventions such as pharmacological treatments, which improve cessation rates by 1.5 to 3 fold over placebo intervention [2, 3]. Approved pharmacotherapies (e.g., nicotine replacements, bupropion SR, varenicline) for smoking cessation act on the central nervous system, each with a different mechanism of action. Other novel medications are being developed including immunotherapeutics targeting nicotine. Nicotine conjugate vaccines stimulate the immune system to develop nicotine specific antibodies (Abs) using an immunogen comprised of nicotine covalently linked to a larger carrier protein. Conceptually, the mechanism of action is that anti-nicotine antibodies bind nicotine molecules and the resulting complex is too large to cross the blood-brain barrier. With increasing Ab levels more nicotine is captured and sequestered in the blood and prevented from entering the brain, leading to less reinforcing effects from nicotine. Animal studies have demonstrated that passive or active immunization results in approximately 30% to 90% less nicotine entering the brain compared to control rats [4–7] and attenuated locomotor [4, 5] and behavioral [8, 9] responses to nicotine. Furthermore, vaccination reduced nicotine elimination from the body in a study with rats [10, 11], which may also contribute to reduced smoking. Although human studies are limited, published data evaluating different nicotine vaccines support the general concept that nicotine vaccines can be effective for smoking cessation in some smokers [12, 13]. Unfortunately, these studies either had small sample sizes [12], did not use an intent-to-treat population of smokers [13] or did not perform statistical analysis of the data [14]. The primary aim of the present study was to establish the proof-of-concept that (i) anti-nicotine antibodies are useful as an aid to smoking cessation and (ii) higher serum anti-nicotine antibody concentrations are associated with higher abstinence rates in an intent-to-treat population of smokers. One of the challenges with immunotherapeutics, such as vaccines, is attainment of therapeutic levels of antibody in most people. Therefore, this study tested two different doses of 3'-aminomethylnicotine P. aeruginosa r-exoprotein A - NicVAX (3'AmNic-rEPA) to identify a dose and schedule for further development: 200 and 400 μg across two different schedules (4 or 5 injections) compared to placebo for immunogenicity, efficacy and safety.\n\nBODY.RESULTS:\nA total of 301 subjects were randomized. Figure 2 shows the disposition and number of subjects within each treatment group. No significant group differences were observed in the demographic or smoking history by treatment or antibody levels (see Table 1).\n\nBODY.RESULTS.COMPLIANCE:\nAll 301 subjects received injection 1, 96.7%, 84.1%, 72.4% and 61.2% received injections 2, 3, 4 and 5 (Schedule 2 subjects only), respectively. No significant differences were observed across treatment groups for subjects receiving injections 2 through 4 for Schedules 1 and 2. Mean in-study duration was 286 ± 121 days.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON ABSTINENCE:\nHigh Ab responders to 3'AmNic-rEPA were defined as the top 30% of responders by AUC (0 to 26 weeks) and the low Ab group as the remaining bottom 70% of responders. 3'AmNic-rEPA recipients in the high Ab group were significantly more likely to attain 8 weeks of continuous abstinence from weeks 19 through 26 than placebo (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). No significant differences were observed between the 3'AmNic-rEPA low Ab group vs. placebo (9.3% vs. 12.0%., p=0.46). As a secondary outcome, continuous abstinence rate (CAR) to 52 weeks were evaluated from weeks 19 to 52 and were significantly higher for the high Ab group vs. placebo (19.7% vs. 10.0%, p=0.044, OR=2.64, 95% CI, 1.03–6.79) with no significant difference between the low Ab group and placebo (7.1% vs. 10.0%, p=0.43). 7-day point prevalence abstinence results show that subjects with high Ab levels were significantly more likely to abstain compared to placebo at 26 weeks (36.1% vs. 16.0%, p=0.0024, OR=3.30, 95% CI, 1.53–7.13) and 52 weeks (31.1% vs. 12.0%, p=0.0021, OR=3.69, 95% CI, 0.42–2.14). No significant differences were observed in the point prevalence abstinence rates between the low Ab group and placebo at 26 and 52 weeks (12.9% vs. 16.0%, p=0.51 and 11.4% vs. 12.0%, p=0.89, respectively). As shown in Figure 3A, abstinence rates remained essentially the same following the target quit date (TQD) for the duration of the study. To further validate the proof-of-concept, the relationship between abstinence during the final eight weeks of the study and anti-nicotine Ab concentrations (AUC) is shown in Figure 3B for all subjects receiving the vaccine. Continuous abstinence rates from week 45–52 are displayed for each 10th percentile increase in AUC. The proportion of abstinent subjects increased with increasing AUC percentile, and the ordered ranking maintained.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON TIME TO CONTINUOUS ABSTINENCE:\nAn exploratory analysis examined the rate and time to continuous abstinence through study end (Figure 3C). Most smokers quit soon after the TQD, with a clear divergence of the high Ab group from the placebo and low Ab group. Among the 18 high Ab continuous abstainers, 12 initiated abstinence prior to the primary endpoint while 6 initiated their abstinence after the start of the primary endpoint. Furthermore, 3 of the 15 subjects who abstained during the primary endpoint relapsed by the end of the study. Cox proportional hazards analysis demonstrated superiority of the high Ab group compared to placebo (p=0.0069, hazard ratio of 2.76).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EVALUATION OF LONG-TERM ABSTINENCE:\nAs most subjects achieved abstinence shortly after their TQD, additional analyses were undertaken to evaluate prolonged abstinence to 6 and 12 months allowing for a 2 week grace period after the TQD [15]. (Prolonged abstinence is defined as not a single puff during the period from 2 weeks after the TQD for 20 weeks and 44 weeks, respectively). Prolonged abstinence rates to 6 months were significantly higher in the high Ab group vs. placebo (19.7% vs. 6.0%, p=0.0060, OR=4.41, 95% CI, 1.53–12.71) with no significant differences between the placebo and low Ab groups (7.9% vs. 6.0%, p=0.60). Subjects with high Ab were also significantly more likely to be abstinent for 12 months compared to placebo (18.0% vs. 6.0%, p=0.014; OR of 3.84; 95% CI, 1.32–11.20). The low Ab group did not differ significantly from placebo (7.1% vs. 6.0%, p=0.67).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.CIGARETTE SMOKING IN NON-QUITTERS:\nStatistically significant differences were observed in reduction of daily cigarette consumption and cotinine between non-abstainers (weeks 19–52) with high Ab levels and non-abstainers in the placebo group (p=0.0015 and 0.019, respectively; see Figures 4A and 4C. The difference in the median reduction in cigarette consumption, following the TQD, between the high Ab non-abstainers and placebo non-abstainers was on average 4.6 cigarettes per day. Similarly, cotinine geometric mean concentrations (GMCs) were 19.0% lower on average following the target quit date in the high Ab non-abstainers as compared to placebo non-abstainers. Median cigarettes per day and cotinine GMC for placebo and low Ab group are nearly identical over the study period. Differences in mean CO were not observed across all three groups (see Figure 4B). 15 out of the 301 subjects smoked more than a 2-fold higher number of cigarettes following the TQD as compared to baseline with no significant difference between the placebo (n=4/100) and 3'AmNic-rEPA (n=11/201) groups. The highest smoking levels observed post-TQD were 5-fold baseline in the placebo and 4-fold baseline in the 3'AmNic-rEPA groups. Elevated smoking levels for 11 of these 15 subjects returned to below 2-fold baseline by study end. Subjects with remaining elevated levels were similar between the 3'AmNic-rEPA group (n=3/201) and placebo (n=1/100). Individual subjects with CO levels elevated by 2-fold or higher than baseline were also assessed and results were similar with no significant difference between the placebo (n=5/100) and 3'AmNic-rEPA (n=13/201) groups.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.WITHDRAWAL SYMPTOMS:\nSignificant differences were not observed in overall withdrawal severity between placebo and the high and low Ab groups (p >0.22).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.IMMUNOGENICITY AND EFFICACY BY STUDY GROUP:\nFigure 5 depicts immune response by study group from baseline to week 52. Anti-nicotine Ab GMCs increased across all active treatment groups after each vaccination, with each subsequent dose resulting in a higher Ab response than the previous dose. Schedule 2 showed a higher initial increase in Ab concentrations. The 400 μg/Schedule 2 group demonstrated the highest Ab concentrations. However, no significant differences (p >0.05) were observed in AUC, Cmax and Cavg across the treatment groups to 26 or 52 weeks likely because the study was not powered to detect such difference. An intent-to-treat analysis demonstrated that the Schedule 2, 400 μg dose group had significantly higher prolonged abstinence to 6 months as compared to placebo (17.6% vs. 6.0%; p=0.015; OR of 4.14; 95% CI, 1.32–13.02), although not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0%, p=0.054; OR=3.23; 95% CI, 0.98–10.67) or between placebo and Schedule 1 for each of the doses (p >0.84). The Schedule 2, 400 μg dose group also had the highest rates of prolonged abstinence to 12-months, significantly higher than placebo (15.7% vs. 6.0%, p=0.038; OR=3.44; 95% CI, 1.07–11.04), but not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0% for 200 (p=0.056; OR=3.21; 95% CI, 0.97–10.63) or between placebo and Schedule 1 for each dose (p >0.88).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.SAFETY:\nTable 2 lists the number of subjects experiencing local and systemic reactogenicity. Reactogenicity events were aggregated over all injections. Overall, ache and tenderness were the most commonly reported local events, with at least one report by nearly all subjects (86% to 98%) in each treatment group. Myalgia, malaise, and headache were the most commonly reported systemic events (64% to 88% of subjects). Swelling, heat, burning, erythema, and nausea were reported by about half the subjects. Fever and vomiting were less common (4% to 16%). A total of 1184 treatment-emergent adverse events (AEs), predominantly rated mild or moderate, were reported by 266 of 301 subjects; 87.1% of 3'AmNic-rEPA recipients and 91.0% of placebo recipients. On average, 3.7 and 4.3 events were observed per person in the vaccinated and placebo groups, respectively, including subjects with no events. The distribution of 161 physician-determined treatment-related AEs, according to severity and relationship to treatment, was similar for the 3'AmNic-rEPA and placebo arms. Seven 3'AmNic-rEPA recipients (3.5%) and 2 subjects in the placebo arm (2.0%) withdrew from the study due to adverse events. 18 Serious AEs were reported: 8 events in the 3'AmNic-rEPA treatment groups among 7 subjects (3.5% of the 3'AmNic-rEPA recipients) and 10 events in the placebo group among 5 subjects (5.0% of the placebo recipients). Only one of these SAEs (anaphylactic reaction in a 3'AmNic-rEPA 400 μg/Schedule 2 recipient) was considered by the Investigator to be treatment related. This subject, who had a history of urticaria to penicillin and seasonal allergies, experienced difficulty breathing, throat tightness, facial erythema and urticaria 70 minutes after the initial vaccination. The subject was treated with a single injection of subcutaneous epinephrine and diphenhydramine, which resolved the symptoms. Herpes Zoster was reported in 6 subjects; one occurring within 3–5 hours after the first vaccination which would be impossible to link to vaccination. Of the remaining cases, 4 (2%) occurred in 3'AmNic-rEPA recipients; while 1 occurred in placebo (1%). In contrast, the related herpes virus, simplex infection was reported in 4 3'AmNic-rEPA recipients (1%) and 3 placebo recipients (2%).\n\nBODY.DISCUSSION:\nResults demonstrated the proof-of-concept that smokers who achieved higher anti-nicotine Ab concentrations were more likely to quit and remain abstinent from smoking. The high Ab group demonstrated the highest abstinence rates independent of the time period of ascertainment. Similarly, in a separate study conducted by Cornuz and coworkers [13] testing a different nicotine vaccine (nicotine derivative conjugated to a virus-like particle derived from bacteriophage Qβ), post hoc analysis showed subjects stratified to the highest Ab group had a significantly higher quit rate than placebo. However, unlike the current study, which used the intent-to-treat (ITT) population to establish proof of concept, the reported finding by Cornuz et al. [13] was observed after eliminating about a third of the subjects who used nicotine replacement therapies during the course of the study or who had incomplete Ab titer values. In the present 3'AmNic study, subjects in the high Ab group had observed odds ratios of 4.4 (95% CI 1.5–12.7) and 3.9 (95% CI 1.3–11.2) for prolonged abstinence rates to 6 and 12 months versus placebo. Although no direct comparisons can be made, these odds ratios are not unlike ones observed in the meta-analyses conducted for the U.S. Clinical Practice Guideline where the reported odds-ratios ranged from 1.5 (95% CI 1.2–1.7) for nicotine gum to 3.1 (95% CI 2.5–3.8) for varenicline at 6 months post-quit [3]. If current study findings are confirmed in larger studies, imunotherapeutics are likely to emerge as an important aid to smoking cessation. No significant compensatory smoking in response to the presence of anti-nicotine antibodies, as determined by the number of cigarettes smoked per day, carbon monoxide levels or cotinine levels, was observed in this study. This result is consistent with observations from other studies [12, 13]. In the current study, subjects in the high Ab group who did not abstain smoked significantly lower number of cigarettes (median reduction of ~5 cigarettes/day) and experienced lower cotinine levels (~20%) than placebo subjects along with no differences observed between the low Ab and placebo groups. However, a small number of individual subjects (N=15/301) smoked more than 2-fold the number of cigarettes at baseline with no significant differences between the active treatment and placebo groups. A major challenge for immunotherapeutics is to stimulate high Ab levels in the vast majority of smokers trying to quit. Vaccine dose and frequency of vaccination have an impact on the Ab levels attained. The 5 injection/400 μg dose was associated with the highest Ab response, although not statistically significant, possibly due to the small sample size. Importantly, this dose and schedule demonstrated statistically significant improved 44-week CAR compared to placebo. Because the 4 injection/400 μg dose was not associated with higher abstinence rates, this result demonstrates that consideration of both dose and schedule of injection are critical. In an independent, follow-up immunogenicity study to examine if peak Ab levels could be elevated, a total of 74 subjects received 6 injections of 400 μg 3'AmNic-rEPA at week 0, 4, 8, 12, 16, and 26. More than 80% of subjects receiving the 6-dose immunization regimen exceeded a target level of Ab (25 μg/ml) by week 14. In contrast, only 50% of subjects receiving 5 injections of the 400 μg dose achieved this level by week 14 in the current study and, only 7% of subjects attained this level by the target quit date. This finding suggests that more frequent injections and a later quit date may increase treatment success. In general, 3'AmNic-rEPA was well-tolerated. The frequencies of local and systemic vaccine reactogenicity events were similar in the vaccine and placebo groups and similar to licensed adult vaccines containing Alum adjuvant [16]. The slight increase in cases of herpes zoster observed in this study may be spurious, but continued monitoring is necessary to determine if a causal relationship exists. The occurrence of a single anaphylactic reaction would suggest a need for continued monitoring and follow-up, even considering the subjects' history of prior drug allergy to penicillin.1 In summary, results from this study support the concept that high anti-nicotine Ab levels are associated with higher rates of abstinence. These findings suggest that vaccines attaining high Ab levels by the target quit date may be more effective. Other future strategies may include examining additional ways to increase Ab levels across all individuals. Nonetheless, this study demonstrates that 3'AmNic-rEPA has significant potential as a smoking cessation, and perhaps a relapse prevention aid.\n\nBODY.METHODS.STUDY POPULATION:\nSmokers were recruited via advertisement across nine geographically diverse U.S. sites. Interested subjects were screened over the telephone and more extensively screened at the first Screening Visit. Subject informed consent was obtained prior to screening. Subjects were 18 years of age or older, smoked ≥15 cigarettes/day, had exhaled CO ≥10 ppm; wanted to quit smoking, and were in good general physical and mental health. Exclusion criteria included recent use of any medications or drugs that might interfere with immune response, interact with the vaccine, and pharmacotherapies or other treatments for smoking cessation. For females, a negative urine pregnancy test at enrollment and active use of acceptable birth control or documentation of surgical sterility was required.\n\nBODY.METHODS.STUDY DESIGN:\nThis Phase 2 study was a randomized double-blind, placebo-controlled, parallel-arm trial design (see Figure 1). Four treatment groups varied the dose and/or schedule of intramuscular vaccination: 200 or 400 μg of 3'AmNic-rEPA or placebo according to Schedule 1 (weeks 0, 6, 12, and 26) or Schedule 2 (weeks 0, 4, 8, 16, and 26). Subjects (N=150) were first randomized within Schedule 1 groups in a 1:1:1 ratio (200 μg: 400 μg: placebo) and then 151 subjects randomized within Schedule 2 groups in the same ratio. The TQD was 1 week after the second injection (end of week 7 for Schedule 1 and end of week 5 for Schedule 2). If the subjects relapsed (seven consecutive days of smoking) after the quit date, a second quit date coinciding with a future clinic visit was allowed between time of relapse and week 18. Cessation counseling (based on the USDHHS Clinical Practice Guidelines [17]) for the first quit attempt involved 5 standardized face-to-face sessions (≤10 minutes) and for the second quit attempt, a face-to-face session plus 2 post-quit telephone counseling sessions. Subjects were followed for 52 weeks after randomization and the first injection on Day 0 for a total of 21 visits. During the injection day, subjects remained at the study site for 30 to 60 minutes for observation and attended a visit 24 hours after each injection to assess side effects. Otherwise, visits ranged from weekly to bi-weekly and were less frequent after later injections. Subjects who failed to quit smoking on their TQDs were encouraged to remain in the study and continue to attempt to achieve abstinence. Subjects who terminated from the study were not replaced and presumed to be smokers. Institutional Review Board approval was obtained from all institutions involved in the study. A Data and Safety Monitoring Board (DSMB) met four times during the study.\n\nBODY.METHODS.INVESTIGATIONAL PRODUCT:\nThe active investigational product was purified 3'-aminomethylnicotine conjugated to P. aeruginosa r-exoprotein A. For the 200 and 400 μg/mL dose, each single-use syringe contained 3'-aminomethylnicotine conjugated to 200 or 400 μg rEPA, respectively, adsorbed to 1.2 mg aluminum hydroxide adjuvant (Alhydrogel 85) in 1 mL phosphate buffered saline (0.15 M NaCl, 0.002 M NaPO4, pH 7.2, 0.01% polysorbate 80; PBS). For the placebo dose, PBS with 1.2 mg Alhydrogel 85 was included in a 1 mL single-use syringe.\n\nBODY.METHODS.MEASURES:\nCigarette use was recorded daily on an electronic diary for 182 days, and then weekly for the remainder of the study. Exhaled CO and urine cotinine were measured at each study visit, except for visits within 24 hours of vaccination. Questionnaires were collected via electronic diary: Fagerström Test for Nicotine Dependence [18] (administered days 0, 210, 364), Minnesota Nicotine Withdrawal Scale [MNWS, 19] (administered weekly until Month 6) and data on other tobacco usage. Sera were collected for immunogenicity measurements at 16–17 time points (schedule-dependent) from baseline to week 52. Anti-nicotine antibody concentrations were measured using ELISA (Enzyme-linked Immunosorbent Assay) [12]. Subjects recorded standard local and systemic reactogenicity events for 7 days after each injection. All reactogenicity events were followed until resolution or study completion. Treatment emergent AEs were recorded until 4 weeks after the last dose, with the exception of SAEs, which were collected through week 52. Subjects were also periodically monitored at clinic visits for vital signs, weight, hematology, chemistry and urinalysis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Intent-to-Treat (ITT) population was used for evaluation of efficacy, safety and immunogenicity. The ITT population was defined as all subjects who were randomized to treatment. The primary endpoint was continuous smoking abstinence for a total of 8 weeks measured from the beginning of week 19 to the end of week 26 (determined from subject diaries confirmed by exhaled CO ≤8 ppm). The analysis for proof-of-concept stratified the active-treatment recipients into high (top 30% AUC from weeks 0 to 26) and low (bottom 70% AUC from weeks 0 to 26) Ab responders, regardless of treatment group. An a priori decision was made to establish the antibody cutoff between 50% and 25%. Top 30% by AUC group was selected as the largest group of high antibody responders between the 25% and 50% cutoffs that demonstrated statistical significance as compared to placebo. Smoking outcomes were compared between subjects with high Ab and pooled placebo recipients using logistic regression. Secondary aims of this study were to assess a) 7-day point prevalence abstinence at various times, CARs during 52 weeks and time to sustained abstinence defined as attaining 8 weeks of continuous abstinence at anytime prior to week 46 and maintaining continuous abstinence through 52 weeks; b) impact on compensatory smoking amongst non-abstainers; c) withdrawal symptoms and d) immunogenicity, efficacy and safety of administration of either 4 or 5 of the 200 and 400 μg doses. Secondary smoking cessation analyses used logistic regression for binary outcomes and Cox proportional hazards regression models and log-rank tests for time-to-sustained abstinence analyses. Mixed-effects repeated-measures analyses of the number of cigarettes smoked, CO and cotinine adjusted for baseline were utilized in assessing compensatory smoking among non-abstainers or in assessing withdrawal symptoms. Anti-nicotine Ab responses were summarized as GMC with 95% confidence intervals. Safety was assessed throughout this study primarily using reactogenicity and adverse events (AEs). Reactogenicity data for 7 days after each injection were tabulated, and the proportions of subjects with any post-vaccination reactogenicity, aggregated over all injections, among the five treatment groups were compared using the Generalized Cochran-Mantel-Haenszel test. When a subject dropped out of the study, they were assigned presumed to be smokers. Otherwise, all missing diary data related to cigarette use were imputed utilizing the Last Observation Carried Forward principle. No imputation was carried out for CO level. The missing serology data were imputed by first defining a set of injection windows for each schedule. The missing serology was imputed by using the next available measured serology in its corresponding window; if the next value was not available the value of the nearest previous time point in that window was used. The AUC for anti-nicotine Ab was calculated based on imputed data. For Ab values one week after the target quit date, the value at week 9 was used for Schedule 1 as sera were not collected at week 8.\n\n**Question:** Compared to placebo what was the result of high Ab group on Prolonged abstinence from smoking rates to 6 months?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
201
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy of positive end-expiratory pressure titration after the alveolar recruitment manoeuvre in patients with acute respiratory distress syndrome\n\n ABSTRACT.INTRODUCTION:\nIn acute respiratory distress syndrome (ARDS), adequate positive end-expiratory pressure (PEEP) may decrease ventilator-induced lung injury by minimising overinflation and cyclic recruitment-derecruitment of the lung. We evaluated whether setting the PEEP using decremental PEEP titration after an alveolar recruitment manoeuvre (ARM) affects the clinical outcome in patients with ARDS.\n\nABSTRACT.METHODS:\nFifty-seven patients with early ARDS were randomly assigned to a group given decremental PEEP titration following ARM or a table-based PEEP (control) group. PEEP and inspired fraction of oxygen (FiO2) in the control group were set according to the table-based combinations of FiO2 and PEEP of the ARDS network, by which we aimed to achieve a PEEP level compatible with an oxygenation target. In the decremental PEEP titration group, the oxygen saturation and static compliance were monitored as the patients performed the ARM along with the extended sigh method, which is designed to gradually apply and withdraw a high distending pressure over a prolonged period, and the decremental titration of PEEP.\n\nABSTRACT.RESULTS:\nThe baseline characteristics did not differ significantly between the control and decremental PEEP titration groups. Initial oxygenation improved more in the decremental PEEP titration group than in the control group. However, dynamic compliance, tidal volume and PEEP were similar in the two groups during the first week. The duration of use of paralysing or sedative agents, mechanical ventilation, stay in the intensive care unit and mortality at 28 days did not differ significantly between the decremental PEEP titration and control groups.\n\nABSTRACT.CONCLUSIONS:\nThe daily decremental PEEP titration after ARM showed only initial oxygenation improvement compared with the table-based PEEP method. Respiratory mechanics and patient outcomes did not differ between the decremental PEEP titration and control groups.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov identifier: ISRCTN79027921.\n\nBODY.INTRODUCTION:\nTwo recent randomised controlled trials involving patients with acute lung injury (ALI) or acute respiratory distress syndrome (ARDS) demonstrated that mortality can be reduced significantly by setting a low tidal volume (VT) [1] and by setting both a low VT and adequate positive end-expiratory pressure (PEEP) levels titrated by pressure-volume curves [2,3]. However, this strategy favours further lung collapse or derecruitment, especially when used with a high inspired fraction of oxygen (FiO2) [4]. The importance of opening the lung and keeping it open seems increasingly significant in this era of lung-protective ventilatory support because the use of a small VT for this strategy may worsen progressive lung collapse. Moreover, the alveolar and systemic inflammatory responses can be attenuated by minimising overinflation and cyclic recruitment–derecruitment of the lung by reducing VT and increasing PEEP in ARDS [5]. The best method of setting optimal PEEP after recruitment to prevent recollapse is still a matter of debate [6]. In the ALVEOLI study, mortality rates and the number of ventilator-free days did not differ significantly between the lower- and higher-PEEP study groups [7]. This result may have reflected the use of the same PEEP level (combination of FiO2 and PEEP) for the heterogeneous patient group and an inappropriately high PEEP in the nonrecruiters, which may have resulted in overdistension. Gattinoni and colleagues reported that the percentage of potentially recruitable lung tissue may be different in patients with ARDS and that the use of a higher PEEP level in patients with a lower percentage of potentially recruitable lung may be harmful [8]. These studies did not evaluate completely the effect of using individualised PEEP on the survival rate of patients with ARDS. The higher PEEP levels should be adjusted according to individual lung morphology. However, the strategies for setting PEEP using a plateau pressure or recruitment manoeuvre do not decrease mortality [9,10]. We designed an individual PEEP strategy using decremental PEEP titration after an alveolar recruitment manoeuvre (ARM) for each patient with ARDS. An ARM is a way to standardise the history of lung volume [11]. The objective of this study was to evaluate whether setting the PEEP using decremental PEEP titration after ARM affects the oxygenation and outcome of patients in the early stage of ARDS compared with the table-based combinations of FiO2 and PEEP in the ARDS network [1].\n\nBODY.MATERIALS AND METHODS.STUDY POPULATION:\nFifty-seven consecutive patients (35 men and 22 women) admitted to the medical intensive care unit (MICU) of Asan Medical Center, in Seoul, Korea, who were diagnosed with ARDS of various aetiologies were enrolled in the study between July 2004 and September 2006. Patient selection for the study was based on the criteria of ARDS proposed by the American–European Consensus Conference on ARDS [12]: acute onset, presence of hypoxaemia (partial arterial pressure of oxygen (PaO2)/FiO2 (PF ratio) ≤ 200 mmHg regardless of the PEEP level), bilateral and diffuse opacities seen on frontal chest x-ray and absence of left ventricular failure with pulmonary arterial occluded pressure of 18 mmHg of less. The study protocol was approved by the institutional board of the ethics committee and written informed consent was obtained from the patients' families.\n\nBODY.MATERIALS AND METHODS.VENTILATOR PROCEDURES:\nPatients were given ventilatory support primarily in the supine position and ventilated according to the ARDS network strategy. FiO2, PEEP and respiratory rate were set to achieve an arterial oxygen saturation (SaO2) of between 88 and 92% [2]. The target VT was 6 ml/kg of predicted body weight, with allowances of up to 8 ml/kg if the SaO2 were below 88% or less than 7.2 of arterial pH by severe hypercapnoea. The patients were randomly assigned with the use of a randomisation scheme to either the decremental PEEP titration group or the control (table-based PEEP setting) group (Figure 1). Figure 1Study groups of patients. Four patients who withdrew from the study were excluded from the analysis. ARDS = acute respiratory distress syndrome; PEEP = positive end-expiratory pressure.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.TABLE-BASED PEEP SETTING (CONTROL) GROUP:\nThe FiO2-PEEP strategy has been used in previous ARDS Network studies (Figure 2). PEEP and FiO2 were set according to the table of lower PEEP/higher FiO2 combinations (the lower PEEP strategy of the ALVEOLI study), with the goal of obtaining a lower PEEP level compatible with an oxygenation target. Figure 2Study protocol. (a) Table-based positive end-expiratory pressure (PEEP) setting (control) group. (b) Decremental PEEP titration group after alveolar recruitment manoeuvre (ARM). FiO2 = inspired fracture of oxygen.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.DECREMENTAL PEEP TITRATION GROUP:\nThe ARM was performed immediately after enrollment in the study and was applied once a day usually in the morning for one week. The ventilatory circuit was not disconnected after ARM to avoid lung derecruitment. The ARM was also repeated when the ventilatory circuit was disconnected (incidentally or for bronchoscope) or if FiO2 requirement was increasing again in the patient, who showed initial improvement of oxygenation by ARM. If the weaning trial was performed within one week, the ARM was stopped earlier than the usual schedule. During the ARM, all patients were sedated and paralysed by continuous infusion of midazolam-ketamine and vecuronium bromide. No changes were made in the doses of inotropic agents or fluid infusion during the ARM. The ARM used the extended sigh method, which is designed to gradually apply and withdraw a high distending pressure over a prolonged period. It takes about 15 to 20 minutes for two cycles of ARM according to our protocol (Figure 2) [13]. We changed the ventilatory mode from pressure-controlled mode to the volume-controlled mode during ARM. The distending pressure was determined by the delivered VT, PEEP increment and the pause time (0.5 seconds). During the ARM, PEEP was added from baseline to 15, 20 and 25 cmH2O sequentially (every 30 seconds from the baseline PEEP until 25 cmH2O). The VT was decreased by 25% from the baseline VT during the incremental PEEP trial phase, and then returned to baseline levels during the decremental PEEP trial phase. Therefore, the distending pressures were changed depending on the patient's VT and lung mechanics. However, we did not allow the peak airway pressure to go above 55 cmH2O during the ARM. The decremental PEEP titration at the second cycle of ARM was performed with progressive decreases in PEEP in steps of 1 cmH2O every 30 seconds from 20 cmH2O while continuously monitoring saturation and static compliance. The decrease in PEEP was continued until a decrease of more than 2% of saturation from the previous SaO2 and drop of static compliance was identified. This PEEP level was considered the alveolar collapsing pressure and the optimal PEEP after the ARM was set 2 cmH2O above this pressure. No patients showed significant arrhythmia or gross barotraumas of any type during ARM.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.RESCUE THERAPY:\nIf the level of inspired oxygen was not decreased to 0.6 or oxygenation improvement was not achieved after PEEP readjustment in all patients, rescue therapies such as prone position or nitric oxide inhalation were performed.\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION:\nThe primary end point was improvement in oxygenation (improvement of PaO2/FiO2 (PF) ratio). The secondary end points included respiratory mechanics (PEEP and dynamic compliance), ICU stay, duration of sedatives and paralysing agents and patient outcomes (28-day mortality, 60-day mortality, duration of mechanical ventilation). Responders were defined by a 20% improvement in the PF ratio on day 1 compared with day 0 (baseline) after PEEP adjustment [14].\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION.RESPIRATORY MECHANICS:\nAirway pressure and flow were monitored continuously. VT, dynamic compliance (in ml/cmH2O), and peak airway, mean airway and minute ventilation were recorded at 30 minutes after the change of PEEP level in both groups. Because pressure control mode was the main ventilatory strategy, we monitored and compared the dynamic compliance and peak airway pressure in both group.\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION.HAEMODYNAMICS AND GAS EXCHANGE:\nWe collected arterial blood samples to measure partial pressure of oxygen (PO2), partial pressure of carbon dioxide (PCO2), pH, and SaO2 30 minutes after reapplication of PEEP. Haemodynamic variables monitored included heart rate and systolic, diastolic and mean systemic arterial pressure.\n\nBODY.MATERIALS AND METHODS.DATA ANALYSIS:\nSample size calculation showed that 36 patients per group would provide 80% power at a two-sided α level of 0.05 to detect a 20% difference in the improvement of oxygenation (improvement of PF ratio). All data were analysed using SPSS for Windows (version 11.0; SPSS Inc., Chicago, IL, USA). Statistical analyses were based on the intention-to-treat principle and involved all patients who had undergone randomisation. All values are expressed as the mean ± standard error of the mean or as the number and percentage of patients. Probability of mortality and differences between the groups were compared using a log-rank test. The chi-squared test or Fisher's exact test was used to compare categorical data, and Student's t test or the Mann-Whitney U test was used to compare continuous data. Significance was defined as p < 0.05.\n\nBODY.RESULTS.CHARACTERISTICS OF THE PATIENTS:\nWe enrolled 61 patients in the study, 30 of whom were randomly assigned to the control (table-based PEEP setting) group and 31 to the decremental PEEP titration group. Fifty-seven patients completed the study (27 in the control group and 30 in the decremental PEEP titration group) and contributed data for the analyses. Most baseline characteristics were similar in the two study groups (Table 1). The most common cause of ARDS was pneumonia. The initial ventilatory setting and severity index did not differ between the control and decremental PEEP titration groups. Table 1 Baseline characteristics of the patients at enrollment Control group (n = 27) Decremental PEEP titration group (n = 30) Age (years) 62.0 ± 2.2 55.0 ± 3.7 Percentage of women 37 40 APACHE II score 20.0 ± 1.4 22.0 ± 1.1 Lung injury score 2.5 ± 0.1 2.8 ± 0.2 Tidal volume (ml/kg of predicted body weight) 8.0 ± 1.4 7.9 ± 1.9 Respiratory rate (breaths/minute) 22.0 ± 3.0 22.2 ± 3.2 Peak airway pressure (cmH 2 O) 25.9 ± 5.9 27.8 ± 5.5 Positive end-expiratory pressure (cmH 2 O) 7.0 ± 3.7 8.4 ± 3.1 Dynamic compliance (Cdyn, ml/cmH 2 O) 25.7 ± 8.1 24.3 ± 7.6 PF ratio (PaO 2 :FiO 2 ) 110.8 ± 6.3 115.0 ± 8.5 Co-morbidities, n Haematological malignancy 3 7 Solid organ malignancy 6 4 Chronic liver disease 5 3 Connective tissue disease 2 1 Others a 3 3 Cause of lung injury (ARDSp:ARDSexp) 18:9 20:10 Pneumonia 15 17 Sepsis 7 7 Massive transfusion 2 1 Pulmonary alveolar haemorrhage 1 1 Others b 2 4 Data was presented as mean ± standard error of the mean. a including complicated diabetes mellitus (n = 4), Crohn's disease (n = 1) and AIDS (n = 1). b including leptospirosis (n = 3), near-drowning (n = 1), contusion (n = 1) and scrub typhus (n = 1). APACHE = acute physiology and chronic health evaluation; ARDSp = pulmonary ARDS; ARDSexp = extrapulmonary ARDS; FiO 2 = inspired fracture of oxygen; PaO 2 = partial arterial pressure of oxygen; PEEP = positive end-expiratory pressure. \n\nBODY.RESULTS.RESPIRATORY MECHANICS AND OXYGENATION:\nFigure 3 shows the ventilatory setting and respiratory variables at baseline and follow-up during the first week of treatment. The peak pressure was significantly higher on days 3 and 5 in the decremental PEEP titration group than in the control group, and the mean pressure was significantly higher in the decremental PEEP titration group because of the higher PEEP during the first week. Dynamic compliance and VT during the first week were similar in the two groups. Oxygenation improved compared with the baseline PF ratio in both groups (Figure 4). Initial oxygenation improved more in the decremental PEEP titration group than in the control group. The partial arterial pressure of oxygen (PaCO2) level was significantly higher in the decremental PEEP titration group than in the control group on day 1, suggesting increased dead space ventilation. However, the improvement of oxygenation and PaCO2 level were not different between the two groups during follow-up. Figure 3Respiratory values during the first week of treatment. The closed circles indicate the control group and the open circles denote the decremental positive end-expiratory pressure (PEEP) titration group. Values are expressed as the mean ± standard error of the mean (bars). *p < 0.05 between the control and decremental PEEP titration groups; †p < 0.05 compared with day 0 in the control group; ‡p < 0.05 compared with day 0 in the decremental PEEP titration group. Figure 4Oxygenation changes and PaCO2 levels during the first week of treatment. All patients showed improved oxygenation during treatment. The level of partial arterial pressure of carbon dioxide (PaCO2) at day 1 was increased significantly in the decremental positive end-expiratory pressure (PEEP) titration group than the control group. The black bars indicate the control group and gray bars denote the decremental PEEP titration group. Values are expressed as the mean ± standard error of the mean (bars). *p < 0.05 between the control and decremental PEEP titration groups, †p < 0.05 compared with day 0 in the control group, ‡p < 0.05 compared with day 0 in the decremental PEEP titration group.\n\nBODY.RESULTS.CLINICAL OUTCOMES:\nThe overall mortality at 28 days was 37%. Mortality at 28 days was 33% in the control group and 40% in the decremental PEEP titration group (Table 2). Using Cox regression for 28-day mortality, the survival rate in the decremental PEEP titration group was not different (p = 0.725; hazard ratio = 1.168; 95% confidence interval = 0.493 to 2.768). However, 60-day mortality was significantly increased to 55.6% (p = 0.031) compared with 28-day mortality (33.3%) in the control group only. Table 2 Clinical outcomes according to treatment group Control group (n = 27) Decremental PEEP titration group (n = 30) p value Responder (%) 44.4 70 0.046 Clinical outcomes Duration of mechanical ventilation, days 15.2 ± 3.2 19.8 ± 0.5 0.380 Intensive care unit stay, days 21.4 ± 5.3 25.1 ± 5.6 0.643 Duration of paralysing agent, days 9.0 ± 2.3 11.8 ± 2.0 0.358 Duration of sedative agents, days 14.2 ± 2.4 18.7 ± 3.4 0.303 Weaning trial within seven days 8 6 Tracheostomy 5 8 Reintubation 5 2 Barotrauma 3 3 Ventilator-associated pneumonia 5 5 Mortality, number (%) Mortality at 28 days 9 (33.3) 12 (40) 0.784 Death in the intensive care unit 13 (48.1) 14 (46.7) 1.000 Mortality at 60 days 15 (55.6) 14 (46.7) 0.599 Cause of in-hospital death, number (%) Progressive respiratory failure 8 (53.3) 8 (57.1) Refractory septic shock 4 (26.7) 2 (14.3) Hepatic failure 3 (20) 2 (14.3) Myocardial infarction 2 (14.3) Rescue therapy (%) Prone position 44.4 50.0 0.792 Nitric oxide inhalation 48.1 53.3 0.793 Data was presented as mean ± standard error of the mean. PEEP = positive end-expiratory pressure. Eight patients (30%) in the control group and six patients (20%) in the decremental PEEP titration group had performed the weaning trial within a week of enrollment. The incidence of barotrauma was similar in both groups. The durations of mechanical ventilation, ICU stay and use of paralysing or sedative agents did not differ between the groups (Table 2).\n\nBODY.DISCUSSION:\nAs suggested by Lachmann more than 10 years ago [15], \"open up the lung and keep the lung open\" appears advantageous to recruit the lungs of patients with ARDS and to prevent subsequent lung derecruitment [12]. Clinical outcomes were similar regardless of whether lower or higher PEEP levels were used in the ALVEOLI trial [7]. The problem of the ALVEOLI trial was the higher PEEP strategy, which was table-based like the one on the current study, matched on the oxygenation target regardless of any patient-related variable. A reasonable approach to determining the appropriate level of PEEP requires maintaining PEEP-induced reopening of atelectatic areas and avoiding PEEP-induced lung overinflation. Higher than traditional PEEP levels together with lung-recruiting maneuvers seems to be a way to find an appropriate PEEP level [16]. Experimental data suggest that the effects of ARM on alveolar recruitment are transient if the preceding PEEP levels are maintained after the manoeuvre [14]. Once the alveoli have been recruited, higher PEEP levels are required to keep them aerated [17]. The right level of PEEP as an anti-derecruiting force is important in preserving the effect of the ARM. We previously reported that a sufficient level of PEEP after ARM is important as an anti-decruitment strategy [18]. We hypothesised that the decremental PEEP trial would be an appropriate method to establish the PEEP level after ARM at bedside. Because higher PEEP and the ARM performed in patients with mild lung injury may have fewer benefits and more adverse effects, we only focused on ARDS patients to address our assumption. We found that daily decremental PEEP titration after ARM showed only initial oxygenation improvement compared with the table-based PEEP method and did not improve the respiratory mechanics within a week. We performed the ARM and PEEP titration daily during the first week in the decremental PEEP titration group. However, no significant differences were observed in the 28-day mortality, ICU stay and 60-day mortality. Although the responder rate was higher in the decremental PEEP titration group than in the control group, the earlier improvement in oxygenation was not associated with increased survival rate. Our finding showed the 60-day mortality in the control group was significantly increased compared with the 28-day mortality. We could not explain whether this finding was associated with the protective effect of ARM to the ventilator-induced lung injury. To add any relevant information, further study will be needed for the biomarkers such as proinflammatory cytokines. The lower dynamic compliance in the decremental PEEP titration group was an unexpected result, although there was no significant difference between the two groups. We speculated that a higher peak airway pressure might affect the lower dynamic compliance in the decremental PEEP titration group than the control. A reason for this result might be related to the subjects' characteristics. Most of the patients with ARDS had pneumonia, which did not respond well to the applied PEEP [19]. We included mostly pulmonary ARDS with severe underlying diseases, which would be a common phenomenon in a university hospital MICU. That may be the reason why mortality related to progressive respiratory failure was higher in our study group. The mortality of patients with pneumonia was 43.3% and the mortality of patients without pneumonia was 29.6%. The baseline lung conditions of these patients was a higher proportion of refractory consolidation to the distending pressure which may also have influenced the PF ratio of less than 250 and PEEP levels less than 15 cmH2O after ARM. Talmor and colleagues reported that a low lung distending pressure was applied in the patients with a stiff chest wall [20]. We did not measure the chest-wall mechanics or the recruitable lung, so we could not address this possibility as a cause of low PF ratio. One limitation of our study is that we could not evaluate whether recruitment manoeuvre maximised the alveolar collapse. If the recruitment effect of our ARM was not sufficient, the effect of a decremental PEEP trial might be insufficient. Borges and colleagues reported that a peak airway pressure of more than 60 cmH2O could recruit the collapsed lung [21]. Another limitation is that our indicators of oxygen saturation and static compliance to find an appropriate PEEP level might be insensitive to detect the collapsing pressure of the lung. Finally, small sample size in a single centre limits the power of the study outcomes.\n\nBODY.CONCLUSION:\nThe daily decremental PEEP titration after ARM did not show the persistent improvement of oxygenation, the respiratory mechanics and the mortality rate of patients with ARDS compared with the table-based PEEP setting. Further investigations are needed to find the correct level of PEEP in ARDS with reference to chest wall compliance and alveoli mechanics.\n\nBODY.KEY MESSAGES:\n• The daily decremental PEEP titration after ARM method did not show a persistent improvement of oxygenation. • Respiratory mechanics such as dynamic compliance, VT and PEEP were not significantly different between the daily decremental PEEP titration after ARM group and the table-based PEEP setting group. • The daily decremental PEEP titration after ARM without the reference of lung mechanics did not reduce the dependence of ventilator or mortality rate of patients with ARDS compared with the table-based PEEP setting.\n\nBODY.ABBREVIATIONS:\nALI: acute lung injury; ARDS: acute respiratory distress syndrome; ARM: alveolar recruitment manoeuvre; FiO2: inspired fracture of oxygen; MICU: medical intensive care unit; PEEP: positive end-expiratory pressure; PaCO2: partial arterial pressure of carbon dioxide; PaO2: partial arterial pressure of oxygen; PCO2: partial pressure of carbon dioxide; PO2: partial pressure of oxygen; SaO2: arterial oxygen saturation; VT: tidal volume.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJWH recruited patients, analysed the data and wrote the manuscript. HJ and HSC helped to recruit patients and analysed the data. SBH and CML recruited patients and interpreted the data. YK designed the study, interpreted the data and wrote the paper. All authors read and approved the final manuscript.\n\n**Question:** Compared to table-based PEEP (control) group what was the result of Decremental PEEP titration group on The durations of mechanical ventilation, ICU stay and use of paralysing or sedative agents of patients with ARDS?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
141
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Reductions in systolic blood pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
181
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Severity of pain?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
151
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Incidence of minor hypoglycaemia?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
112
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Patients reaching HbA1c goals less than 7.0% and equal or less than 6.5%?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
153
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on Changes in calcitonin at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
102
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Fasting plasma glucose at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
129
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on ADA postprandial plasma glucose goals less than 10.0 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
195
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Midwife-led unit on Oxytocin infusion for augmentation of labour?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
104
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Postprandial plasma glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
206
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Immunogenicity and Smoking Cessation Outcomes for a Novel Nicotine Immunotherapeutic\n\n ABSTRACT:\nNicVAX®, a nicotine vaccine (3'AmNic-rEPA), has been clinically evaluated to determine if higher antibody concentrations are associated with higher smoking abstinence rates and if doses and frequency of administration are associated with increased antibody response. This randomized, double-blinded, placebo-controlled multicenter clinical trial (N=301 smokers) tested 200 and 400 μg doses administered 4 or 5 times over 6 months compared to placebo. 3'AmNic-rEPA recipients with the highest serum anti-nicotine antibody response (top 30% by AUC) were significantly more likely to attain 8 weeks continuous abstinence from weeks 19 through 26 than the placebo recipients (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). The 5 injection 400 μg dose regimen had the greatest antibody response and had significantly higher abstinence rates than placebo. This study demonstrates proof-of-concept that 3'AmNic-rEPA elicits antibodies to nicotine and is associated with higher continuous abstinence rates, justifying its further development as a treatment for nicotine dependence.\n\nBODY.INTRODUCTION:\nWorldwide, smoking prevalence is 1.2 billion and approximately 5 million people die each year of smoking caused illnesses [1]. The global rate of smoking and smoking related deaths is anticipated to increase over the next 20 years unless significant public health measures are instituted. These include effective cessation interventions such as pharmacological treatments, which improve cessation rates by 1.5 to 3 fold over placebo intervention [2, 3]. Approved pharmacotherapies (e.g., nicotine replacements, bupropion SR, varenicline) for smoking cessation act on the central nervous system, each with a different mechanism of action. Other novel medications are being developed including immunotherapeutics targeting nicotine. Nicotine conjugate vaccines stimulate the immune system to develop nicotine specific antibodies (Abs) using an immunogen comprised of nicotine covalently linked to a larger carrier protein. Conceptually, the mechanism of action is that anti-nicotine antibodies bind nicotine molecules and the resulting complex is too large to cross the blood-brain barrier. With increasing Ab levels more nicotine is captured and sequestered in the blood and prevented from entering the brain, leading to less reinforcing effects from nicotine. Animal studies have demonstrated that passive or active immunization results in approximately 30% to 90% less nicotine entering the brain compared to control rats [4–7] and attenuated locomotor [4, 5] and behavioral [8, 9] responses to nicotine. Furthermore, vaccination reduced nicotine elimination from the body in a study with rats [10, 11], which may also contribute to reduced smoking. Although human studies are limited, published data evaluating different nicotine vaccines support the general concept that nicotine vaccines can be effective for smoking cessation in some smokers [12, 13]. Unfortunately, these studies either had small sample sizes [12], did not use an intent-to-treat population of smokers [13] or did not perform statistical analysis of the data [14]. The primary aim of the present study was to establish the proof-of-concept that (i) anti-nicotine antibodies are useful as an aid to smoking cessation and (ii) higher serum anti-nicotine antibody concentrations are associated with higher abstinence rates in an intent-to-treat population of smokers. One of the challenges with immunotherapeutics, such as vaccines, is attainment of therapeutic levels of antibody in most people. Therefore, this study tested two different doses of 3'-aminomethylnicotine P. aeruginosa r-exoprotein A - NicVAX (3'AmNic-rEPA) to identify a dose and schedule for further development: 200 and 400 μg across two different schedules (4 or 5 injections) compared to placebo for immunogenicity, efficacy and safety.\n\nBODY.RESULTS:\nA total of 301 subjects were randomized. Figure 2 shows the disposition and number of subjects within each treatment group. No significant group differences were observed in the demographic or smoking history by treatment or antibody levels (see Table 1).\n\nBODY.RESULTS.COMPLIANCE:\nAll 301 subjects received injection 1, 96.7%, 84.1%, 72.4% and 61.2% received injections 2, 3, 4 and 5 (Schedule 2 subjects only), respectively. No significant differences were observed across treatment groups for subjects receiving injections 2 through 4 for Schedules 1 and 2. Mean in-study duration was 286 ± 121 days.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON ABSTINENCE:\nHigh Ab responders to 3'AmNic-rEPA were defined as the top 30% of responders by AUC (0 to 26 weeks) and the low Ab group as the remaining bottom 70% of responders. 3'AmNic-rEPA recipients in the high Ab group were significantly more likely to attain 8 weeks of continuous abstinence from weeks 19 through 26 than placebo (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). No significant differences were observed between the 3'AmNic-rEPA low Ab group vs. placebo (9.3% vs. 12.0%., p=0.46). As a secondary outcome, continuous abstinence rate (CAR) to 52 weeks were evaluated from weeks 19 to 52 and were significantly higher for the high Ab group vs. placebo (19.7% vs. 10.0%, p=0.044, OR=2.64, 95% CI, 1.03–6.79) with no significant difference between the low Ab group and placebo (7.1% vs. 10.0%, p=0.43). 7-day point prevalence abstinence results show that subjects with high Ab levels were significantly more likely to abstain compared to placebo at 26 weeks (36.1% vs. 16.0%, p=0.0024, OR=3.30, 95% CI, 1.53–7.13) and 52 weeks (31.1% vs. 12.0%, p=0.0021, OR=3.69, 95% CI, 0.42–2.14). No significant differences were observed in the point prevalence abstinence rates between the low Ab group and placebo at 26 and 52 weeks (12.9% vs. 16.0%, p=0.51 and 11.4% vs. 12.0%, p=0.89, respectively). As shown in Figure 3A, abstinence rates remained essentially the same following the target quit date (TQD) for the duration of the study. To further validate the proof-of-concept, the relationship between abstinence during the final eight weeks of the study and anti-nicotine Ab concentrations (AUC) is shown in Figure 3B for all subjects receiving the vaccine. Continuous abstinence rates from week 45–52 are displayed for each 10th percentile increase in AUC. The proportion of abstinent subjects increased with increasing AUC percentile, and the ordered ranking maintained.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON TIME TO CONTINUOUS ABSTINENCE:\nAn exploratory analysis examined the rate and time to continuous abstinence through study end (Figure 3C). Most smokers quit soon after the TQD, with a clear divergence of the high Ab group from the placebo and low Ab group. Among the 18 high Ab continuous abstainers, 12 initiated abstinence prior to the primary endpoint while 6 initiated their abstinence after the start of the primary endpoint. Furthermore, 3 of the 15 subjects who abstained during the primary endpoint relapsed by the end of the study. Cox proportional hazards analysis demonstrated superiority of the high Ab group compared to placebo (p=0.0069, hazard ratio of 2.76).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EVALUATION OF LONG-TERM ABSTINENCE:\nAs most subjects achieved abstinence shortly after their TQD, additional analyses were undertaken to evaluate prolonged abstinence to 6 and 12 months allowing for a 2 week grace period after the TQD [15]. (Prolonged abstinence is defined as not a single puff during the period from 2 weeks after the TQD for 20 weeks and 44 weeks, respectively). Prolonged abstinence rates to 6 months were significantly higher in the high Ab group vs. placebo (19.7% vs. 6.0%, p=0.0060, OR=4.41, 95% CI, 1.53–12.71) with no significant differences between the placebo and low Ab groups (7.9% vs. 6.0%, p=0.60). Subjects with high Ab were also significantly more likely to be abstinent for 12 months compared to placebo (18.0% vs. 6.0%, p=0.014; OR of 3.84; 95% CI, 1.32–11.20). The low Ab group did not differ significantly from placebo (7.1% vs. 6.0%, p=0.67).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.CIGARETTE SMOKING IN NON-QUITTERS:\nStatistically significant differences were observed in reduction of daily cigarette consumption and cotinine between non-abstainers (weeks 19–52) with high Ab levels and non-abstainers in the placebo group (p=0.0015 and 0.019, respectively; see Figures 4A and 4C. The difference in the median reduction in cigarette consumption, following the TQD, between the high Ab non-abstainers and placebo non-abstainers was on average 4.6 cigarettes per day. Similarly, cotinine geometric mean concentrations (GMCs) were 19.0% lower on average following the target quit date in the high Ab non-abstainers as compared to placebo non-abstainers. Median cigarettes per day and cotinine GMC for placebo and low Ab group are nearly identical over the study period. Differences in mean CO were not observed across all three groups (see Figure 4B). 15 out of the 301 subjects smoked more than a 2-fold higher number of cigarettes following the TQD as compared to baseline with no significant difference between the placebo (n=4/100) and 3'AmNic-rEPA (n=11/201) groups. The highest smoking levels observed post-TQD were 5-fold baseline in the placebo and 4-fold baseline in the 3'AmNic-rEPA groups. Elevated smoking levels for 11 of these 15 subjects returned to below 2-fold baseline by study end. Subjects with remaining elevated levels were similar between the 3'AmNic-rEPA group (n=3/201) and placebo (n=1/100). Individual subjects with CO levels elevated by 2-fold or higher than baseline were also assessed and results were similar with no significant difference between the placebo (n=5/100) and 3'AmNic-rEPA (n=13/201) groups.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.WITHDRAWAL SYMPTOMS:\nSignificant differences were not observed in overall withdrawal severity between placebo and the high and low Ab groups (p >0.22).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.IMMUNOGENICITY AND EFFICACY BY STUDY GROUP:\nFigure 5 depicts immune response by study group from baseline to week 52. Anti-nicotine Ab GMCs increased across all active treatment groups after each vaccination, with each subsequent dose resulting in a higher Ab response than the previous dose. Schedule 2 showed a higher initial increase in Ab concentrations. The 400 μg/Schedule 2 group demonstrated the highest Ab concentrations. However, no significant differences (p >0.05) were observed in AUC, Cmax and Cavg across the treatment groups to 26 or 52 weeks likely because the study was not powered to detect such difference. An intent-to-treat analysis demonstrated that the Schedule 2, 400 μg dose group had significantly higher prolonged abstinence to 6 months as compared to placebo (17.6% vs. 6.0%; p=0.015; OR of 4.14; 95% CI, 1.32–13.02), although not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0%, p=0.054; OR=3.23; 95% CI, 0.98–10.67) or between placebo and Schedule 1 for each of the doses (p >0.84). The Schedule 2, 400 μg dose group also had the highest rates of prolonged abstinence to 12-months, significantly higher than placebo (15.7% vs. 6.0%, p=0.038; OR=3.44; 95% CI, 1.07–11.04), but not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0% for 200 (p=0.056; OR=3.21; 95% CI, 0.97–10.63) or between placebo and Schedule 1 for each dose (p >0.88).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.SAFETY:\nTable 2 lists the number of subjects experiencing local and systemic reactogenicity. Reactogenicity events were aggregated over all injections. Overall, ache and tenderness were the most commonly reported local events, with at least one report by nearly all subjects (86% to 98%) in each treatment group. Myalgia, malaise, and headache were the most commonly reported systemic events (64% to 88% of subjects). Swelling, heat, burning, erythema, and nausea were reported by about half the subjects. Fever and vomiting were less common (4% to 16%). A total of 1184 treatment-emergent adverse events (AEs), predominantly rated mild or moderate, were reported by 266 of 301 subjects; 87.1% of 3'AmNic-rEPA recipients and 91.0% of placebo recipients. On average, 3.7 and 4.3 events were observed per person in the vaccinated and placebo groups, respectively, including subjects with no events. The distribution of 161 physician-determined treatment-related AEs, according to severity and relationship to treatment, was similar for the 3'AmNic-rEPA and placebo arms. Seven 3'AmNic-rEPA recipients (3.5%) and 2 subjects in the placebo arm (2.0%) withdrew from the study due to adverse events. 18 Serious AEs were reported: 8 events in the 3'AmNic-rEPA treatment groups among 7 subjects (3.5% of the 3'AmNic-rEPA recipients) and 10 events in the placebo group among 5 subjects (5.0% of the placebo recipients). Only one of these SAEs (anaphylactic reaction in a 3'AmNic-rEPA 400 μg/Schedule 2 recipient) was considered by the Investigator to be treatment related. This subject, who had a history of urticaria to penicillin and seasonal allergies, experienced difficulty breathing, throat tightness, facial erythema and urticaria 70 minutes after the initial vaccination. The subject was treated with a single injection of subcutaneous epinephrine and diphenhydramine, which resolved the symptoms. Herpes Zoster was reported in 6 subjects; one occurring within 3–5 hours after the first vaccination which would be impossible to link to vaccination. Of the remaining cases, 4 (2%) occurred in 3'AmNic-rEPA recipients; while 1 occurred in placebo (1%). In contrast, the related herpes virus, simplex infection was reported in 4 3'AmNic-rEPA recipients (1%) and 3 placebo recipients (2%).\n\nBODY.DISCUSSION:\nResults demonstrated the proof-of-concept that smokers who achieved higher anti-nicotine Ab concentrations were more likely to quit and remain abstinent from smoking. The high Ab group demonstrated the highest abstinence rates independent of the time period of ascertainment. Similarly, in a separate study conducted by Cornuz and coworkers [13] testing a different nicotine vaccine (nicotine derivative conjugated to a virus-like particle derived from bacteriophage Qβ), post hoc analysis showed subjects stratified to the highest Ab group had a significantly higher quit rate than placebo. However, unlike the current study, which used the intent-to-treat (ITT) population to establish proof of concept, the reported finding by Cornuz et al. [13] was observed after eliminating about a third of the subjects who used nicotine replacement therapies during the course of the study or who had incomplete Ab titer values. In the present 3'AmNic study, subjects in the high Ab group had observed odds ratios of 4.4 (95% CI 1.5–12.7) and 3.9 (95% CI 1.3–11.2) for prolonged abstinence rates to 6 and 12 months versus placebo. Although no direct comparisons can be made, these odds ratios are not unlike ones observed in the meta-analyses conducted for the U.S. Clinical Practice Guideline where the reported odds-ratios ranged from 1.5 (95% CI 1.2–1.7) for nicotine gum to 3.1 (95% CI 2.5–3.8) for varenicline at 6 months post-quit [3]. If current study findings are confirmed in larger studies, imunotherapeutics are likely to emerge as an important aid to smoking cessation. No significant compensatory smoking in response to the presence of anti-nicotine antibodies, as determined by the number of cigarettes smoked per day, carbon monoxide levels or cotinine levels, was observed in this study. This result is consistent with observations from other studies [12, 13]. In the current study, subjects in the high Ab group who did not abstain smoked significantly lower number of cigarettes (median reduction of ~5 cigarettes/day) and experienced lower cotinine levels (~20%) than placebo subjects along with no differences observed between the low Ab and placebo groups. However, a small number of individual subjects (N=15/301) smoked more than 2-fold the number of cigarettes at baseline with no significant differences between the active treatment and placebo groups. A major challenge for immunotherapeutics is to stimulate high Ab levels in the vast majority of smokers trying to quit. Vaccine dose and frequency of vaccination have an impact on the Ab levels attained. The 5 injection/400 μg dose was associated with the highest Ab response, although not statistically significant, possibly due to the small sample size. Importantly, this dose and schedule demonstrated statistically significant improved 44-week CAR compared to placebo. Because the 4 injection/400 μg dose was not associated with higher abstinence rates, this result demonstrates that consideration of both dose and schedule of injection are critical. In an independent, follow-up immunogenicity study to examine if peak Ab levels could be elevated, a total of 74 subjects received 6 injections of 400 μg 3'AmNic-rEPA at week 0, 4, 8, 12, 16, and 26. More than 80% of subjects receiving the 6-dose immunization regimen exceeded a target level of Ab (25 μg/ml) by week 14. In contrast, only 50% of subjects receiving 5 injections of the 400 μg dose achieved this level by week 14 in the current study and, only 7% of subjects attained this level by the target quit date. This finding suggests that more frequent injections and a later quit date may increase treatment success. In general, 3'AmNic-rEPA was well-tolerated. The frequencies of local and systemic vaccine reactogenicity events were similar in the vaccine and placebo groups and similar to licensed adult vaccines containing Alum adjuvant [16]. The slight increase in cases of herpes zoster observed in this study may be spurious, but continued monitoring is necessary to determine if a causal relationship exists. The occurrence of a single anaphylactic reaction would suggest a need for continued monitoring and follow-up, even considering the subjects' history of prior drug allergy to penicillin.1 In summary, results from this study support the concept that high anti-nicotine Ab levels are associated with higher rates of abstinence. These findings suggest that vaccines attaining high Ab levels by the target quit date may be more effective. Other future strategies may include examining additional ways to increase Ab levels across all individuals. Nonetheless, this study demonstrates that 3'AmNic-rEPA has significant potential as a smoking cessation, and perhaps a relapse prevention aid.\n\nBODY.METHODS.STUDY POPULATION:\nSmokers were recruited via advertisement across nine geographically diverse U.S. sites. Interested subjects were screened over the telephone and more extensively screened at the first Screening Visit. Subject informed consent was obtained prior to screening. Subjects were 18 years of age or older, smoked ≥15 cigarettes/day, had exhaled CO ≥10 ppm; wanted to quit smoking, and were in good general physical and mental health. Exclusion criteria included recent use of any medications or drugs that might interfere with immune response, interact with the vaccine, and pharmacotherapies or other treatments for smoking cessation. For females, a negative urine pregnancy test at enrollment and active use of acceptable birth control or documentation of surgical sterility was required.\n\nBODY.METHODS.STUDY DESIGN:\nThis Phase 2 study was a randomized double-blind, placebo-controlled, parallel-arm trial design (see Figure 1). Four treatment groups varied the dose and/or schedule of intramuscular vaccination: 200 or 400 μg of 3'AmNic-rEPA or placebo according to Schedule 1 (weeks 0, 6, 12, and 26) or Schedule 2 (weeks 0, 4, 8, 16, and 26). Subjects (N=150) were first randomized within Schedule 1 groups in a 1:1:1 ratio (200 μg: 400 μg: placebo) and then 151 subjects randomized within Schedule 2 groups in the same ratio. The TQD was 1 week after the second injection (end of week 7 for Schedule 1 and end of week 5 for Schedule 2). If the subjects relapsed (seven consecutive days of smoking) after the quit date, a second quit date coinciding with a future clinic visit was allowed between time of relapse and week 18. Cessation counseling (based on the USDHHS Clinical Practice Guidelines [17]) for the first quit attempt involved 5 standardized face-to-face sessions (≤10 minutes) and for the second quit attempt, a face-to-face session plus 2 post-quit telephone counseling sessions. Subjects were followed for 52 weeks after randomization and the first injection on Day 0 for a total of 21 visits. During the injection day, subjects remained at the study site for 30 to 60 minutes for observation and attended a visit 24 hours after each injection to assess side effects. Otherwise, visits ranged from weekly to bi-weekly and were less frequent after later injections. Subjects who failed to quit smoking on their TQDs were encouraged to remain in the study and continue to attempt to achieve abstinence. Subjects who terminated from the study were not replaced and presumed to be smokers. Institutional Review Board approval was obtained from all institutions involved in the study. A Data and Safety Monitoring Board (DSMB) met four times during the study.\n\nBODY.METHODS.INVESTIGATIONAL PRODUCT:\nThe active investigational product was purified 3'-aminomethylnicotine conjugated to P. aeruginosa r-exoprotein A. For the 200 and 400 μg/mL dose, each single-use syringe contained 3'-aminomethylnicotine conjugated to 200 or 400 μg rEPA, respectively, adsorbed to 1.2 mg aluminum hydroxide adjuvant (Alhydrogel 85) in 1 mL phosphate buffered saline (0.15 M NaCl, 0.002 M NaPO4, pH 7.2, 0.01% polysorbate 80; PBS). For the placebo dose, PBS with 1.2 mg Alhydrogel 85 was included in a 1 mL single-use syringe.\n\nBODY.METHODS.MEASURES:\nCigarette use was recorded daily on an electronic diary for 182 days, and then weekly for the remainder of the study. Exhaled CO and urine cotinine were measured at each study visit, except for visits within 24 hours of vaccination. Questionnaires were collected via electronic diary: Fagerström Test for Nicotine Dependence [18] (administered days 0, 210, 364), Minnesota Nicotine Withdrawal Scale [MNWS, 19] (administered weekly until Month 6) and data on other tobacco usage. Sera were collected for immunogenicity measurements at 16–17 time points (schedule-dependent) from baseline to week 52. Anti-nicotine antibody concentrations were measured using ELISA (Enzyme-linked Immunosorbent Assay) [12]. Subjects recorded standard local and systemic reactogenicity events for 7 days after each injection. All reactogenicity events were followed until resolution or study completion. Treatment emergent AEs were recorded until 4 weeks after the last dose, with the exception of SAEs, which were collected through week 52. Subjects were also periodically monitored at clinic visits for vital signs, weight, hematology, chemistry and urinalysis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Intent-to-Treat (ITT) population was used for evaluation of efficacy, safety and immunogenicity. The ITT population was defined as all subjects who were randomized to treatment. The primary endpoint was continuous smoking abstinence for a total of 8 weeks measured from the beginning of week 19 to the end of week 26 (determined from subject diaries confirmed by exhaled CO ≤8 ppm). The analysis for proof-of-concept stratified the active-treatment recipients into high (top 30% AUC from weeks 0 to 26) and low (bottom 70% AUC from weeks 0 to 26) Ab responders, regardless of treatment group. An a priori decision was made to establish the antibody cutoff between 50% and 25%. Top 30% by AUC group was selected as the largest group of high antibody responders between the 25% and 50% cutoffs that demonstrated statistical significance as compared to placebo. Smoking outcomes were compared between subjects with high Ab and pooled placebo recipients using logistic regression. Secondary aims of this study were to assess a) 7-day point prevalence abstinence at various times, CARs during 52 weeks and time to sustained abstinence defined as attaining 8 weeks of continuous abstinence at anytime prior to week 46 and maintaining continuous abstinence through 52 weeks; b) impact on compensatory smoking amongst non-abstainers; c) withdrawal symptoms and d) immunogenicity, efficacy and safety of administration of either 4 or 5 of the 200 and 400 μg doses. Secondary smoking cessation analyses used logistic regression for binary outcomes and Cox proportional hazards regression models and log-rank tests for time-to-sustained abstinence analyses. Mixed-effects repeated-measures analyses of the number of cigarettes smoked, CO and cotinine adjusted for baseline were utilized in assessing compensatory smoking among non-abstainers or in assessing withdrawal symptoms. Anti-nicotine Ab responses were summarized as GMC with 95% confidence intervals. Safety was assessed throughout this study primarily using reactogenicity and adverse events (AEs). Reactogenicity data for 7 days after each injection were tabulated, and the proportions of subjects with any post-vaccination reactogenicity, aggregated over all injections, among the five treatment groups were compared using the Generalized Cochran-Mantel-Haenszel test. When a subject dropped out of the study, they were assigned presumed to be smokers. Otherwise, all missing diary data related to cigarette use were imputed utilizing the Last Observation Carried Forward principle. No imputation was carried out for CO level. The missing serology data were imputed by first defining a set of injection windows for each schedule. The missing serology was imputed by using the next available measured serology in its corresponding window; if the next value was not available the value of the nearest previous time point in that window was used. The AUC for anti-nicotine Ab was calculated based on imputed data. For Ab values one week after the target quit date, the value at week 9 was used for Schedule 1 as sera were not collected at week 8.\n\n**Question:** Compared to non-abstainers in the placebo group what was the result of non-abstainers (weeks 19–52) with high Ab levels on Reduction of daily cigarette consumption and cotinine?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
116
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on Fasting plasma glucose at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
168
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Parasite clearance at day 1?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
136
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on HOMA-B?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
182
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Nodules diameters?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
165
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Trends in Use of Referral Hospital Services for Care of Sick Newborns in a Community-based Intervention in Tangail District, Bangladesh\n\n ABSTRACT:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district), Tangail district, Bangladesh, is promoting care-seeking for sick newborns through health education of families, identification and referral of sick newborns in the community by community health workers (CHWs), and strengthening of neonatal care in Kumudini Hospital, Mirzapur. Data were drawn from records maintained by the CHWs, referral hospital registers, a baseline household survey of recently-delivered women conducted from March to June 2003, and two interim household surveys in January and September 2005. Increases were observed in self-referral of sick newborns for care, compliance after referral by the CHWs, and care-seeking from qualified providers and from the Kumudini Hospital, and decreases were observed in care-seeking from unqualified providers in the intervention arm. An active surveillance for illness by the CHWs in the home, education of families by them on recognition of danger signs and counselling to seek immediate care for serious illness, and improved linkages between the community and the hospital can produce substantial increases in care-seeking for sick newborns.\n\nBODY.INTRODUCTION:\nThe timely and appropriate use of health services is crucial to reduce maternal and child mortality (1–4). Many lifesaving interventions, such as caesarean section, blood transfusion, oxygen, and intravenous antibiotics, can only be made available through health facilities. Evidence suggests that bringing women and children to facilities to receive these services is associated with reductions in mortality (1, 4). Countries that have achieved high rates of deliveries in facilities for basic or comprehensive essential obstetric care have witnessed significant and sustained decreases in maternal mortality (4), while countries, such as Sri Lanka, with elevated rates of care-seeking for sick children, have much lower rates of mortality among children aged less than five years (under-five mortality) than would be predicted from their per-capita income (1). Numerous studies have examined community-based interventions to improve care-seeking and referral for maternal emergencies from the community to first- and second-level facilities (3–8). Murray and Pearson have recently published a systematic review and proposed a research agendum to identify how programmes can better promote timely and appropriate maternal referral (9). Sibley has reviewed the effectiveness of traditional birth attendants (TBAs) in promoting referral from the community to facilities offering emergency obstetric care (10). Much less is known about referral of sick newborns from the community to health facilities. While several studies have examined referral of children, aged less than five-years, from first-level to second-level facilities (11–13), few studies have specifically examined referral from the community to facilities (14), and even less is known about referral of newborns from the community to facilities. Many factors affecting referral and care-seeking for maternal conditions from the community to health facilities could be applicable to promoting care for sick newborns. First, there is a need to act rapidly for certain maternal and newborn conditions, such as severe postpartum haemorrhage and birth asphyxia. So, research needs to examine not only recognition of danger signs, but also how long it takes for recognition of the problem to occur. The constraints on rapid action by families, such as distance, poor conditions of road, lack of transport, and lack of money, are common to both. Macintyre and Hotchkiss have developed a conceptual framework of factors at the individual, household, and community levels affecting referral in Africa which is equally applicable to other regions of the world (15). Second, in both mothers and newborns, many important causes of morbidity and mortality have signs and symptoms that \"lie on a continuum, from normal to abnormal\" (16). For such signs and symptoms, there can be both over-reporting of non-serious conditions, such as transient tachypnoea of the newborn or upper respiratory viral infection, or under-reporting of truly serious conditions, as happens when families fail to recognize excessive loss of maternal blood after delivery (16). Finally, patterns of decision-making within the household may lead to a significant delay, especially when permission of the husband is needed before seeking care but he is away, or when it is not clear to the family where to seek care from among a range of formal and informal sector providers (17–19). While there is much to learn from previous research on care-seeking and referral for older children, there are also obstacles to promoting early and appropriate care that are specific to newborns. In many cultures, families practise a period of postpartum confinement of both mother and newborn lasting from one to six week(s) or more (20). Additional efforts may be needed during this period to convince families to seek care outside the home. Sometimes, it is also difficult to detect danger signs in sick newborns, and families may not understand the significance of signs, such as hypothermia, feeding problems, or lethargy (21). This paper describes the trends in compliance by families with referrals when sick newborns were identified by community health workers (CHWs) and were referred to the Kumudini Hospital for care. In this project, families are educated about danger signs, and the CHWs visit the home during the postpartum period and examine newborns for any signs indicating the need for urgent medical care. Actions to increase the rate of compliance with referrals and their effects are also described.\n\nBODY.MATERIALS AND METHODS.STUDY SITE:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district) of Tangail district in central Bangladesh is implementing an intervention aimed at improving maternal and newborn-care practices and care-seeking for maternal and newborn conditions through: (a) behaviour change communication, (b) identification and referral of sick newborns in the community, and (c) strengthening of neonatal care in health facilities. The cluster-randomized trial has two arms: an intervention arm with CHWs delivering a package of maternal and newborn-care interventions in the home and a comparison arm. Mirzapur upazila has 13 unions, with a population of around 24,000 each; of these, six were randomly allocated to each study arm, excluding the one urban union. Given the need to have sick neonates assessed and treated in the hospital to identify aetiology of infections, a major focus of the problem is to identify barriers to care-seeking and design of strategies to address those barriers. The Kumudini Hospital, a 750-bed private hospital run by the Kumudini Welfare Trust, is situated at the centre of the project area. The hospital has a large paediatric unit (total 65 beds, including one separate neonatal ward) with two full-time consultants and 7–8 regular physicians.\n\nBODY.MATERIALS AND METHODS.DESCRIPTION OF THE INTERVENTION MODEL:\nIn the Projahnmo-II project, 36 CHWs were recruited and provided one month of initial training to equip them to provide a package of maternal and newborn care. These CHWs had a minimum of 10th grade education and resided in the population they would serve. Each CHW was responsible for about 4,000 people. The CHWs carried out bi-monthly pregnancy surveillance and registration of married women of reproductive age (MWRA) and made home-visits in the third and the eighth month of pregnancy to counsel families on birth and neonatal care preparedness (BNCP). After delivery, the CHWs made home-visits to promote evidence-based domiciliary newborn care and to identify and refer sick newborns and mothers on day 0 (day of birth), 3, 6, and 9. Improvements were made in maternal and neonatal healthcare at the designated referral facility (Kumudini Hospital), and the CHWs facilitated referrals of sick newborns they identified during home-visits to this hospital. For families that refused referral and for babies who had at least one danger sign of very severe disease, or any two from possible very severe disease, the CHWs carried out home-treatment of cases with suspected serious infection with oral co-trimoxazole. The Field Supervisors supervised the daily activities of CHWs in the community and also reviewed the key performance and process indicators relating to coverage and quality every fortnight and provided feedback to the CHWs. Figure 1 is a model that shows how the intervention package helps promote hospital care for sick newborns. During the antenatal period, families were educated about signs indicating the need to seek care and sources of care by health workers during antenatal care visits at health facilities and by CHWs during antenatal home-visits (left side of Fig. 1). This should lead to an increased recognition by families of danger signs in newborns. This, in turn, should lead them either to seek care directly (self-referral) from the Kumudini Hospital and other appropriate sources of care, or notify the CHW to come to the house and assess the child. The CHW may also come in contact with a sick newborn during the course of her routine postnatal home-visits, and all findings are recorded in a Visit Record Form (VRF). The criteria for referral of sick newborns are: (a) in the case of birth asphyxia: if breathing difficulty continues 20 minutes after birth despite resuscitation efforts; (b) if there is one or more signs/symptoms of very severe disease, such as fever or lethargy; (c) jaundice—any where in the body within 24 hours of birth; (d) eyes discharging pus (possible gonococcal eye infection); and/or (e) diarrhoea with blood in stool and/or dehydration. Fig. 1.Intervention model: promotion by community health workers of care for sick newborns at Kumudini Hospital between April 2004 and September 2005 (Table 1) Dotted arrow indicates action not anticipated in the intervention model\n*Coverage estimates from the second adequacy survey, September 2005\nSources of data: Project management information system (records maintained by CHWs and hospital registers) and household survey (second adequacy survey in September 2005)\nANC=Antenatal care;\nBNCP=Birth and neonatal care preparedness;\nCHWs=Community health workers A standard algorithm adapted from integrated management of childhood illness (IMCI) for use in the community by the CHWs is followed to assess and classify sickness in newborns. If the newborn requires referral, the CHW facilitates referral to the Kumudini Hospital. The community-based system of facilitated referral was in place by 19 February 2004 and initially consisted of the following elements, in addition to home-visits by the CHWs: (a) referral slips for the CHWs to fill in when referring a sick newborn to the hospital; (b) Birth and Neonatal Care Preparedness (BNCP) Cards, with an identification number, are supplied to families during antenatal home-visits by the CHWs. Families can carry the BNCP Card with them to the Kumudini Hospital in the event that the CHW is not available to issue a referral slip to the family when the newborn falls ill; (c) a referral-tracking form; (d) free inpatient care at the Kumudini Hospital for newborns arriving with a referral slip; (e) a system of emergency transport; and (f) training of TBAs, so that they could also promote referral to hospital for newborns with danger signs. If referral to the Kumudini Hospital fails, additional follow-up visits in the home are made to follow the condition of the child and treat presumptively with antibiotics, if appropriate. The CHW makes a final visit—called a graduation visit—as soon as the baby crosses 28 days of life. At that time, the completed VRF goes to the Mirzapur field office for review and is then sent to the main project office in Dhaka for data entry and further review.\n\nBODY.MATERIALS AND METHODS.MODIFICATIONS TO THE INTERVENTION MODEL:\nThe CHWs helped families to arrange transportation, convinced family members to have the newborn treated outside the home, and provided a transport allowance to the poorest families to reach the Kumudini Hospital. After three months of initial implementation of the programme, further changes were made to improve coverage with home-visits and compliance with referrals. A referral-tracking form was introduced in April 2004, and every two weeks, the number of newborns referred and the outcome of referral were reviewed in a meeting with the supervisors and CHWs. In early 2005, a decision was made to emphasize more the management and referral of birth asphyxia and low-birth-weight newborns. The CHWs started to use digital weighing machines in February 2005 to obtain the weight of the newborn at first contact. In April 2005, the CHWs received refresher training on how to counsel families during antenatal home-visits on low birth-weight and birth asphyxia.\n\nBODY.MATERIALS AND METHODS.MONITORING OF FUNCTIONING OF THE REFERRAL SYSTEM:\nData are presented from the project management information system (MIS) for the April 2004–September 2005 period, which includes the records maintained by the CHWs and registers maintained in the referral hospital (Kumudini Hospital). In addition, in-depth interviews were undertaken at baseline and during implementation to investigate the factors affecting compliance. Results of the interviews with parents appearing at the Kumudini Hospital and from those who did not comply with referral advice were shared with the CHWs and Field Supervisors to identify ways to improve counselling on referral.\n\nBODY.MATERIALS AND METHODS.SAMPLING AND SAMPLE SIZE:\nA baseline household survey among recently-delivered women was conducted in early 2003. Demographic and socioeconomic information of the listed households was collected, and information on birth-history and neonatal mortality was collected from all 14,526 women who had a pregnancy outcome in the 36 months preceding the survey. Information on knowledge, practices, and coverage of pregnancy, childbirth, and postpartum/postnatal care of mothers and newborns was collected from a randomly-selected sub-set of 4,611 recently-delivered women who had a pregnancy outcome in the last one year. Two interim household adequacy surveys were conducted in January and September 2005 to measure the adequacy of project inputs and selected process indicators to assess progress in early changes in behavioural patterns, including care-seeking. Identified through a systematic random-sampling method, in total, 1,200 women who had a pregnancy outcome in the last 7–8 months in each of the intervention and comparison arms were interviewed in each of the interim household surveys. Eighty-four randomly-selected parents arriving in the Outpatient Department of the Kumudini Hospital during January-June 2005 were asked why they had come to the hospital. Reasons for non-compliance with referral were analyzed on a continual basis and contributed to fine-tuning of the system of facilitated referral. Randomly-selected parents of 162 newborns who were referred for care but did not comply with referral during the same period mentioned above were interviewed regarding their reasons for non-compliance. Structured brief questionnaires were used in both instances.\n\nBODY.RESULTS.FUNCTIONING OF THE REFERRAL SYSTEM:\nResults of the second adequacy survey conducted in September 2005 showed that 72.5% of the recently-delivered women had attended at least one antenatal care visit, and 87.6% had received at least one antenatal BNCP visit by a CHW. Table 1 shows the trends between April 2004 and September 2005 in assessment, referral, and admission of sick newborns in the study intervention arm. Figure 1 presents data for the entire period. Although the project staff judged that the CHWs succeeded in identifying most pregnant women, the CHWs documented deliveries for only 3,354 (74.4%) of the 4,508 women estimated to have their due date during this period. The primary reason for this lower-than-expected figure was that significant numbers of women, particularly primigravidae, migrated at some point prior to delivery to live in another household located outside the intervention arm of the study. In most cases, they left the household of their husband's family (shashurbari) to reside in their natal home (baperbari), a phenomenon also observed in other sites in Bangladesh (20). Of 3,354 women who did not change residence, 3,228 (96.2%) received at least one home-visit by the CHW during the first 28 days of life of the baby. Table 1. Trends over time in assessment, referral, and admission of sick newborns in Mirzapur sub-district, Tangail district, Bangladesh between April 2004 and September 2005 (*indicates that figures are also displayed in Fig. 1 ) Variable and statistical assessment of trends Apr-Jun 2004 Jul-Sep 2004 Oct-Dec 2004 Jan-Mar 2005 Apr-Jun 2005 Jul-Sep 2005 Total Apr 2004-Sept 2005* Assessment and referral of sick newborns in the community by CHWs Home-deliveries 417 574 870 541 433 519 3,354* CHW-visit within first 28 days 324 443 862 659 436 504 3,228* Newborns assessed as sick 134 156 190 84 111 119 794* Referred to Kumudini Hospital 115 148 161 71 87 102 684* Percentage of sick newborns who were referred 85.8 94.9 84.7 84.5 78.4 85.7 86.1 Chi-square for linear trend=NS Arrival and admission at outpatient/emergency department of Kumudini Hospital Neonates reaching Kumudini Hospital OPD/emergency after self-referral or referral by CHWs 89 146 211 128 159 188 921* Neonates reaching Kumudini OPD/emergency after self-referral 25 55 82 75 95 111 443* Neonates reaching Kumudini Hospital OPD/emergency with CHW referral slip 64 91 129 53 64 77 478* Chi-square for linear trend=43.5, df=1, p<0.00001 71.9 62.3 61.1 41.4 40.3 41.0 51.9 Percentage of newborns referred by CHWs who arrived at Kumudini Hospital OPD/emergency 55.7 61.5 80.1 74.6 73.6 75.5 69.9 Chi-square for linear trend=12.97, df=1, p=0.00032 CHW=Community health worker; df=Degree of freedom; NS=Not significant; OPD=Outpatient department The CHWs identified 794 newborns as sick during this period, excluding newborns with feeding problems. Of these, 684 (86.1%) were referred by the CHWs to the Kumudini Hospital for care. The proportion of sick newborns who were referred stayed essentially constant between April 2004 and September 2005 (non-significant chi-square test for linear trend). Newborns arriving from households located in the intervention arm could either (a) have been referred by the CHW after she examined the child during a home-visit and issued a referral slip, or (b) the family could have taken the decision to seek care directly without first contacting the CHW, a situation we refer to as self-referral. Overall, of the 921 newborns arriving at the outpatient or emergency departments of the Kumudini Hospital during this period, 443 (48.1%) arrived after self-referral, and 478 (51.9%) arrived with a referral slip issued by the CHWs. The proportion of all cases who arrived with a referral slip declined continuously during this period (Row 8 of Table 1), from 71.9% at the beginning of implementation between April and June 2004 to 41.0% between July and September 2005, a trend which was highly significant (chi-square for linear trend=43.5, df=1, p<0.00001). Compliance with referral to the Kumudini Hospital by the CHWs increased from 55.7% during the first three-month period of implementation to 80.1% during the third three-month period of implementation (Row 9 of Table 1) and was thereafter maintained at 75–80%. The overall trend was significant (p=0.00032).\n\nBODY.RESULTS.INTERVIEWS ON FACTORS AFFECTING COMPLIANCE:\nEighty-four parents arriving in the Outpatient Department of the Kumudini Hospital were asked why they had come to the hospital. They mentioned (multiple responses allowed) that the CHWs advised them to visit the Kumudini Hospital because treatment was available (65.5%), treatment was of high quality (34.5%) and free of charge (21.4%), the hospital was the nearest one to their home (2.4%), and other reasons (4.8%). Parents of 162 newborns who were referred for care but did not comply with referral were interviewed. The reasons cited for non-compliance (multiple responses allowed) included: nobody was available to accompany the child (and the mother) to the health facility (24.7%); the child was given a traditional treatment instead (19.1%); bad weather or general strikes (17.9%); the family disliked hospital treatment (12.3%); symptoms resolved on their own (7.4%); unwillingness of the family or the TBA to refer the baby for other reasons (6.2%); and other issues (12.3%), such as illness of the mother; the child was too young to be taken for outside care; and lack of transport. Although distance was a commonly-cited reason for failure to seek care from the health facilities, the proportion of cases referred by the CHWs in the farthest unions in the intervention arm, Warsi (2 hours away), Ajgana (1.5 hours away), and Bahuria (1.5 hours away) were at approximately the same level (79.3%, 80.6%, and 82.7% respectively) as the closest unions that were 0.5 hours away from the Kumudini Hospital, Banail (87.9%), and Bhatgram (81.6%).\n\nBODY.RESULTS.EVALUATION OF TRENDS IN CARE-SEEKING:\nTable 2 demonstrates the changes in care-seeking/self-referral to the Kumudini Hospital and other providers between the baseline survey (January 2003) and the first (January 2005) and the second (September 2005) adequacy survey. Caution is necessary in assigning significance to the observed trends as the two adequacy surveys are based on much smaller samples than the baseline survey. At the time of the baseline household survey in January 2003, there was no significant difference between the intervention arm and the comparison arm of the study in the proportion of sick newborns who were taken outside the home for care from any qualified provider (including Kumudini Hospital), to the Kumudini Hospital specifically, or to an unqualified provider, most commonly an unlicensed 'village doctor'. Table 2. Trends in care-seeking for sick newborns from Kumudini Hospital and other providers based on population-based household surveys Measures of care-seeking Baseline survey: January 2003 First adequacy ssurvey: January 2005 Second adequacy survey: September 2005 Intervention arm Comparison arm Intervention arm Comparison arm Intervention arm Comparison arm Reported sickness among newborns in the sample Total number of newborns in the sample 2,053 2,290 523 550 520 548 Number of newborns reported to have been sick (%) 818 (37.5) 780 (37.6) 255 (48.8) 279 (50.7) 207 (39.8) 257 (46.9) Reported care-seeking outside home Proportion of sick newborns reported to have been given any care in or outside home 92.9 93.7 93.3 93.2 93.2 95.3 Proportion of sick newborns for whom care was sought from outside home 66.1 66.4 82.8 81.4 82.6 77.4 Reported care-seeking from qualified providers ( Fig. 2 ) Proportion of sick newborns for whom care was sought from qualified providers 31.2 29.6 55.7 38.4 60.4 33.9 Odds ratio for care from qualified providers, intervention vs comparison (95% CI) 1.08 (0.86–1.34) (p=0.499) 2.02 (1.41–2.90) (p<0.0001) 2.98 (2.00–4.44) (p<0.0001) Chi-square trend test for care from qualified providers, intervention group Chi-square for linear trend=80.13, df=1, p<0.00001 Chi-square trend test for care from qualified providers, comparison group Chi-square for linear trend=3.42, df=1, p=0.065 Reported care-seeking from Kumudini Hospital ( Fig. 3 ) Proportion of sick newborns for whom care was sought from Kumudini Hospital 17.9 17.6 42.0 21.9 46.4 23.0 Odds ratio for care from Kumudini Hospital, intervention vs comparison (95% CI) 1.02 (0.78–1.33) (p<0.882) 2.58 (1.74–3.84) (p<0.0001) 2.90 (1.91–4.41) (p<0.0001) Chi-square trend test for care from Kumudini Hospital, intervention Group Chi-square for linear trend=93.40, df=1, p<0.00001 Chi-square trend test for care from Kumudini Hospital, comparison Group Chi-square for linear trend=4.47, df=1, p=0.035 Reported care-seeking from unqualified providers ( Fig. 4 ) Proportion of sick newborns for whom care was sought from unqualified providers 66.7 67.9 49.8 66.0 36.7 65.0 Odds ratio for care from unqualified providers, intervention vs comparison (95% CI) 0.95 (0.76–1.17) (p<0.609) 0.51 (0.36–0.74) (p=0.0002) 0.31 (0.21–0.47) (p<0.0001) Chi-square trend test for care from unqualified providers, intervention group Chi-square for linear trend=71.01, df=1, p<0.00001 Chi-square trend test for care from unqualified providers, comparison group Chi-square for linear trend=0.90, df=1, p=0.34 CI=Confidence interval; df=Degree of freedom Between the time of the baseline and the first adequacy survey, there was a significant increase in care-seeking in both intervention and comparison arms of the study (Row 4 of Table 2). This difference could be due to both increased awareness of the newborn's health problems and/or changes in how the survey was administered. Figure 2 demonstrates that there was a highly significant (p<0.00001) increase in the proportion of families that sought care from qualified providers for sick newborns in the intervention arm (Fig. 2 and Rows 5 and 7 of Table 2) and a non-significant increase in the comparison arm (Rows 5 and 8). Figure 3 shows that care-seeking for sick newborns specifically from the Kumudini Hospital increased significantly in both intervention and comparison arms, but the increase was of a much greater magnitude in the intervention arm (Fig. 3 and Row 9–12 of Table 2). Finally, Figure 4 demonstrates that the proportion of families who sought care from unqualified providers, such as unlicensed village doctors, remained unchanged in the comparison arm, but declined significantly in the intervention arm (Fig. 4 and Row 13–16 of Table 2). Fig. 2.Trend in proportion of sick newborns for whom care was sought from qualified providers*p<0.0001; Chi-square for linear trend (intervention) 80.13 (p<0.00001)\nOR=Odds ration Fig. 3.Trend in proportion of sick newborns for whom care was sought from Kumudini Hospital*p<0.0001; Chi-square for linear trend (intervention) 93.4 (p<0.00001)\nOR=Odds ratio Fig. 4.Trend in proportion of sick newborns for whom care was sought from unqualified providers*p<0.0001; Chi-square for linear trend (intervention) 71.01 (p<0.00001)\nOR=Odds ratio\n\nBODY.DISCUSSION:\nSignificant reductions in neonatal mortality must be made to reach the Millennium Development Goal for under-five mortality. One key to reducing neonatal mortality is to ensure that sick newborns are assessed and treated quickly either in the home (22, 23) or in a health facility. Practices of postpartum confinement of mothers and newborns found in many cultures, difficulties in transport, and patterns of household decision-making are among the factors that can delay or prevent care-seeking outside the home. Data presented in this paper demonstrate that it is possible to achieve high rates of care-seeking from hospitals or other qualified providers and to significantly decrease care-seeking from unqualified providers, even in a low-income rural area where all these factors are present. The trends observed in the intervention arm included increased care-seeking, increased proportion of sick newborns arriving at the Kumudini Hospital after self-referral rather than referral by a CHW, increased compliance after referral by the CHWs, increased care-seeking from the qualified providers (Fig. 2) and from the Kumudini Hospital (Fig. 3), and decreases in care-seeking from the unqualified providers (Fig. 4). In the comparison arm, an increase in care-seeking from the Kumudini Hospital was also observed, but the proportions seeking care from the qualified and unqualified providers did not change significantly. Reasons for the increasing trend in the proportion of cases in the intervention arm arriving at the Kumudini Hospital after self-referral have not yet been fully elucidated, but include increasing awareness of the signs of illness in newborns and experience with the services offered by the Kumudini Hospital. There also appeared to be some cases where the CHWs judged that the newborns did not require referral, but the family decided to seek care from the Kumudini Hospital anyway. In a number of these cases, the child had physiologic jaundice, a condition which the family felt warranted further investigation, despite reassurances provided by the CHWs. The project investigators are currently investigating this situation further. Substantial increases in referral compliance for newborn illness were likely related to (a) education of families on danger signs by the CHWs; (b) active surveillance for illness by the CHWs during routine postnatal home-visits; (c) facilitated referral by the CHWs, including counselling, use of referral slips along with improved linkages between community and hospital; (d) incentives for labour/birth notification; (e) enhanced capacity at the referral-care centre to manage sick newborns; and (f) availability of subsidized treatment. Sustained community-level education enhanced the empowerment of families towards decision-making for self-referral. In low-income countries with high rates of neonatal mortality, sick newborns can either be treated presumptively in the home (22, 23) or referred to health facilities. This paper demonstrates that it is possible to achieve high rates of compliance with referral, but to do this requires an extensive infrastructure of CHWs or other community contact persons (8) to assess newborns and facilitate referrals. Alternatively, an increased emphasis could be placed on community mobilization, education on danger signs, and facilitation of self-referral, perhaps with similar results. This paper is one of the only studies to provide data on levels of referral compliance achieved through facilitated referral (12, 14). Whether the emphasis is on treatment in facilities or treatment in the community, substantial investments will need to be made in the creation of demand with the community, community and family education, and facilitation of referral.\n\nBODY.ACKNOWLEDGEMENTS:\nThis study was supported primarily through the generous support of the Infectious Disease Initiative of the Wellcome Trust–Burroughs Wellcome Fund. Additional support was provided by the Department for International Development (DFID), UK; the United States Agency for International Development, Office of Health, Infectious Diseases, and Nutrition, Global Bureau through the Global Research Activity Cooperative Agreement (No. GHS-A-00-03-00019-00); the Government of Bangladesh (Improved Health for the Poor); and Save the Children-USA through a grant from the Bill and Melinda Gates Foundation. The authors thank the study participants in Mirzapur upazila, Bangladesh, who were generous with their time and patience with interviewers through the several rounds of interviews.\n\n**Question:** Compared to Comparison arm what was the result of Promotion by CHWs of maternal and newborn-care interventions on Care-seeking from qualified providers for ill newborns ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
197
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Midwife-led unit on Pain relief: Acupuncture?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
161
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on Improvement in lower extremity Fugl-Meyer score ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
184
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Extend of the disease as visualized during surgery?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
200
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Efficacy of positive end-expiratory pressure titration after the alveolar recruitment manoeuvre in patients with acute respiratory distress syndrome\n\n ABSTRACT.INTRODUCTION:\nIn acute respiratory distress syndrome (ARDS), adequate positive end-expiratory pressure (PEEP) may decrease ventilator-induced lung injury by minimising overinflation and cyclic recruitment-derecruitment of the lung. We evaluated whether setting the PEEP using decremental PEEP titration after an alveolar recruitment manoeuvre (ARM) affects the clinical outcome in patients with ARDS.\n\nABSTRACT.METHODS:\nFifty-seven patients with early ARDS were randomly assigned to a group given decremental PEEP titration following ARM or a table-based PEEP (control) group. PEEP and inspired fraction of oxygen (FiO2) in the control group were set according to the table-based combinations of FiO2 and PEEP of the ARDS network, by which we aimed to achieve a PEEP level compatible with an oxygenation target. In the decremental PEEP titration group, the oxygen saturation and static compliance were monitored as the patients performed the ARM along with the extended sigh method, which is designed to gradually apply and withdraw a high distending pressure over a prolonged period, and the decremental titration of PEEP.\n\nABSTRACT.RESULTS:\nThe baseline characteristics did not differ significantly between the control and decremental PEEP titration groups. Initial oxygenation improved more in the decremental PEEP titration group than in the control group. However, dynamic compliance, tidal volume and PEEP were similar in the two groups during the first week. The duration of use of paralysing or sedative agents, mechanical ventilation, stay in the intensive care unit and mortality at 28 days did not differ significantly between the decremental PEEP titration and control groups.\n\nABSTRACT.CONCLUSIONS:\nThe daily decremental PEEP titration after ARM showed only initial oxygenation improvement compared with the table-based PEEP method. Respiratory mechanics and patient outcomes did not differ between the decremental PEEP titration and control groups.\n\nABSTRACT.TRIAL REGISTRATION:\nClinicalTrials.gov identifier: ISRCTN79027921.\n\nBODY.INTRODUCTION:\nTwo recent randomised controlled trials involving patients with acute lung injury (ALI) or acute respiratory distress syndrome (ARDS) demonstrated that mortality can be reduced significantly by setting a low tidal volume (VT) [1] and by setting both a low VT and adequate positive end-expiratory pressure (PEEP) levels titrated by pressure-volume curves [2,3]. However, this strategy favours further lung collapse or derecruitment, especially when used with a high inspired fraction of oxygen (FiO2) [4]. The importance of opening the lung and keeping it open seems increasingly significant in this era of lung-protective ventilatory support because the use of a small VT for this strategy may worsen progressive lung collapse. Moreover, the alveolar and systemic inflammatory responses can be attenuated by minimising overinflation and cyclic recruitment–derecruitment of the lung by reducing VT and increasing PEEP in ARDS [5]. The best method of setting optimal PEEP after recruitment to prevent recollapse is still a matter of debate [6]. In the ALVEOLI study, mortality rates and the number of ventilator-free days did not differ significantly between the lower- and higher-PEEP study groups [7]. This result may have reflected the use of the same PEEP level (combination of FiO2 and PEEP) for the heterogeneous patient group and an inappropriately high PEEP in the nonrecruiters, which may have resulted in overdistension. Gattinoni and colleagues reported that the percentage of potentially recruitable lung tissue may be different in patients with ARDS and that the use of a higher PEEP level in patients with a lower percentage of potentially recruitable lung may be harmful [8]. These studies did not evaluate completely the effect of using individualised PEEP on the survival rate of patients with ARDS. The higher PEEP levels should be adjusted according to individual lung morphology. However, the strategies for setting PEEP using a plateau pressure or recruitment manoeuvre do not decrease mortality [9,10]. We designed an individual PEEP strategy using decremental PEEP titration after an alveolar recruitment manoeuvre (ARM) for each patient with ARDS. An ARM is a way to standardise the history of lung volume [11]. The objective of this study was to evaluate whether setting the PEEP using decremental PEEP titration after ARM affects the oxygenation and outcome of patients in the early stage of ARDS compared with the table-based combinations of FiO2 and PEEP in the ARDS network [1].\n\nBODY.MATERIALS AND METHODS.STUDY POPULATION:\nFifty-seven consecutive patients (35 men and 22 women) admitted to the medical intensive care unit (MICU) of Asan Medical Center, in Seoul, Korea, who were diagnosed with ARDS of various aetiologies were enrolled in the study between July 2004 and September 2006. Patient selection for the study was based on the criteria of ARDS proposed by the American–European Consensus Conference on ARDS [12]: acute onset, presence of hypoxaemia (partial arterial pressure of oxygen (PaO2)/FiO2 (PF ratio) ≤ 200 mmHg regardless of the PEEP level), bilateral and diffuse opacities seen on frontal chest x-ray and absence of left ventricular failure with pulmonary arterial occluded pressure of 18 mmHg of less. The study protocol was approved by the institutional board of the ethics committee and written informed consent was obtained from the patients' families.\n\nBODY.MATERIALS AND METHODS.VENTILATOR PROCEDURES:\nPatients were given ventilatory support primarily in the supine position and ventilated according to the ARDS network strategy. FiO2, PEEP and respiratory rate were set to achieve an arterial oxygen saturation (SaO2) of between 88 and 92% [2]. The target VT was 6 ml/kg of predicted body weight, with allowances of up to 8 ml/kg if the SaO2 were below 88% or less than 7.2 of arterial pH by severe hypercapnoea. The patients were randomly assigned with the use of a randomisation scheme to either the decremental PEEP titration group or the control (table-based PEEP setting) group (Figure 1). Figure 1Study groups of patients. Four patients who withdrew from the study were excluded from the analysis. ARDS = acute respiratory distress syndrome; PEEP = positive end-expiratory pressure.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.TABLE-BASED PEEP SETTING (CONTROL) GROUP:\nThe FiO2-PEEP strategy has been used in previous ARDS Network studies (Figure 2). PEEP and FiO2 were set according to the table of lower PEEP/higher FiO2 combinations (the lower PEEP strategy of the ALVEOLI study), with the goal of obtaining a lower PEEP level compatible with an oxygenation target. Figure 2Study protocol. (a) Table-based positive end-expiratory pressure (PEEP) setting (control) group. (b) Decremental PEEP titration group after alveolar recruitment manoeuvre (ARM). FiO2 = inspired fracture of oxygen.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.DECREMENTAL PEEP TITRATION GROUP:\nThe ARM was performed immediately after enrollment in the study and was applied once a day usually in the morning for one week. The ventilatory circuit was not disconnected after ARM to avoid lung derecruitment. The ARM was also repeated when the ventilatory circuit was disconnected (incidentally or for bronchoscope) or if FiO2 requirement was increasing again in the patient, who showed initial improvement of oxygenation by ARM. If the weaning trial was performed within one week, the ARM was stopped earlier than the usual schedule. During the ARM, all patients were sedated and paralysed by continuous infusion of midazolam-ketamine and vecuronium bromide. No changes were made in the doses of inotropic agents or fluid infusion during the ARM. The ARM used the extended sigh method, which is designed to gradually apply and withdraw a high distending pressure over a prolonged period. It takes about 15 to 20 minutes for two cycles of ARM according to our protocol (Figure 2) [13]. We changed the ventilatory mode from pressure-controlled mode to the volume-controlled mode during ARM. The distending pressure was determined by the delivered VT, PEEP increment and the pause time (0.5 seconds). During the ARM, PEEP was added from baseline to 15, 20 and 25 cmH2O sequentially (every 30 seconds from the baseline PEEP until 25 cmH2O). The VT was decreased by 25% from the baseline VT during the incremental PEEP trial phase, and then returned to baseline levels during the decremental PEEP trial phase. Therefore, the distending pressures were changed depending on the patient's VT and lung mechanics. However, we did not allow the peak airway pressure to go above 55 cmH2O during the ARM. The decremental PEEP titration at the second cycle of ARM was performed with progressive decreases in PEEP in steps of 1 cmH2O every 30 seconds from 20 cmH2O while continuously monitoring saturation and static compliance. The decrease in PEEP was continued until a decrease of more than 2% of saturation from the previous SaO2 and drop of static compliance was identified. This PEEP level was considered the alveolar collapsing pressure and the optimal PEEP after the ARM was set 2 cmH2O above this pressure. No patients showed significant arrhythmia or gross barotraumas of any type during ARM.\n\nBODY.MATERIALS AND METHODS.PATIENT GROUP.RESCUE THERAPY:\nIf the level of inspired oxygen was not decreased to 0.6 or oxygenation improvement was not achieved after PEEP readjustment in all patients, rescue therapies such as prone position or nitric oxide inhalation were performed.\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION:\nThe primary end point was improvement in oxygenation (improvement of PaO2/FiO2 (PF) ratio). The secondary end points included respiratory mechanics (PEEP and dynamic compliance), ICU stay, duration of sedatives and paralysing agents and patient outcomes (28-day mortality, 60-day mortality, duration of mechanical ventilation). Responders were defined by a 20% improvement in the PF ratio on day 1 compared with day 0 (baseline) after PEEP adjustment [14].\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION.RESPIRATORY MECHANICS:\nAirway pressure and flow were monitored continuously. VT, dynamic compliance (in ml/cmH2O), and peak airway, mean airway and minute ventilation were recorded at 30 minutes after the change of PEEP level in both groups. Because pressure control mode was the main ventilatory strategy, we monitored and compared the dynamic compliance and peak airway pressure in both group.\n\nBODY.MATERIALS AND METHODS.OUTCOME MEASURES AND DATA COLLECTION.HAEMODYNAMICS AND GAS EXCHANGE:\nWe collected arterial blood samples to measure partial pressure of oxygen (PO2), partial pressure of carbon dioxide (PCO2), pH, and SaO2 30 minutes after reapplication of PEEP. Haemodynamic variables monitored included heart rate and systolic, diastolic and mean systemic arterial pressure.\n\nBODY.MATERIALS AND METHODS.DATA ANALYSIS:\nSample size calculation showed that 36 patients per group would provide 80% power at a two-sided α level of 0.05 to detect a 20% difference in the improvement of oxygenation (improvement of PF ratio). All data were analysed using SPSS for Windows (version 11.0; SPSS Inc., Chicago, IL, USA). Statistical analyses were based on the intention-to-treat principle and involved all patients who had undergone randomisation. All values are expressed as the mean ± standard error of the mean or as the number and percentage of patients. Probability of mortality and differences between the groups were compared using a log-rank test. The chi-squared test or Fisher's exact test was used to compare categorical data, and Student's t test or the Mann-Whitney U test was used to compare continuous data. Significance was defined as p < 0.05.\n\nBODY.RESULTS.CHARACTERISTICS OF THE PATIENTS:\nWe enrolled 61 patients in the study, 30 of whom were randomly assigned to the control (table-based PEEP setting) group and 31 to the decremental PEEP titration group. Fifty-seven patients completed the study (27 in the control group and 30 in the decremental PEEP titration group) and contributed data for the analyses. Most baseline characteristics were similar in the two study groups (Table 1). The most common cause of ARDS was pneumonia. The initial ventilatory setting and severity index did not differ between the control and decremental PEEP titration groups. Table 1 Baseline characteristics of the patients at enrollment Control group (n = 27) Decremental PEEP titration group (n = 30) Age (years) 62.0 ± 2.2 55.0 ± 3.7 Percentage of women 37 40 APACHE II score 20.0 ± 1.4 22.0 ± 1.1 Lung injury score 2.5 ± 0.1 2.8 ± 0.2 Tidal volume (ml/kg of predicted body weight) 8.0 ± 1.4 7.9 ± 1.9 Respiratory rate (breaths/minute) 22.0 ± 3.0 22.2 ± 3.2 Peak airway pressure (cmH 2 O) 25.9 ± 5.9 27.8 ± 5.5 Positive end-expiratory pressure (cmH 2 O) 7.0 ± 3.7 8.4 ± 3.1 Dynamic compliance (Cdyn, ml/cmH 2 O) 25.7 ± 8.1 24.3 ± 7.6 PF ratio (PaO 2 :FiO 2 ) 110.8 ± 6.3 115.0 ± 8.5 Co-morbidities, n Haematological malignancy 3 7 Solid organ malignancy 6 4 Chronic liver disease 5 3 Connective tissue disease 2 1 Others a 3 3 Cause of lung injury (ARDSp:ARDSexp) 18:9 20:10 Pneumonia 15 17 Sepsis 7 7 Massive transfusion 2 1 Pulmonary alveolar haemorrhage 1 1 Others b 2 4 Data was presented as mean ± standard error of the mean. a including complicated diabetes mellitus (n = 4), Crohn's disease (n = 1) and AIDS (n = 1). b including leptospirosis (n = 3), near-drowning (n = 1), contusion (n = 1) and scrub typhus (n = 1). APACHE = acute physiology and chronic health evaluation; ARDSp = pulmonary ARDS; ARDSexp = extrapulmonary ARDS; FiO 2 = inspired fracture of oxygen; PaO 2 = partial arterial pressure of oxygen; PEEP = positive end-expiratory pressure. \n\nBODY.RESULTS.RESPIRATORY MECHANICS AND OXYGENATION:\nFigure 3 shows the ventilatory setting and respiratory variables at baseline and follow-up during the first week of treatment. The peak pressure was significantly higher on days 3 and 5 in the decremental PEEP titration group than in the control group, and the mean pressure was significantly higher in the decremental PEEP titration group because of the higher PEEP during the first week. Dynamic compliance and VT during the first week were similar in the two groups. Oxygenation improved compared with the baseline PF ratio in both groups (Figure 4). Initial oxygenation improved more in the decremental PEEP titration group than in the control group. The partial arterial pressure of oxygen (PaCO2) level was significantly higher in the decremental PEEP titration group than in the control group on day 1, suggesting increased dead space ventilation. However, the improvement of oxygenation and PaCO2 level were not different between the two groups during follow-up. Figure 3Respiratory values during the first week of treatment. The closed circles indicate the control group and the open circles denote the decremental positive end-expiratory pressure (PEEP) titration group. Values are expressed as the mean ± standard error of the mean (bars). *p < 0.05 between the control and decremental PEEP titration groups; †p < 0.05 compared with day 0 in the control group; ‡p < 0.05 compared with day 0 in the decremental PEEP titration group. Figure 4Oxygenation changes and PaCO2 levels during the first week of treatment. All patients showed improved oxygenation during treatment. The level of partial arterial pressure of carbon dioxide (PaCO2) at day 1 was increased significantly in the decremental positive end-expiratory pressure (PEEP) titration group than the control group. The black bars indicate the control group and gray bars denote the decremental PEEP titration group. Values are expressed as the mean ± standard error of the mean (bars). *p < 0.05 between the control and decremental PEEP titration groups, †p < 0.05 compared with day 0 in the control group, ‡p < 0.05 compared with day 0 in the decremental PEEP titration group.\n\nBODY.RESULTS.CLINICAL OUTCOMES:\nThe overall mortality at 28 days was 37%. Mortality at 28 days was 33% in the control group and 40% in the decremental PEEP titration group (Table 2). Using Cox regression for 28-day mortality, the survival rate in the decremental PEEP titration group was not different (p = 0.725; hazard ratio = 1.168; 95% confidence interval = 0.493 to 2.768). However, 60-day mortality was significantly increased to 55.6% (p = 0.031) compared with 28-day mortality (33.3%) in the control group only. Table 2 Clinical outcomes according to treatment group Control group (n = 27) Decremental PEEP titration group (n = 30) p value Responder (%) 44.4 70 0.046 Clinical outcomes Duration of mechanical ventilation, days 15.2 ± 3.2 19.8 ± 0.5 0.380 Intensive care unit stay, days 21.4 ± 5.3 25.1 ± 5.6 0.643 Duration of paralysing agent, days 9.0 ± 2.3 11.8 ± 2.0 0.358 Duration of sedative agents, days 14.2 ± 2.4 18.7 ± 3.4 0.303 Weaning trial within seven days 8 6 Tracheostomy 5 8 Reintubation 5 2 Barotrauma 3 3 Ventilator-associated pneumonia 5 5 Mortality, number (%) Mortality at 28 days 9 (33.3) 12 (40) 0.784 Death in the intensive care unit 13 (48.1) 14 (46.7) 1.000 Mortality at 60 days 15 (55.6) 14 (46.7) 0.599 Cause of in-hospital death, number (%) Progressive respiratory failure 8 (53.3) 8 (57.1) Refractory septic shock 4 (26.7) 2 (14.3) Hepatic failure 3 (20) 2 (14.3) Myocardial infarction 2 (14.3) Rescue therapy (%) Prone position 44.4 50.0 0.792 Nitric oxide inhalation 48.1 53.3 0.793 Data was presented as mean ± standard error of the mean. PEEP = positive end-expiratory pressure. Eight patients (30%) in the control group and six patients (20%) in the decremental PEEP titration group had performed the weaning trial within a week of enrollment. The incidence of barotrauma was similar in both groups. The durations of mechanical ventilation, ICU stay and use of paralysing or sedative agents did not differ between the groups (Table 2).\n\nBODY.DISCUSSION:\nAs suggested by Lachmann more than 10 years ago [15], \"open up the lung and keep the lung open\" appears advantageous to recruit the lungs of patients with ARDS and to prevent subsequent lung derecruitment [12]. Clinical outcomes were similar regardless of whether lower or higher PEEP levels were used in the ALVEOLI trial [7]. The problem of the ALVEOLI trial was the higher PEEP strategy, which was table-based like the one on the current study, matched on the oxygenation target regardless of any patient-related variable. A reasonable approach to determining the appropriate level of PEEP requires maintaining PEEP-induced reopening of atelectatic areas and avoiding PEEP-induced lung overinflation. Higher than traditional PEEP levels together with lung-recruiting maneuvers seems to be a way to find an appropriate PEEP level [16]. Experimental data suggest that the effects of ARM on alveolar recruitment are transient if the preceding PEEP levels are maintained after the manoeuvre [14]. Once the alveoli have been recruited, higher PEEP levels are required to keep them aerated [17]. The right level of PEEP as an anti-derecruiting force is important in preserving the effect of the ARM. We previously reported that a sufficient level of PEEP after ARM is important as an anti-decruitment strategy [18]. We hypothesised that the decremental PEEP trial would be an appropriate method to establish the PEEP level after ARM at bedside. Because higher PEEP and the ARM performed in patients with mild lung injury may have fewer benefits and more adverse effects, we only focused on ARDS patients to address our assumption. We found that daily decremental PEEP titration after ARM showed only initial oxygenation improvement compared with the table-based PEEP method and did not improve the respiratory mechanics within a week. We performed the ARM and PEEP titration daily during the first week in the decremental PEEP titration group. However, no significant differences were observed in the 28-day mortality, ICU stay and 60-day mortality. Although the responder rate was higher in the decremental PEEP titration group than in the control group, the earlier improvement in oxygenation was not associated with increased survival rate. Our finding showed the 60-day mortality in the control group was significantly increased compared with the 28-day mortality. We could not explain whether this finding was associated with the protective effect of ARM to the ventilator-induced lung injury. To add any relevant information, further study will be needed for the biomarkers such as proinflammatory cytokines. The lower dynamic compliance in the decremental PEEP titration group was an unexpected result, although there was no significant difference between the two groups. We speculated that a higher peak airway pressure might affect the lower dynamic compliance in the decremental PEEP titration group than the control. A reason for this result might be related to the subjects' characteristics. Most of the patients with ARDS had pneumonia, which did not respond well to the applied PEEP [19]. We included mostly pulmonary ARDS with severe underlying diseases, which would be a common phenomenon in a university hospital MICU. That may be the reason why mortality related to progressive respiratory failure was higher in our study group. The mortality of patients with pneumonia was 43.3% and the mortality of patients without pneumonia was 29.6%. The baseline lung conditions of these patients was a higher proportion of refractory consolidation to the distending pressure which may also have influenced the PF ratio of less than 250 and PEEP levels less than 15 cmH2O after ARM. Talmor and colleagues reported that a low lung distending pressure was applied in the patients with a stiff chest wall [20]. We did not measure the chest-wall mechanics or the recruitable lung, so we could not address this possibility as a cause of low PF ratio. One limitation of our study is that we could not evaluate whether recruitment manoeuvre maximised the alveolar collapse. If the recruitment effect of our ARM was not sufficient, the effect of a decremental PEEP trial might be insufficient. Borges and colleagues reported that a peak airway pressure of more than 60 cmH2O could recruit the collapsed lung [21]. Another limitation is that our indicators of oxygen saturation and static compliance to find an appropriate PEEP level might be insensitive to detect the collapsing pressure of the lung. Finally, small sample size in a single centre limits the power of the study outcomes.\n\nBODY.CONCLUSION:\nThe daily decremental PEEP titration after ARM did not show the persistent improvement of oxygenation, the respiratory mechanics and the mortality rate of patients with ARDS compared with the table-based PEEP setting. Further investigations are needed to find the correct level of PEEP in ARDS with reference to chest wall compliance and alveoli mechanics.\n\nBODY.KEY MESSAGES:\n• The daily decremental PEEP titration after ARM method did not show a persistent improvement of oxygenation. • Respiratory mechanics such as dynamic compliance, VT and PEEP were not significantly different between the daily decremental PEEP titration after ARM group and the table-based PEEP setting group. • The daily decremental PEEP titration after ARM without the reference of lung mechanics did not reduce the dependence of ventilator or mortality rate of patients with ARDS compared with the table-based PEEP setting.\n\nBODY.ABBREVIATIONS:\nALI: acute lung injury; ARDS: acute respiratory distress syndrome; ARM: alveolar recruitment manoeuvre; FiO2: inspired fracture of oxygen; MICU: medical intensive care unit; PEEP: positive end-expiratory pressure; PaCO2: partial arterial pressure of carbon dioxide; PaO2: partial arterial pressure of oxygen; PCO2: partial pressure of carbon dioxide; PO2: partial pressure of oxygen; SaO2: arterial oxygen saturation; VT: tidal volume.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nJWH recruited patients, analysed the data and wrote the manuscript. HJ and HSC helped to recruit patients and analysed the data. SBH and CML recruited patients and interpreted the data. YK designed the study, interpreted the data and wrote the paper. All authors read and approved the final manuscript.\n\n**Question:** Compared to table-based PEEP (control) group what was the result of Decremental PEEP titration group on The survival rate / overall mortality of patients with ARDS?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
123
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Postprandial plasma glucose?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
180
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Haemoglobin concentration?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
203
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Immunogenicity and Smoking Cessation Outcomes for a Novel Nicotine Immunotherapeutic\n\n ABSTRACT:\nNicVAX®, a nicotine vaccine (3'AmNic-rEPA), has been clinically evaluated to determine if higher antibody concentrations are associated with higher smoking abstinence rates and if doses and frequency of administration are associated with increased antibody response. This randomized, double-blinded, placebo-controlled multicenter clinical trial (N=301 smokers) tested 200 and 400 μg doses administered 4 or 5 times over 6 months compared to placebo. 3'AmNic-rEPA recipients with the highest serum anti-nicotine antibody response (top 30% by AUC) were significantly more likely to attain 8 weeks continuous abstinence from weeks 19 through 26 than the placebo recipients (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). The 5 injection 400 μg dose regimen had the greatest antibody response and had significantly higher abstinence rates than placebo. This study demonstrates proof-of-concept that 3'AmNic-rEPA elicits antibodies to nicotine and is associated with higher continuous abstinence rates, justifying its further development as a treatment for nicotine dependence.\n\nBODY.INTRODUCTION:\nWorldwide, smoking prevalence is 1.2 billion and approximately 5 million people die each year of smoking caused illnesses [1]. The global rate of smoking and smoking related deaths is anticipated to increase over the next 20 years unless significant public health measures are instituted. These include effective cessation interventions such as pharmacological treatments, which improve cessation rates by 1.5 to 3 fold over placebo intervention [2, 3]. Approved pharmacotherapies (e.g., nicotine replacements, bupropion SR, varenicline) for smoking cessation act on the central nervous system, each with a different mechanism of action. Other novel medications are being developed including immunotherapeutics targeting nicotine. Nicotine conjugate vaccines stimulate the immune system to develop nicotine specific antibodies (Abs) using an immunogen comprised of nicotine covalently linked to a larger carrier protein. Conceptually, the mechanism of action is that anti-nicotine antibodies bind nicotine molecules and the resulting complex is too large to cross the blood-brain barrier. With increasing Ab levels more nicotine is captured and sequestered in the blood and prevented from entering the brain, leading to less reinforcing effects from nicotine. Animal studies have demonstrated that passive or active immunization results in approximately 30% to 90% less nicotine entering the brain compared to control rats [4–7] and attenuated locomotor [4, 5] and behavioral [8, 9] responses to nicotine. Furthermore, vaccination reduced nicotine elimination from the body in a study with rats [10, 11], which may also contribute to reduced smoking. Although human studies are limited, published data evaluating different nicotine vaccines support the general concept that nicotine vaccines can be effective for smoking cessation in some smokers [12, 13]. Unfortunately, these studies either had small sample sizes [12], did not use an intent-to-treat population of smokers [13] or did not perform statistical analysis of the data [14]. The primary aim of the present study was to establish the proof-of-concept that (i) anti-nicotine antibodies are useful as an aid to smoking cessation and (ii) higher serum anti-nicotine antibody concentrations are associated with higher abstinence rates in an intent-to-treat population of smokers. One of the challenges with immunotherapeutics, such as vaccines, is attainment of therapeutic levels of antibody in most people. Therefore, this study tested two different doses of 3'-aminomethylnicotine P. aeruginosa r-exoprotein A - NicVAX (3'AmNic-rEPA) to identify a dose and schedule for further development: 200 and 400 μg across two different schedules (4 or 5 injections) compared to placebo for immunogenicity, efficacy and safety.\n\nBODY.RESULTS:\nA total of 301 subjects were randomized. Figure 2 shows the disposition and number of subjects within each treatment group. No significant group differences were observed in the demographic or smoking history by treatment or antibody levels (see Table 1).\n\nBODY.RESULTS.COMPLIANCE:\nAll 301 subjects received injection 1, 96.7%, 84.1%, 72.4% and 61.2% received injections 2, 3, 4 and 5 (Schedule 2 subjects only), respectively. No significant differences were observed across treatment groups for subjects receiving injections 2 through 4 for Schedules 1 and 2. Mean in-study duration was 286 ± 121 days.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON ABSTINENCE:\nHigh Ab responders to 3'AmNic-rEPA were defined as the top 30% of responders by AUC (0 to 26 weeks) and the low Ab group as the remaining bottom 70% of responders. 3'AmNic-rEPA recipients in the high Ab group were significantly more likely to attain 8 weeks of continuous abstinence from weeks 19 through 26 than placebo (24.6% vs. 12.0%, p=0.024, OR=2.69, 95% CI, 1.14–6.37). No significant differences were observed between the 3'AmNic-rEPA low Ab group vs. placebo (9.3% vs. 12.0%., p=0.46). As a secondary outcome, continuous abstinence rate (CAR) to 52 weeks were evaluated from weeks 19 to 52 and were significantly higher for the high Ab group vs. placebo (19.7% vs. 10.0%, p=0.044, OR=2.64, 95% CI, 1.03–6.79) with no significant difference between the low Ab group and placebo (7.1% vs. 10.0%, p=0.43). 7-day point prevalence abstinence results show that subjects with high Ab levels were significantly more likely to abstain compared to placebo at 26 weeks (36.1% vs. 16.0%, p=0.0024, OR=3.30, 95% CI, 1.53–7.13) and 52 weeks (31.1% vs. 12.0%, p=0.0021, OR=3.69, 95% CI, 0.42–2.14). No significant differences were observed in the point prevalence abstinence rates between the low Ab group and placebo at 26 and 52 weeks (12.9% vs. 16.0%, p=0.51 and 11.4% vs. 12.0%, p=0.89, respectively). As shown in Figure 3A, abstinence rates remained essentially the same following the target quit date (TQD) for the duration of the study. To further validate the proof-of-concept, the relationship between abstinence during the final eight weeks of the study and anti-nicotine Ab concentrations (AUC) is shown in Figure 3B for all subjects receiving the vaccine. Continuous abstinence rates from week 45–52 are displayed for each 10th percentile increase in AUC. The proportion of abstinent subjects increased with increasing AUC percentile, and the ordered ranking maintained.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EFFECTS OF HIGH AB ON TIME TO CONTINUOUS ABSTINENCE:\nAn exploratory analysis examined the rate and time to continuous abstinence through study end (Figure 3C). Most smokers quit soon after the TQD, with a clear divergence of the high Ab group from the placebo and low Ab group. Among the 18 high Ab continuous abstainers, 12 initiated abstinence prior to the primary endpoint while 6 initiated their abstinence after the start of the primary endpoint. Furthermore, 3 of the 15 subjects who abstained during the primary endpoint relapsed by the end of the study. Cox proportional hazards analysis demonstrated superiority of the high Ab group compared to placebo (p=0.0069, hazard ratio of 2.76).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.EVALUATION OF LONG-TERM ABSTINENCE:\nAs most subjects achieved abstinence shortly after their TQD, additional analyses were undertaken to evaluate prolonged abstinence to 6 and 12 months allowing for a 2 week grace period after the TQD [15]. (Prolonged abstinence is defined as not a single puff during the period from 2 weeks after the TQD for 20 weeks and 44 weeks, respectively). Prolonged abstinence rates to 6 months were significantly higher in the high Ab group vs. placebo (19.7% vs. 6.0%, p=0.0060, OR=4.41, 95% CI, 1.53–12.71) with no significant differences between the placebo and low Ab groups (7.9% vs. 6.0%, p=0.60). Subjects with high Ab were also significantly more likely to be abstinent for 12 months compared to placebo (18.0% vs. 6.0%, p=0.014; OR of 3.84; 95% CI, 1.32–11.20). The low Ab group did not differ significantly from placebo (7.1% vs. 6.0%, p=0.67).\n\nBODY.RESULTS.PROOF-OF-CONCEPT.CIGARETTE SMOKING IN NON-QUITTERS:\nStatistically significant differences were observed in reduction of daily cigarette consumption and cotinine between non-abstainers (weeks 19–52) with high Ab levels and non-abstainers in the placebo group (p=0.0015 and 0.019, respectively; see Figures 4A and 4C. The difference in the median reduction in cigarette consumption, following the TQD, between the high Ab non-abstainers and placebo non-abstainers was on average 4.6 cigarettes per day. Similarly, cotinine geometric mean concentrations (GMCs) were 19.0% lower on average following the target quit date in the high Ab non-abstainers as compared to placebo non-abstainers. Median cigarettes per day and cotinine GMC for placebo and low Ab group are nearly identical over the study period. Differences in mean CO were not observed across all three groups (see Figure 4B). 15 out of the 301 subjects smoked more than a 2-fold higher number of cigarettes following the TQD as compared to baseline with no significant difference between the placebo (n=4/100) and 3'AmNic-rEPA (n=11/201) groups. The highest smoking levels observed post-TQD were 5-fold baseline in the placebo and 4-fold baseline in the 3'AmNic-rEPA groups. Elevated smoking levels for 11 of these 15 subjects returned to below 2-fold baseline by study end. Subjects with remaining elevated levels were similar between the 3'AmNic-rEPA group (n=3/201) and placebo (n=1/100). Individual subjects with CO levels elevated by 2-fold or higher than baseline were also assessed and results were similar with no significant difference between the placebo (n=5/100) and 3'AmNic-rEPA (n=13/201) groups.\n\nBODY.RESULTS.PROOF-OF-CONCEPT.WITHDRAWAL SYMPTOMS:\nSignificant differences were not observed in overall withdrawal severity between placebo and the high and low Ab groups (p >0.22).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.IMMUNOGENICITY AND EFFICACY BY STUDY GROUP:\nFigure 5 depicts immune response by study group from baseline to week 52. Anti-nicotine Ab GMCs increased across all active treatment groups after each vaccination, with each subsequent dose resulting in a higher Ab response than the previous dose. Schedule 2 showed a higher initial increase in Ab concentrations. The 400 μg/Schedule 2 group demonstrated the highest Ab concentrations. However, no significant differences (p >0.05) were observed in AUC, Cmax and Cavg across the treatment groups to 26 or 52 weeks likely because the study was not powered to detect such difference. An intent-to-treat analysis demonstrated that the Schedule 2, 400 μg dose group had significantly higher prolonged abstinence to 6 months as compared to placebo (17.6% vs. 6.0%; p=0.015; OR of 4.14; 95% CI, 1.32–13.02), although not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0%, p=0.054; OR=3.23; 95% CI, 0.98–10.67) or between placebo and Schedule 1 for each of the doses (p >0.84). The Schedule 2, 400 μg dose group also had the highest rates of prolonged abstinence to 12-months, significantly higher than placebo (15.7% vs. 6.0%, p=0.038; OR=3.44; 95% CI, 1.07–11.04), but not significant for the Schedule 2, 200 μg dose (14.0% vs. 6.0% for 200 (p=0.056; OR=3.21; 95% CI, 0.97–10.63) or between placebo and Schedule 1 for each dose (p >0.88).\n\nBODY.RESULTS.EFFECTS OF DOSE AND SCHEDULE.SAFETY:\nTable 2 lists the number of subjects experiencing local and systemic reactogenicity. Reactogenicity events were aggregated over all injections. Overall, ache and tenderness were the most commonly reported local events, with at least one report by nearly all subjects (86% to 98%) in each treatment group. Myalgia, malaise, and headache were the most commonly reported systemic events (64% to 88% of subjects). Swelling, heat, burning, erythema, and nausea were reported by about half the subjects. Fever and vomiting were less common (4% to 16%). A total of 1184 treatment-emergent adverse events (AEs), predominantly rated mild or moderate, were reported by 266 of 301 subjects; 87.1% of 3'AmNic-rEPA recipients and 91.0% of placebo recipients. On average, 3.7 and 4.3 events were observed per person in the vaccinated and placebo groups, respectively, including subjects with no events. The distribution of 161 physician-determined treatment-related AEs, according to severity and relationship to treatment, was similar for the 3'AmNic-rEPA and placebo arms. Seven 3'AmNic-rEPA recipients (3.5%) and 2 subjects in the placebo arm (2.0%) withdrew from the study due to adverse events. 18 Serious AEs were reported: 8 events in the 3'AmNic-rEPA treatment groups among 7 subjects (3.5% of the 3'AmNic-rEPA recipients) and 10 events in the placebo group among 5 subjects (5.0% of the placebo recipients). Only one of these SAEs (anaphylactic reaction in a 3'AmNic-rEPA 400 μg/Schedule 2 recipient) was considered by the Investigator to be treatment related. This subject, who had a history of urticaria to penicillin and seasonal allergies, experienced difficulty breathing, throat tightness, facial erythema and urticaria 70 minutes after the initial vaccination. The subject was treated with a single injection of subcutaneous epinephrine and diphenhydramine, which resolved the symptoms. Herpes Zoster was reported in 6 subjects; one occurring within 3–5 hours after the first vaccination which would be impossible to link to vaccination. Of the remaining cases, 4 (2%) occurred in 3'AmNic-rEPA recipients; while 1 occurred in placebo (1%). In contrast, the related herpes virus, simplex infection was reported in 4 3'AmNic-rEPA recipients (1%) and 3 placebo recipients (2%).\n\nBODY.DISCUSSION:\nResults demonstrated the proof-of-concept that smokers who achieved higher anti-nicotine Ab concentrations were more likely to quit and remain abstinent from smoking. The high Ab group demonstrated the highest abstinence rates independent of the time period of ascertainment. Similarly, in a separate study conducted by Cornuz and coworkers [13] testing a different nicotine vaccine (nicotine derivative conjugated to a virus-like particle derived from bacteriophage Qβ), post hoc analysis showed subjects stratified to the highest Ab group had a significantly higher quit rate than placebo. However, unlike the current study, which used the intent-to-treat (ITT) population to establish proof of concept, the reported finding by Cornuz et al. [13] was observed after eliminating about a third of the subjects who used nicotine replacement therapies during the course of the study or who had incomplete Ab titer values. In the present 3'AmNic study, subjects in the high Ab group had observed odds ratios of 4.4 (95% CI 1.5–12.7) and 3.9 (95% CI 1.3–11.2) for prolonged abstinence rates to 6 and 12 months versus placebo. Although no direct comparisons can be made, these odds ratios are not unlike ones observed in the meta-analyses conducted for the U.S. Clinical Practice Guideline where the reported odds-ratios ranged from 1.5 (95% CI 1.2–1.7) for nicotine gum to 3.1 (95% CI 2.5–3.8) for varenicline at 6 months post-quit [3]. If current study findings are confirmed in larger studies, imunotherapeutics are likely to emerge as an important aid to smoking cessation. No significant compensatory smoking in response to the presence of anti-nicotine antibodies, as determined by the number of cigarettes smoked per day, carbon monoxide levels or cotinine levels, was observed in this study. This result is consistent with observations from other studies [12, 13]. In the current study, subjects in the high Ab group who did not abstain smoked significantly lower number of cigarettes (median reduction of ~5 cigarettes/day) and experienced lower cotinine levels (~20%) than placebo subjects along with no differences observed between the low Ab and placebo groups. However, a small number of individual subjects (N=15/301) smoked more than 2-fold the number of cigarettes at baseline with no significant differences between the active treatment and placebo groups. A major challenge for immunotherapeutics is to stimulate high Ab levels in the vast majority of smokers trying to quit. Vaccine dose and frequency of vaccination have an impact on the Ab levels attained. The 5 injection/400 μg dose was associated with the highest Ab response, although not statistically significant, possibly due to the small sample size. Importantly, this dose and schedule demonstrated statistically significant improved 44-week CAR compared to placebo. Because the 4 injection/400 μg dose was not associated with higher abstinence rates, this result demonstrates that consideration of both dose and schedule of injection are critical. In an independent, follow-up immunogenicity study to examine if peak Ab levels could be elevated, a total of 74 subjects received 6 injections of 400 μg 3'AmNic-rEPA at week 0, 4, 8, 12, 16, and 26. More than 80% of subjects receiving the 6-dose immunization regimen exceeded a target level of Ab (25 μg/ml) by week 14. In contrast, only 50% of subjects receiving 5 injections of the 400 μg dose achieved this level by week 14 in the current study and, only 7% of subjects attained this level by the target quit date. This finding suggests that more frequent injections and a later quit date may increase treatment success. In general, 3'AmNic-rEPA was well-tolerated. The frequencies of local and systemic vaccine reactogenicity events were similar in the vaccine and placebo groups and similar to licensed adult vaccines containing Alum adjuvant [16]. The slight increase in cases of herpes zoster observed in this study may be spurious, but continued monitoring is necessary to determine if a causal relationship exists. The occurrence of a single anaphylactic reaction would suggest a need for continued monitoring and follow-up, even considering the subjects' history of prior drug allergy to penicillin.1 In summary, results from this study support the concept that high anti-nicotine Ab levels are associated with higher rates of abstinence. These findings suggest that vaccines attaining high Ab levels by the target quit date may be more effective. Other future strategies may include examining additional ways to increase Ab levels across all individuals. Nonetheless, this study demonstrates that 3'AmNic-rEPA has significant potential as a smoking cessation, and perhaps a relapse prevention aid.\n\nBODY.METHODS.STUDY POPULATION:\nSmokers were recruited via advertisement across nine geographically diverse U.S. sites. Interested subjects were screened over the telephone and more extensively screened at the first Screening Visit. Subject informed consent was obtained prior to screening. Subjects were 18 years of age or older, smoked ≥15 cigarettes/day, had exhaled CO ≥10 ppm; wanted to quit smoking, and were in good general physical and mental health. Exclusion criteria included recent use of any medications or drugs that might interfere with immune response, interact with the vaccine, and pharmacotherapies or other treatments for smoking cessation. For females, a negative urine pregnancy test at enrollment and active use of acceptable birth control or documentation of surgical sterility was required.\n\nBODY.METHODS.STUDY DESIGN:\nThis Phase 2 study was a randomized double-blind, placebo-controlled, parallel-arm trial design (see Figure 1). Four treatment groups varied the dose and/or schedule of intramuscular vaccination: 200 or 400 μg of 3'AmNic-rEPA or placebo according to Schedule 1 (weeks 0, 6, 12, and 26) or Schedule 2 (weeks 0, 4, 8, 16, and 26). Subjects (N=150) were first randomized within Schedule 1 groups in a 1:1:1 ratio (200 μg: 400 μg: placebo) and then 151 subjects randomized within Schedule 2 groups in the same ratio. The TQD was 1 week after the second injection (end of week 7 for Schedule 1 and end of week 5 for Schedule 2). If the subjects relapsed (seven consecutive days of smoking) after the quit date, a second quit date coinciding with a future clinic visit was allowed between time of relapse and week 18. Cessation counseling (based on the USDHHS Clinical Practice Guidelines [17]) for the first quit attempt involved 5 standardized face-to-face sessions (≤10 minutes) and for the second quit attempt, a face-to-face session plus 2 post-quit telephone counseling sessions. Subjects were followed for 52 weeks after randomization and the first injection on Day 0 for a total of 21 visits. During the injection day, subjects remained at the study site for 30 to 60 minutes for observation and attended a visit 24 hours after each injection to assess side effects. Otherwise, visits ranged from weekly to bi-weekly and were less frequent after later injections. Subjects who failed to quit smoking on their TQDs were encouraged to remain in the study and continue to attempt to achieve abstinence. Subjects who terminated from the study were not replaced and presumed to be smokers. Institutional Review Board approval was obtained from all institutions involved in the study. A Data and Safety Monitoring Board (DSMB) met four times during the study.\n\nBODY.METHODS.INVESTIGATIONAL PRODUCT:\nThe active investigational product was purified 3'-aminomethylnicotine conjugated to P. aeruginosa r-exoprotein A. For the 200 and 400 μg/mL dose, each single-use syringe contained 3'-aminomethylnicotine conjugated to 200 or 400 μg rEPA, respectively, adsorbed to 1.2 mg aluminum hydroxide adjuvant (Alhydrogel 85) in 1 mL phosphate buffered saline (0.15 M NaCl, 0.002 M NaPO4, pH 7.2, 0.01% polysorbate 80; PBS). For the placebo dose, PBS with 1.2 mg Alhydrogel 85 was included in a 1 mL single-use syringe.\n\nBODY.METHODS.MEASURES:\nCigarette use was recorded daily on an electronic diary for 182 days, and then weekly for the remainder of the study. Exhaled CO and urine cotinine were measured at each study visit, except for visits within 24 hours of vaccination. Questionnaires were collected via electronic diary: Fagerström Test for Nicotine Dependence [18] (administered days 0, 210, 364), Minnesota Nicotine Withdrawal Scale [MNWS, 19] (administered weekly until Month 6) and data on other tobacco usage. Sera were collected for immunogenicity measurements at 16–17 time points (schedule-dependent) from baseline to week 52. Anti-nicotine antibody concentrations were measured using ELISA (Enzyme-linked Immunosorbent Assay) [12]. Subjects recorded standard local and systemic reactogenicity events for 7 days after each injection. All reactogenicity events were followed until resolution or study completion. Treatment emergent AEs were recorded until 4 weeks after the last dose, with the exception of SAEs, which were collected through week 52. Subjects were also periodically monitored at clinic visits for vital signs, weight, hematology, chemistry and urinalysis.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nThe Intent-to-Treat (ITT) population was used for evaluation of efficacy, safety and immunogenicity. The ITT population was defined as all subjects who were randomized to treatment. The primary endpoint was continuous smoking abstinence for a total of 8 weeks measured from the beginning of week 19 to the end of week 26 (determined from subject diaries confirmed by exhaled CO ≤8 ppm). The analysis for proof-of-concept stratified the active-treatment recipients into high (top 30% AUC from weeks 0 to 26) and low (bottom 70% AUC from weeks 0 to 26) Ab responders, regardless of treatment group. An a priori decision was made to establish the antibody cutoff between 50% and 25%. Top 30% by AUC group was selected as the largest group of high antibody responders between the 25% and 50% cutoffs that demonstrated statistical significance as compared to placebo. Smoking outcomes were compared between subjects with high Ab and pooled placebo recipients using logistic regression. Secondary aims of this study were to assess a) 7-day point prevalence abstinence at various times, CARs during 52 weeks and time to sustained abstinence defined as attaining 8 weeks of continuous abstinence at anytime prior to week 46 and maintaining continuous abstinence through 52 weeks; b) impact on compensatory smoking amongst non-abstainers; c) withdrawal symptoms and d) immunogenicity, efficacy and safety of administration of either 4 or 5 of the 200 and 400 μg doses. Secondary smoking cessation analyses used logistic regression for binary outcomes and Cox proportional hazards regression models and log-rank tests for time-to-sustained abstinence analyses. Mixed-effects repeated-measures analyses of the number of cigarettes smoked, CO and cotinine adjusted for baseline were utilized in assessing compensatory smoking among non-abstainers or in assessing withdrawal symptoms. Anti-nicotine Ab responses were summarized as GMC with 95% confidence intervals. Safety was assessed throughout this study primarily using reactogenicity and adverse events (AEs). Reactogenicity data for 7 days after each injection were tabulated, and the proportions of subjects with any post-vaccination reactogenicity, aggregated over all injections, among the five treatment groups were compared using the Generalized Cochran-Mantel-Haenszel test. When a subject dropped out of the study, they were assigned presumed to be smokers. Otherwise, all missing diary data related to cigarette use were imputed utilizing the Last Observation Carried Forward principle. No imputation was carried out for CO level. The missing serology data were imputed by first defining a set of injection windows for each schedule. The missing serology was imputed by using the next available measured serology in its corresponding window; if the next value was not available the value of the nearest previous time point in that window was used. The AUC for anti-nicotine Ab was calculated based on imputed data. For Ab values one week after the target quit date, the value at week 9 was used for Schedule 1 as sera were not collected at week 8.\n\n**Question:** Compared to placebo what was the result of low Ab group on Prolonged abstinence from smoking rates to 6 months?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
135
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on HOMA-B?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
139
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on HOMA-IR?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
183
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Endometrial thickness?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
101
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Fasting plasma glucose at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
94
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Routine resite of peripheral intravenous devices every 3 days did not reduce complications compared with clinically indicated resite: a randomised controlled trial\n\n ABSTRACT.BACKGROUND:\nPeripheral intravenous device (IVD) complications were traditionally thought to be reduced by limiting dwell time. Current recommendations are to resite IVDs by 96 hours with the exception of children and patients with poor veins. Recent evidence suggests routine resite is unnecessary, at least if devices are inserted by a specialised IV team. The aim of this study was to compare the impact of peripheral IVD 'routine resite' with 'removal on clinical indication' on IVD complications in a general hospital without an IV team.\n\nABSTRACT.METHODS:\nA randomised, controlled trial was conducted in a regional teaching hospital. After ethics approval, 362 patients (603 IVDs) were randomised to have IVDs replaced on clinical indication (185 patients) or routine change every 3 days (177 patients). IVDs were inserted and managed by the general hospital medical and nursing staff; there was no IV team. The primary endpoint was a composite of IVD complications: phlebitis, infiltration, occlusion, accidental removal, local infection, and device-related bloodstream infection.\n\nABSTRACT.RESULTS:\nIVD complication rates were 68 per 1,000 IVD days (clinically indicated) and 66 per 1,000 IVD days (routine replacement) (P = 0.86; HR 1.03; 95% CI, 0.74-1.43). Time to first complication per patient did not differ between groups (KM with log rank, P = 0.53). There were no local infections or IVD-related bloodstream infections in either group. IV therapy duration did not differ between groups (P = 0.22), but more (P = 0.004) IVDs were placed per patient in the routine replacement (mean, 1.8) than the clinical indication group (mean, 1.5), with significantly higher hospital costs per patient (P < 0.001).\n\nABSTRACT.CONCLUSIONS:\nResite on clinical indication would allow one in two patients to have a single cannula per course of IV treatment, as opposed to one in five patients managed with routine resite; overall complication rates appear similar. Clinically indicated resite would achieve savings in equipment, staff time and patient discomfort. There is growing evidence to support the extended use of peripheral IVDs with removal only on clinical indication.\n\nABSTRACT.REGISTRATION NUMBER:\nAustralian New Zealand Clinical Trials Registry (ANZCTR) Number ACTRN12608000421336.\n\nBODY.BACKGROUND:\nPeripheral intravenous device (IVD) insertion is the most commonly performed invasive procedure in hospitalised patients, with an estimated 150 million peripheral intravenous devices placed each year in North America alone [1]. IVDs are vital for delivery of hydration, medicines and nutrition but are not without complications. Serious adverse outcomes are fortunately rare, with IVD-related bloodstream infection reported in a recent meta-analysis of 110 studies to occur in 0.1% of devices and 0.5 per 1,000 device days [2]. IVD treatment is more frequently interrupted by phlebitis, an irritation of the vein characterised by pain, tenderness on palpation, erythema, warmth, swelling, induration or palpable cord (thrombosis) of the cannulated vein; diagnostic algorithms usually require two or more of these conditions [3-5]. Phlebitis is in almost all cases a biochemical reaction to the mechanical irritation by the presence of the IVD and associated infusate [3], although phlebitis symptoms such as erythema may be misperceived as indicative of an infection. In fact, there is not a high correlation between phlebitis and device infection, and the Centers for Disease Control (CDC) states that infection is rarely associated with peripheral, as opposed to central, venous devices [3,6,7]. Fluid infiltration or 'tissuing' of devices is another common IVD complication which may also reflect the inflammatory (phlebitic) response of the vein, rather than simple misplacement of the device tip [8]. Early cohort studies noted an association between increased device time in situ and phlebitis [9,10]. This association was responded to with policies for routine device removal. Recommended timelines for routine resite have been extended over the past three decades from 24, to 48, then to 72 hours. Currently, 72- to 96-hour resite is recommended to reduce phlebitis by the CDC's 2002 Guidelines for the Prevention of Intravascular Device Infection, with the exemption that this is not required in children or those with poor veins [7]. Such policies cause increased workload in hospitals, where the task of removing and replacing well-functioning IVDs generally falls to busy nursing and junior medical staff. In addition, few patients welcome the prospect of additional venipuncture. Despite the general clinical acceptance of routine IVD replacement as a phlebitis and infection prevention measure, it has not been supported by recent data. It may be that the risk of complications during the entire IVD treatment episode is similar, regardless of whether multiple short-dwell or fewer longer-dwell IVDs are used over this time. Three small (n = 47-60) randomised, controlled trials (RCTs) suggested routine replacement at 12, 24 or 48 hours may reduce phlebitis compared to resite on clinical indication, although a systematic review for the Swedish Council on Technology Assessment in Healthcare assessed these as low- to medium-quality studies providing 'limited scientific evidence' [11-14]. More recently, two well-conducted RCTs found no evidence of effect when comparing IVD replacement every 3 days with replacement only on clinical indication for medical and surgical inpatients [15,16]. The largest of these studies reported findings from 755 general medical and surgical patients with 1,428 IVDs and found a 5% difference in combined phlebitis and infiltration rates per patient (38% clinically indicated resite, 33% routine resite), suggesting a potential small clinical benefit of 3-day resite [15]. However, this difference was not statistically significant (RR 1.15; 95% CI, 0.95-1.40) and disappeared when overall cannulation time was considered (59.8/1,000 IVD days clinically indicated resite, 60.9/1,000 IVD days routine resite; RR 0.98; 95% CI 0.78-1.24) [15]. In addition, no clinically important or statistically significant differences were observed in the secondary endpoints of phlebitis, infiltration, occlusion, local infection or suspected bloodstream infection rates between study groups [15]. Another recent RCT in the 'hospital in the home' community setting also found no important clinical or statistically significant difference in phlebitis, occlusion or bloodstream infection rates in 316 patients when resite every 3 days was compared with clinically indicated resite [17]. A 2010 Cochrane Collaboration review concluded there was 'no conclusive evidence of benefit' of routine IVD resite and suggested organisations could consider adopting a resite on clinical indication policy [18]. There is growing evidence that routine IVD replacement may be ineffective, although caution has been urged in light of the large number (74% in both groups in the largest study to date) of reported devices inserted by a specialised IV team, a factor known to reduce complications [19]. Device insertion (and reinsertion) is unpleasant for patients, requires skilled and available clinical staff, and has associated costs for the health sector. If replacement only on clinical indication is safe and effective, this would have important benefits for patients and the health system. We report a RCT of 3-day routine IVD resite versus clinically indicated replacement in a medical-surgical hospital where IVDs were inserted by the general medical and nursing staff; the insitution did not have a specialised IV service.\n\nBODY.METHODS.AIM:\nThe aim of the study was to compare the impact of 3-day routine resite, with clinically indicated resite, on peripheral IVD complications.\n\nBODY.METHODS.DESIGN:\nOpen (nonblinded), parallel group RCT.\n\nBODY.METHODS.ETHICS:\nThe study was approved by the Tasmanian State Human Research Ethics Committee. Written informed consent was obtained prospectively from all participants.\n\nBODY.METHODS.SETTING AND SAMPLE:\nThe study was undertaken at a large regional teaching hospital in Australia which functions as the tertiary referral centre for the northern half of the State of Tasmania. The hospital has more than 32,000 separations per annum, with a spectrum of medical and surgical specialties. Eligible patients were at least 18 years of age and scheduled or expected to have a peripheral IVD indwelling for at least 4 days, and they gave written informed consent. Exclusion criteria were immunosuppression, current bloodstream infection or an IVD already in situ for >48 hours. IVDs were inserted and cared for by the general nursing and medical staff; there was no special IV team or service.\n\nBODY.METHODS.SAMPLE SIZE:\nSample size calculations were performed using PASS 2008 (Version 8.0.8; Kaysville, UT) to detect a change in rates by 30% (from 36% to 25%, two-tailed α = 0.05, 90% power) on the basis of the complication rates of routinely resited IVs in a previous study [16]. Although this indicated that n = 378 per group (total 756) were required, the study was ceased early (total n = 606 IVs) because all investigators left the employment of the institution. Consequently, study power was reduced, but remained over 80% (required minimum n = 282 per group).\n\nBODY.METHODS.RECRUITMENT:\nAll adult patients admitted to the inpatient acute medical and surgical wards of the study hospital were screened by a full-time research nurse. This excluded paediatric, day-surgery, mental health, obstetric, critical care and dialysis units.\n\nBODY.METHODS.STUDY PROCEDURES:\nPatients were randomly assigned (computer generated) in a 1:1 allocation ratio to either the 'routine replacement' (control) or 'clinically indicated replacement' (intervention) group. Assignment was concealed until randomisation by use of a telephone service. A tag was placed on the insertion site indicating the study group. All devices for the patient were managed as per randomised group. The intervention group did not have their IVD resited unless clinically indicated. This decision was made by the treating clinician (not the investigators), who ordered IVD resite if the device failed or phlebitis occurred and ongoing IV treatment was required. The control group had a new device relocated to a different site by the general medical or nursing staff every 3 days. Control devices could also be removed at any stage by the clinical staff if they were not required or if complications occurred. Clinical nursing and medical staff undertook insertion and follow-up care of all IVDs as per the CDC Guidelines [7]. Laboratory staff undertaking microbiological culture assessments were blinded to the study group. Due to the nature of the intervention, patients, research, and clinical staff were unable to be blinded. However, the investigators had no involvement in assessing or documenting complications. IVDs were assessed by the clinical nursing staff on each nursing shift for complications as part of standard clinical practice in the hospital. Times and dates of device insertion and removal were recorded along with the reason for device removal and any protocol deviations. A full-time research nurse collected data from the hospital chart and sought clarification from patients and clinical staff if necessary. Microbiological investigations (device tip, blood cultures and site cultures) were performed by the clinical staff on clinical suspicion of infection by the treating clinician. Demographic and clinical data were collected on age, sex, diagnosis at hospital admission, phlebitis risk based on Tagar et al.'s classification (low/medium/high risk) [20], past history of phlebitis, any comorbidities requiring active medical treatment (e.g., type 2 diabetes or congestive heart failure), haemoglobin, concurrent infection at other sites, antibiotic therapy, type of surgery, type of infusate and any additives (and their level of irritability), vein and skin quality assessment, size of device, insertion site, health professional inserting the device, and setting for insertion, presence of other vascular devices, wound drains and urinary catheters. Vein quality was assessed as good (vein easy to visualise and easy to palpate with tourniquet on), fair (not easily visible but can palpate with tourniquet), or poor (veins small, scarred or difficult to palpate with tourniquet; may require heat pack to aid vasodilation). Skin quality was assessed as good (healthy, well hydrated, elastic), fair (mildly dehydrated, reduced elasticity), or poor (papery, dehydrated, or reduced elasticity).\n\nBODY.METHODS.ANALYTIC APPROACH:\nThe primary outcome was a composite measure of any complication causing unplanned cannula removal prior to completion of IV treatment. The composite included phlebitis, infiltration, occlusion, accidental removal, local infection, and IV device-related bloodstream infection (IVD-BSI). These were also analysed individually as secondary endpoints. A composite measure was chosen due to the low rates of these conditions individually and to the assumption that they are comparable measures of 'infusion failure'; that is, the device can no longer be used to deliver treatment. This approach has been used in previous studies on the topic [15-17]. Phlebitis was defined as two or more of pain, erythema, purulence, streak formation, or a palpable venous cord [3]. Local infection IVD-BSI (bacteremia/fungemia with at least one positive blood culture obtained from a peripheral vein, clinical manifestations of infection, and no apparent source for the bloodstream infection (BSI) except the device with or without positive tip or entry site swab culture) were defined using CDC criteria [7]. Other secondary outcomes were time in situ (hours of catheterisation from insertion to removal, both per patient and per device) [7]; IVDs per patient (number of peripheral devices inserted to complete the course of treatment) [7]; costs (calculations based on 20 minutes nursing or medical insertion time at relevant rates [15], plus the cost of the required equipment (cannula, insertion pack including dressing and solution, gloves, saline, syringe, extension tubing and starter pack for all plus fluid bag, tubing and secondary tubing for medication administration for those patients requiring this) for insertions, nursing time and equipment to routinely remove IVDs that were otherwise functional, and the costs of treating any complications that occurred (e.g., IVD-BSI). Cost calculations were undertaken from the viewpoint of the hospital using negotiated wage costs and purchasing agreements for government hospitals in the State of Tasmania. Costs would be similar for other Australian hospitals. All randomised patients were analysed by intention to treat. Each patient was randomised once and could have multiple IVDs, with subsequent IVD resites managed as per the randomised group. Relative incidence complication rates per 1,000 IVD days and 95% confidence intervals were calculated to summarise the impact of clinically indicated replacement relative to 3-day replacement. Kaplan-Meier survival curves were drawn to compare time to first IVD complication between patients in the two study groups. To assess for any potential impact of protocol violations, a per protocol analysis was also undertaken. All clinical and demographic variables were subjected to univariate testing against the primary endpoint to guide selection of possible covariates for the multivariable model. Cox proportional hazards regression modelling was used to examine the impact of age, gender, oncology status, number of comorbidities (nil, one, two, or more than two), IV gauge, site, vein quality, skin quality, oral antibiotics, IV antibiotics, wound drain, inserter occupation, initial versus subsequent IVDs, phlebitis in a preceeding IVD, haemoglobin level, parenteral nutrition, continuous versus intermittent infusion, patient risk category and study group on the outcome of time to complication events using an additive model [3,5,7,20-25]. In addition, to adjust for any inherent correlations or codependencies in the failure times of IVDs (i.e., same patient multiple failure-time data) within the Cox model, we also used the Prentice-Williams-Peterson conditional risk-set method [26]. The Mann-Whitney test was used to compare various secondary outcomes between study groups. Cost differences were calculated using arithmetic means and the t-test [27]. P values <0.05 were considered significant. All statistical data were entered and analysed using SPSS (Version 15.0; Chicago, IL) and Stata (Version 8.2; College Station, TX).\n\nBODY.RESULTS.SAMPLE:\nOver a 10-month period, 1,954 patients were screened for eligibility. Of these, 788 were eligible, with 362 (46%) recruited into the study. The most frequent exclusion criterion was altered mental state that precluded consideration of consent as assessed by the research nurse. Altered mental state was generally related to older medical patients and the immediate postoperative phase for surgical patients. Reasons for exclusion are shown in Figure 1. The 362 patients were randomised into either the routine change group (n = 177 participants, 323 devices) or the clinically indicated replacement group (n = 185 participants, 280 devices). In total 50,173 IVD hours were studied (routine change group 23,288 hours, clinically indicated group 26,885 hours). More patients in the routine change group had an active infection (53% vs. 44%) and were receiving IV antibiotics (73% vs. 64%). However, as shown in Tables 1 and 2, the two groups were generally comparable at baseline for patient- and cannula-related factors. Figure 1Participant flowchart. Table 1 Baseline characteristics of study participants Variable 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) Sex - Male, n (%) 96 (54%) 103 (56%) Age, mean (SD) 65.1 (17.3) 62.7 (15.4) Reason for admission, n (%) • Gastrointestinal 46 (26%) 52 (28%) • Respiratory 37 (21%) 34 (18%) • Oncology 21 (12%) 21 (11%) • Orthopaedic 16 (9%) 22 (12%) • Cardiac 10 (6%) 10 (5%) • Neurological 9 (5%) 10 (5%) • Vascular 7 (4%) 7 (4%) • Renal 16 (9%) 9 (5%) • Other 15 (8%) 20 (11%) Number of comorbidities, n (%) • None 6 (3.4%) 10 (5.4%) • 1 22 (12.4%) 21 (11.4%) • 2 44 (24.9%) 54 (29.2%) • >2 105 (59.3%) 100 (54.1%) Type of surgery, n (%) • Nil 124 (70%) 132 (71%) • Gastrointestinal 22 (12%) 22 (12%) • Orthopaedic 8 (5%) 15 (8%) • Other 23 (13%) 16 (9%) Most recent Hb - Mean (SD) 124.8 (23.2) 126.2 (21.9) Table 2 Baseline infusion-related characteristics of study devices Variable 3-Day Routine Change Group (n = 323) , n (%) Clinically Indicated Change Group (n = 280) , n (%) IV cannula gauge • 22 43 (13%) 46 (16%) • 20 241 (75%) 201 (72%) • 18 27 (12%) 30 (11%) • Other 2 (1%) 3 (1%) Vein assessment • Good 143 (44.3%) 107 (38.2%) • Fair 160 (49.5%) 144 (51.4%) • Poor 20 (6.2%) 29 (10.4%) Skin integrity • Good 138 (43%) 104 (37%) • Fair 178 (55%) 164 (59%) • Poor 7 (2%) 12 (4%) Past history of phlebitis 2 (0.6%) 4 (1.4%) Insertion site • Hand 206 (64%) 187 (67%) • Forearm 59 (18%) 49 (18%) • Cubital fossa 51 (16%) 38 (14%) • Other 7 (2%) 6 (2%) Receiving infusate 241 (75%) 215 (77%) pH of infusate - Mean (SD) 6.0 (0.5) 6.0 (0.4) Receiving oral antibiotics 24 (7%) 24 (9%) Receiving IV antibiotics 236 (73%) 176 (63%) pH of IV antibiotics - Mean (SD) 6.9 (1.1) 6.9 (1.3) Receiving other IV meds 190 (59%) 179 (64%) pH of other IV meds - Mean (SD) 5.6 (2.6) 6.0 (2.8) Wound drain 50 (16%) 40 (14%) Urinary catheter 55 (17%) 41 (15%) Other vascular device 26 (8%) 24 (9%) Inserted by • Junior doctor 232 (72%) 207 (74%) • Registered Nurse 67 (21%) 57 (20%) • Senior doctor 24 (7%) 16 (6%) Where inserted • Ward 216 (67%) 188 (67%) • Emergency department 74 (23%) 70 (25%) • Other 33 (10%) 22 (8%) Current infection (site) • Respiratory 97 (30%) 49 (18%) • Urinary 24 (7%) 19 (7%) • Wound 16 (5%) 15 (5%) • Other 29 (9%) 37 (13%) • >1 site 5 (2%) 4 (1%) N/A (none) 152 (47%) 156 (56%) Risk of phlebitis (Tagar scale) • Low 174 (54%) 144 (51%) • Medium 149 (46%) 136 (49%) • High 0 0 \n\nBODY.RESULTS.EFFECT OF INTERVENTION ON PRIMARY OUTCOME:\nOutcome data were available for all patients. Table 3 shows the rates of primary and secondary outcomes. Differences in complication rates between groups were not significantly different (routine replacement 66.0 per 1,000 IVD days; clinical replacement 67.8 per 1,000 IVD days; HR 1.03; 95% CI, 0.74-1.43; P = 0.86). As shown in Figure 2, the time to first complication per patient was also not significantly different between groups (Kaplan Meier [KM] with log rank P = 0.53). On crude rate per IVD, the catheters replaced on clinical indication had higher complication rates (110/280 or 39% vs. 91/323 or 28%; P = 0.004). However, total complication rates per patient (to deliver the course of IV therapy) were not significantly different (P = 0.39) between clinically indicated (76/185, 41%) and routine resite patients (64/177, 36%). Table 3 Effect of intervention on primary and secondary endpoints Outcomes 3-Day Routine Change Group (n = 177) Clinically Indicated Change Group (n = 185) RR (95% CI) , P Value Primary: IVD complications per patient, n (%) 64 (36%) 76 (41%) RR 1.14 (0.88, 1.47), p = 0.39 IVD complications per 1000 IVD days 66.0 (95% CI 49.8, 82.1) 67.8 (95% CI 52.6, 83.1) HR 1.03 (0.74, 1.43), p = 0.86 Secondary: Phlebitis, n (%) 12 (7%) 18 (10%) RR 1.44 (0.71, 2.89), p = 0.34 Infiltration, n (%) 53 (30%) 61 (33%) RR 1.10 (0.81, 1.49), p = 0.57 Occlusion, n (%) 5 (3%) 4 (2%) RR 0.77 (0.21, 2.80), p = 0.75 Accidental removal, n (%) 11 (6%) 16 (9%) RR 1.39 (0.66, 2.92), p = 0.43 Local infection 0 0 - IVD-related BSI, n (%) 0 0 - IVD costs per patient, AUD$ mean (SD) $55.42 ($35.26) $43.35 ($26.78) Mean difference $12.07 (95%CI $5.57, $18.56), p < 0.001 Figure 2Kaplan-Meier survival curve of time to first intravenous device complication per patient (log rank, P = 0.53). Patient- and device-related variables considered in the multivariable model were older age, number of comorbidities (nil, one, two or more than two), smaller cannula size, poor skin or vein integrity, IV antibiotics, insertion by medical staff and study group. None of these were found to be statistically significant. The final Cox proportional hazards model after adjusting for time found study group was not a significant factor (HR 1.02; 95% CI, 0.77-1.36; P = 0.89). Variance-adjustment testing for potential multiple-failures per patient (cannula data) found no inconsistency in significant results compared to the main Cox model.\n\nBODY.RESULTS.PROTOCOL COMPLIANCE:\nCompliance with the study intervention was achieved in 78% (251 of 323) of routinely replaced IVDs removed at Day 3 and 100% (280 of 280) of IVDs resited on clinical indication. Noncompliance in the routine resite group was generally related to high staff workloads on that day or to staff's perception that the patient was soon to be discharged or have therapy completed, and so the IVD remained in situ beyond Day 3. A per protocol analysis was performed including only those patients in the routine replacement group whose IVDs were all actually removed by 96 hours (n = 251). This found no significant difference (KM with log rank P = 0.16) in the rate of complications between groups (routine replacement 92 per 1,000 IVD days vs. clinically indicated 68 per 1,000 IVD days).\n\nBODY.RESULTS.EFFECT OF INTERVENTION ON SECONDARY OUTCOMES:\nThere was no statistically significant difference in group outcomes for any phlebitis (P = 0.34), infiltration (P = 0.57), occlusion (P = 0.75), or accidental removal (P = 0.43). No cases of local infection or IVD-related bloodstream infection occurred in either group. For overall IVD therapy (total cannulation time per patient for all devices), clinically indicated devices had a median therapy of 120 hours (quartiles 86.5 and 172.5 hours), and those replaced routinely had median therapy of 113 hours (quartiles 72 and 172 hours) (P = 0.21). For individual IVD dwell times, the clinically indicated group devices had a median dwell time of 85 hours (quartiles 51 and 121 hours), and those replaced routinely had a median dwell time of 71 hours (quartiles 48 and 90 hours) (P < 0.001). The maximum IVD dwell time was 1,023 hours (43 days) in the clinical replacement group, and this cannula was still working well on removal for completion of therapy. The overall number of IVDs per patient was significantly less (P = 0.004) for those replaced on clinical indication (mean 1.5, SD 0.8, median 1, quartiles 1 and 2) than for those routinely replaced (mean 1.8, SD 1.1, median 1, quartiles 1 and 2). A total of 22% of patients in the routinely replaced group had three or more IVDs compared with 9% in the clinical indication group. A total of 82 (28%) IVDs in the routine replacement group were resited after 3 days despite functioning well and ongoing treatment being required. (The remainder removed at this time were no longer required and so not resited, or infusion failure had already occurred.) Mean hospital costs per patient for the course of IV therapy were significantly higher (P < 0.001) for those managed with routine resite (mean $55.42, SD $35.26) compared with resite on clinical indication (mean $43.35, SD $26.78).\n\nBODY.DISCUSSION:\nThe finding that 3-day routine resite was not an effective intervention was consistent across the intention-to-treat primary analysis and the per protocol analysis. There remained no effect when events were expressed per patient or per 1,000 IVD days. Neither composite nor individual complication rates differed between groups, and there were no cases of local or device-related bloodstream infection. It appears safe and practical to leave IVDs in situ as long as they are functioning well and are still needed for clinical treatments. All IVDs will fail eventually, but this study shows that artificially shortening the lifespan of individual catheters does not reduce the overall complication rates over the course of therapy. Our results indicate that the average duration of IV therapy is 5-6 days and that many catheters can remain complication-free for this period. If catheters are not routinely resited, the median dwell time would remain within the 72-96 hours recommended by the CDC, but about 10% would remain in situ for longer (in this study up to 43 days with no complications). Our data show that a policy of resite on clinical indication would mean that one of every two patients would need a single cannula to receive treatment, whereas a 3-day change policy would result in only one in five patients having this scenario, with the rest requiring multiple cannulations and therefore additional pain and inconvenience. The results are consistent with the findings of recent RCTs in both hospitals and the community that have found no benefit in routinely resiting IVDs every 3 days [15-17]. In these studies, many cannulae were inserted by an expert IVD team [15-17], which may have minimised complications in both groups [19]. Our study confirms and extends these findings into the general medical/surgical setting without an IV team where IVDs were inserted by a variety of nursing and medical staff. Data from this study were included in a 2010 Cochrane Collaboration systematic review and meta-analysis on the topic [18]. This review included six trials (n = 3,455) and reported no clinically important or statistically significant difference in catheter-related bloodstream infection or phlebitis between IVDs that were routinely resited (at 48-96 hours) or resited on clinical indication, yet there were significantly lower costs in the group resited on clinical indication [18]. The belief that routine resite of IVDs will prevent complications appears to stem from early observational studies that noted longer-dwelling IVDs had more complications than shorter-dwelling IVDs [9,10]. This is intuitively true, given, for example, that an IVD in situ for 6 days has twice the time exposure of risk than an IVD in situ for 3 days. However, this does not prove that two sequentially inserted IVDs (in the same patient), both used for 3 days, have a combined lower risk over time than the 6-day dwell device. Indeed, this and other recent trials strongly suggest that the risk for the patient over the 6-day period is similar. Well-designed cohort studies with modern catheter materials suggest that the daily risk of phlebitis is relatively stable after the first 24 or 48 hours [3,21,28-31]. The peak in phlebitis between 24 and 48 hours is likely associated with the time taken by the body to mount a biological response after the instigation of therapy; those most likely to develop phlebitis will do so at this time. The results support the extension of the use of peripheral IVDs beyond the 72-96 hours currently recommended by the CDC [7]. There is incongruity in the CDC recommendations; they recommend not to routinely resite IVDs in children or in those with limited venous access. If it is safe in these populations, it is unclear why it would be necessary to routinely resite adults or those with better veins. Higher-risk cannulae such as central venous devices are no longer recommended by the CDC for routine replacement, because trials showed this was not of benefit [7]. Our study also confirms that the CDC guidelines are not always complied with; one fifth of IVDs in the routine change group were not replaced by this time. However, the per protocol analysis showed that the intervention remained ineffective even for those who truly had their IVDs resited every 3 days. Limitations of the study included a 9% higher frequency of IV antibiotics and concurrent infection in the routine resite group. This may have put the group at higher risk due to vein irritation, or conversely it protected against bacterial entry. Neither variable was significant in the multivariable model. The unblinded study design was unavoidable, but also a limitation. Our use of clear outcome measures, a full-time research nurse and laboratory staff blinded to culture assessments should have reduced the risk for potential bias. Resource constraints prematurely ended recruitment, thus reducing the anticipated power of the study from 90% to 80%. Routine IVD resite involves pain for patients, staff procedural time, equipment costs and environmental waste. Contemporary evidence suggests the current policy for routine resite by 72-96 hours is ineffective and should be replaced with a 'resite on clinical indication' policy. It remains imperative that clinical staff monitor IVDs closely and that a daily review of the need for continuing therapy be made, with cessation as soon as possible; the only no-risk IVD is no IVD. Of the 4.3 million acute hospital admissions in Australia each year (excluding day cases), over half have IV treatment [15,32]. Conservatively, if even 2 million courses of IV therapy were managed with clinically indicated rather than routine resite, this would save the unnecessary insertion of approximately 660,000 IVDs and free 280,000 hours of staff insertion time. Assuming our costs are similar to those in other Australian hospitals, a change to resite on clinical indication would save approximately AUD$24 million nationally each year.\n\nBODY.CONCLUSIONS:\nAlthough larger, multisite trials are required, evidence to date suggests that routine resite of peripheral IVDs increases patient discomfort and healthcare costs, but does not reduce IVD complications as has traditionally been thought.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nCMR designed the study, applied for funding and drafted the manuscript. DM participated in study design and manuscript preparation, and managed the study. JM recruited patients, ensured protocol integrity and collected data. MRM undertook statistical analyses and assisted with drafting the manuscript. All authors read and approved the final manuscript.\n\nBODY.AUTHORS' INFORMATION:\nCMR, PhD is Professor, Research Centre for Clinical and Community Practice Innovation, Griffith University, Australia. DM holds a Masters by Research and is Senior Lecturer, University of Tasmania, Australia. JM is an RN and Nurse Unit Manager, Calvary Tasmania, Australia. MRM is a PhD qualified Biostatistician, Gippsland Medical School, Monash University, Australia.\n\nBODY.PRE-PUBLICATION HISTORY:\nThe pre-publication history for this paper can be accessed here: http://www.biomedcentral.com/1741-7015/8/53/prepub\n\n**Question:** Compared to staff inclination replacement what was the result of routine replacement on occlusion?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
99
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on HbA1c level at 26 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
144
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Reductions in systolic blood pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
189
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Pain estimates after surgery?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
160
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on Late Life Function and Disability Instrument?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
145
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on Decreases in diastolic blood pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
147
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (all doses) plus glimepiride on Pulse variations?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
155
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Manually-assisted body-weight supported treadmill training what was the result of Body-weight supported treadmill training combined with Lokomat on Self-selected overground walk velocity?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
117
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Fasting plasma glucose at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
143
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Reductions in systolic blood pressure?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
166
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Trends in Use of Referral Hospital Services for Care of Sick Newborns in a Community-based Intervention in Tangail District, Bangladesh\n\n ABSTRACT:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district), Tangail district, Bangladesh, is promoting care-seeking for sick newborns through health education of families, identification and referral of sick newborns in the community by community health workers (CHWs), and strengthening of neonatal care in Kumudini Hospital, Mirzapur. Data were drawn from records maintained by the CHWs, referral hospital registers, a baseline household survey of recently-delivered women conducted from March to June 2003, and two interim household surveys in January and September 2005. Increases were observed in self-referral of sick newborns for care, compliance after referral by the CHWs, and care-seeking from qualified providers and from the Kumudini Hospital, and decreases were observed in care-seeking from unqualified providers in the intervention arm. An active surveillance for illness by the CHWs in the home, education of families by them on recognition of danger signs and counselling to seek immediate care for serious illness, and improved linkages between the community and the hospital can produce substantial increases in care-seeking for sick newborns.\n\nBODY.INTRODUCTION:\nThe timely and appropriate use of health services is crucial to reduce maternal and child mortality (1–4). Many lifesaving interventions, such as caesarean section, blood transfusion, oxygen, and intravenous antibiotics, can only be made available through health facilities. Evidence suggests that bringing women and children to facilities to receive these services is associated with reductions in mortality (1, 4). Countries that have achieved high rates of deliveries in facilities for basic or comprehensive essential obstetric care have witnessed significant and sustained decreases in maternal mortality (4), while countries, such as Sri Lanka, with elevated rates of care-seeking for sick children, have much lower rates of mortality among children aged less than five years (under-five mortality) than would be predicted from their per-capita income (1). Numerous studies have examined community-based interventions to improve care-seeking and referral for maternal emergencies from the community to first- and second-level facilities (3–8). Murray and Pearson have recently published a systematic review and proposed a research agendum to identify how programmes can better promote timely and appropriate maternal referral (9). Sibley has reviewed the effectiveness of traditional birth attendants (TBAs) in promoting referral from the community to facilities offering emergency obstetric care (10). Much less is known about referral of sick newborns from the community to health facilities. While several studies have examined referral of children, aged less than five-years, from first-level to second-level facilities (11–13), few studies have specifically examined referral from the community to facilities (14), and even less is known about referral of newborns from the community to facilities. Many factors affecting referral and care-seeking for maternal conditions from the community to health facilities could be applicable to promoting care for sick newborns. First, there is a need to act rapidly for certain maternal and newborn conditions, such as severe postpartum haemorrhage and birth asphyxia. So, research needs to examine not only recognition of danger signs, but also how long it takes for recognition of the problem to occur. The constraints on rapid action by families, such as distance, poor conditions of road, lack of transport, and lack of money, are common to both. Macintyre and Hotchkiss have developed a conceptual framework of factors at the individual, household, and community levels affecting referral in Africa which is equally applicable to other regions of the world (15). Second, in both mothers and newborns, many important causes of morbidity and mortality have signs and symptoms that \"lie on a continuum, from normal to abnormal\" (16). For such signs and symptoms, there can be both over-reporting of non-serious conditions, such as transient tachypnoea of the newborn or upper respiratory viral infection, or under-reporting of truly serious conditions, as happens when families fail to recognize excessive loss of maternal blood after delivery (16). Finally, patterns of decision-making within the household may lead to a significant delay, especially when permission of the husband is needed before seeking care but he is away, or when it is not clear to the family where to seek care from among a range of formal and informal sector providers (17–19). While there is much to learn from previous research on care-seeking and referral for older children, there are also obstacles to promoting early and appropriate care that are specific to newborns. In many cultures, families practise a period of postpartum confinement of both mother and newborn lasting from one to six week(s) or more (20). Additional efforts may be needed during this period to convince families to seek care outside the home. Sometimes, it is also difficult to detect danger signs in sick newborns, and families may not understand the significance of signs, such as hypothermia, feeding problems, or lethargy (21). This paper describes the trends in compliance by families with referrals when sick newborns were identified by community health workers (CHWs) and were referred to the Kumudini Hospital for care. In this project, families are educated about danger signs, and the CHWs visit the home during the postpartum period and examine newborns for any signs indicating the need for urgent medical care. Actions to increase the rate of compliance with referrals and their effects are also described.\n\nBODY.MATERIALS AND METHODS.STUDY SITE:\nThe Projahnmo-II Project in Mirzapur upazila (sub-district) of Tangail district in central Bangladesh is implementing an intervention aimed at improving maternal and newborn-care practices and care-seeking for maternal and newborn conditions through: (a) behaviour change communication, (b) identification and referral of sick newborns in the community, and (c) strengthening of neonatal care in health facilities. The cluster-randomized trial has two arms: an intervention arm with CHWs delivering a package of maternal and newborn-care interventions in the home and a comparison arm. Mirzapur upazila has 13 unions, with a population of around 24,000 each; of these, six were randomly allocated to each study arm, excluding the one urban union. Given the need to have sick neonates assessed and treated in the hospital to identify aetiology of infections, a major focus of the problem is to identify barriers to care-seeking and design of strategies to address those barriers. The Kumudini Hospital, a 750-bed private hospital run by the Kumudini Welfare Trust, is situated at the centre of the project area. The hospital has a large paediatric unit (total 65 beds, including one separate neonatal ward) with two full-time consultants and 7–8 regular physicians.\n\nBODY.MATERIALS AND METHODS.DESCRIPTION OF THE INTERVENTION MODEL:\nIn the Projahnmo-II project, 36 CHWs were recruited and provided one month of initial training to equip them to provide a package of maternal and newborn care. These CHWs had a minimum of 10th grade education and resided in the population they would serve. Each CHW was responsible for about 4,000 people. The CHWs carried out bi-monthly pregnancy surveillance and registration of married women of reproductive age (MWRA) and made home-visits in the third and the eighth month of pregnancy to counsel families on birth and neonatal care preparedness (BNCP). After delivery, the CHWs made home-visits to promote evidence-based domiciliary newborn care and to identify and refer sick newborns and mothers on day 0 (day of birth), 3, 6, and 9. Improvements were made in maternal and neonatal healthcare at the designated referral facility (Kumudini Hospital), and the CHWs facilitated referrals of sick newborns they identified during home-visits to this hospital. For families that refused referral and for babies who had at least one danger sign of very severe disease, or any two from possible very severe disease, the CHWs carried out home-treatment of cases with suspected serious infection with oral co-trimoxazole. The Field Supervisors supervised the daily activities of CHWs in the community and also reviewed the key performance and process indicators relating to coverage and quality every fortnight and provided feedback to the CHWs. Figure 1 is a model that shows how the intervention package helps promote hospital care for sick newborns. During the antenatal period, families were educated about signs indicating the need to seek care and sources of care by health workers during antenatal care visits at health facilities and by CHWs during antenatal home-visits (left side of Fig. 1). This should lead to an increased recognition by families of danger signs in newborns. This, in turn, should lead them either to seek care directly (self-referral) from the Kumudini Hospital and other appropriate sources of care, or notify the CHW to come to the house and assess the child. The CHW may also come in contact with a sick newborn during the course of her routine postnatal home-visits, and all findings are recorded in a Visit Record Form (VRF). The criteria for referral of sick newborns are: (a) in the case of birth asphyxia: if breathing difficulty continues 20 minutes after birth despite resuscitation efforts; (b) if there is one or more signs/symptoms of very severe disease, such as fever or lethargy; (c) jaundice—any where in the body within 24 hours of birth; (d) eyes discharging pus (possible gonococcal eye infection); and/or (e) diarrhoea with blood in stool and/or dehydration. Fig. 1.Intervention model: promotion by community health workers of care for sick newborns at Kumudini Hospital between April 2004 and September 2005 (Table 1) Dotted arrow indicates action not anticipated in the intervention model\n*Coverage estimates from the second adequacy survey, September 2005\nSources of data: Project management information system (records maintained by CHWs and hospital registers) and household survey (second adequacy survey in September 2005)\nANC=Antenatal care;\nBNCP=Birth and neonatal care preparedness;\nCHWs=Community health workers A standard algorithm adapted from integrated management of childhood illness (IMCI) for use in the community by the CHWs is followed to assess and classify sickness in newborns. If the newborn requires referral, the CHW facilitates referral to the Kumudini Hospital. The community-based system of facilitated referral was in place by 19 February 2004 and initially consisted of the following elements, in addition to home-visits by the CHWs: (a) referral slips for the CHWs to fill in when referring a sick newborn to the hospital; (b) Birth and Neonatal Care Preparedness (BNCP) Cards, with an identification number, are supplied to families during antenatal home-visits by the CHWs. Families can carry the BNCP Card with them to the Kumudini Hospital in the event that the CHW is not available to issue a referral slip to the family when the newborn falls ill; (c) a referral-tracking form; (d) free inpatient care at the Kumudini Hospital for newborns arriving with a referral slip; (e) a system of emergency transport; and (f) training of TBAs, so that they could also promote referral to hospital for newborns with danger signs. If referral to the Kumudini Hospital fails, additional follow-up visits in the home are made to follow the condition of the child and treat presumptively with antibiotics, if appropriate. The CHW makes a final visit—called a graduation visit—as soon as the baby crosses 28 days of life. At that time, the completed VRF goes to the Mirzapur field office for review and is then sent to the main project office in Dhaka for data entry and further review.\n\nBODY.MATERIALS AND METHODS.MODIFICATIONS TO THE INTERVENTION MODEL:\nThe CHWs helped families to arrange transportation, convinced family members to have the newborn treated outside the home, and provided a transport allowance to the poorest families to reach the Kumudini Hospital. After three months of initial implementation of the programme, further changes were made to improve coverage with home-visits and compliance with referrals. A referral-tracking form was introduced in April 2004, and every two weeks, the number of newborns referred and the outcome of referral were reviewed in a meeting with the supervisors and CHWs. In early 2005, a decision was made to emphasize more the management and referral of birth asphyxia and low-birth-weight newborns. The CHWs started to use digital weighing machines in February 2005 to obtain the weight of the newborn at first contact. In April 2005, the CHWs received refresher training on how to counsel families during antenatal home-visits on low birth-weight and birth asphyxia.\n\nBODY.MATERIALS AND METHODS.MONITORING OF FUNCTIONING OF THE REFERRAL SYSTEM:\nData are presented from the project management information system (MIS) for the April 2004–September 2005 period, which includes the records maintained by the CHWs and registers maintained in the referral hospital (Kumudini Hospital). In addition, in-depth interviews were undertaken at baseline and during implementation to investigate the factors affecting compliance. Results of the interviews with parents appearing at the Kumudini Hospital and from those who did not comply with referral advice were shared with the CHWs and Field Supervisors to identify ways to improve counselling on referral.\n\nBODY.MATERIALS AND METHODS.SAMPLING AND SAMPLE SIZE:\nA baseline household survey among recently-delivered women was conducted in early 2003. Demographic and socioeconomic information of the listed households was collected, and information on birth-history and neonatal mortality was collected from all 14,526 women who had a pregnancy outcome in the 36 months preceding the survey. Information on knowledge, practices, and coverage of pregnancy, childbirth, and postpartum/postnatal care of mothers and newborns was collected from a randomly-selected sub-set of 4,611 recently-delivered women who had a pregnancy outcome in the last one year. Two interim household adequacy surveys were conducted in January and September 2005 to measure the adequacy of project inputs and selected process indicators to assess progress in early changes in behavioural patterns, including care-seeking. Identified through a systematic random-sampling method, in total, 1,200 women who had a pregnancy outcome in the last 7–8 months in each of the intervention and comparison arms were interviewed in each of the interim household surveys. Eighty-four randomly-selected parents arriving in the Outpatient Department of the Kumudini Hospital during January-June 2005 were asked why they had come to the hospital. Reasons for non-compliance with referral were analyzed on a continual basis and contributed to fine-tuning of the system of facilitated referral. Randomly-selected parents of 162 newborns who were referred for care but did not comply with referral during the same period mentioned above were interviewed regarding their reasons for non-compliance. Structured brief questionnaires were used in both instances.\n\nBODY.RESULTS.FUNCTIONING OF THE REFERRAL SYSTEM:\nResults of the second adequacy survey conducted in September 2005 showed that 72.5% of the recently-delivered women had attended at least one antenatal care visit, and 87.6% had received at least one antenatal BNCP visit by a CHW. Table 1 shows the trends between April 2004 and September 2005 in assessment, referral, and admission of sick newborns in the study intervention arm. Figure 1 presents data for the entire period. Although the project staff judged that the CHWs succeeded in identifying most pregnant women, the CHWs documented deliveries for only 3,354 (74.4%) of the 4,508 women estimated to have their due date during this period. The primary reason for this lower-than-expected figure was that significant numbers of women, particularly primigravidae, migrated at some point prior to delivery to live in another household located outside the intervention arm of the study. In most cases, they left the household of their husband's family (shashurbari) to reside in their natal home (baperbari), a phenomenon also observed in other sites in Bangladesh (20). Of 3,354 women who did not change residence, 3,228 (96.2%) received at least one home-visit by the CHW during the first 28 days of life of the baby. Table 1. Trends over time in assessment, referral, and admission of sick newborns in Mirzapur sub-district, Tangail district, Bangladesh between April 2004 and September 2005 (*indicates that figures are also displayed in Fig. 1 ) Variable and statistical assessment of trends Apr-Jun 2004 Jul-Sep 2004 Oct-Dec 2004 Jan-Mar 2005 Apr-Jun 2005 Jul-Sep 2005 Total Apr 2004-Sept 2005* Assessment and referral of sick newborns in the community by CHWs Home-deliveries 417 574 870 541 433 519 3,354* CHW-visit within first 28 days 324 443 862 659 436 504 3,228* Newborns assessed as sick 134 156 190 84 111 119 794* Referred to Kumudini Hospital 115 148 161 71 87 102 684* Percentage of sick newborns who were referred 85.8 94.9 84.7 84.5 78.4 85.7 86.1 Chi-square for linear trend=NS Arrival and admission at outpatient/emergency department of Kumudini Hospital Neonates reaching Kumudini Hospital OPD/emergency after self-referral or referral by CHWs 89 146 211 128 159 188 921* Neonates reaching Kumudini OPD/emergency after self-referral 25 55 82 75 95 111 443* Neonates reaching Kumudini Hospital OPD/emergency with CHW referral slip 64 91 129 53 64 77 478* Chi-square for linear trend=43.5, df=1, p<0.00001 71.9 62.3 61.1 41.4 40.3 41.0 51.9 Percentage of newborns referred by CHWs who arrived at Kumudini Hospital OPD/emergency 55.7 61.5 80.1 74.6 73.6 75.5 69.9 Chi-square for linear trend=12.97, df=1, p=0.00032 CHW=Community health worker; df=Degree of freedom; NS=Not significant; OPD=Outpatient department The CHWs identified 794 newborns as sick during this period, excluding newborns with feeding problems. Of these, 684 (86.1%) were referred by the CHWs to the Kumudini Hospital for care. The proportion of sick newborns who were referred stayed essentially constant between April 2004 and September 2005 (non-significant chi-square test for linear trend). Newborns arriving from households located in the intervention arm could either (a) have been referred by the CHW after she examined the child during a home-visit and issued a referral slip, or (b) the family could have taken the decision to seek care directly without first contacting the CHW, a situation we refer to as self-referral. Overall, of the 921 newborns arriving at the outpatient or emergency departments of the Kumudini Hospital during this period, 443 (48.1%) arrived after self-referral, and 478 (51.9%) arrived with a referral slip issued by the CHWs. The proportion of all cases who arrived with a referral slip declined continuously during this period (Row 8 of Table 1), from 71.9% at the beginning of implementation between April and June 2004 to 41.0% between July and September 2005, a trend which was highly significant (chi-square for linear trend=43.5, df=1, p<0.00001). Compliance with referral to the Kumudini Hospital by the CHWs increased from 55.7% during the first three-month period of implementation to 80.1% during the third three-month period of implementation (Row 9 of Table 1) and was thereafter maintained at 75–80%. The overall trend was significant (p=0.00032).\n\nBODY.RESULTS.INTERVIEWS ON FACTORS AFFECTING COMPLIANCE:\nEighty-four parents arriving in the Outpatient Department of the Kumudini Hospital were asked why they had come to the hospital. They mentioned (multiple responses allowed) that the CHWs advised them to visit the Kumudini Hospital because treatment was available (65.5%), treatment was of high quality (34.5%) and free of charge (21.4%), the hospital was the nearest one to their home (2.4%), and other reasons (4.8%). Parents of 162 newborns who were referred for care but did not comply with referral were interviewed. The reasons cited for non-compliance (multiple responses allowed) included: nobody was available to accompany the child (and the mother) to the health facility (24.7%); the child was given a traditional treatment instead (19.1%); bad weather or general strikes (17.9%); the family disliked hospital treatment (12.3%); symptoms resolved on their own (7.4%); unwillingness of the family or the TBA to refer the baby for other reasons (6.2%); and other issues (12.3%), such as illness of the mother; the child was too young to be taken for outside care; and lack of transport. Although distance was a commonly-cited reason for failure to seek care from the health facilities, the proportion of cases referred by the CHWs in the farthest unions in the intervention arm, Warsi (2 hours away), Ajgana (1.5 hours away), and Bahuria (1.5 hours away) were at approximately the same level (79.3%, 80.6%, and 82.7% respectively) as the closest unions that were 0.5 hours away from the Kumudini Hospital, Banail (87.9%), and Bhatgram (81.6%).\n\nBODY.RESULTS.EVALUATION OF TRENDS IN CARE-SEEKING:\nTable 2 demonstrates the changes in care-seeking/self-referral to the Kumudini Hospital and other providers between the baseline survey (January 2003) and the first (January 2005) and the second (September 2005) adequacy survey. Caution is necessary in assigning significance to the observed trends as the two adequacy surveys are based on much smaller samples than the baseline survey. At the time of the baseline household survey in January 2003, there was no significant difference between the intervention arm and the comparison arm of the study in the proportion of sick newborns who were taken outside the home for care from any qualified provider (including Kumudini Hospital), to the Kumudini Hospital specifically, or to an unqualified provider, most commonly an unlicensed 'village doctor'. Table 2. Trends in care-seeking for sick newborns from Kumudini Hospital and other providers based on population-based household surveys Measures of care-seeking Baseline survey: January 2003 First adequacy ssurvey: January 2005 Second adequacy survey: September 2005 Intervention arm Comparison arm Intervention arm Comparison arm Intervention arm Comparison arm Reported sickness among newborns in the sample Total number of newborns in the sample 2,053 2,290 523 550 520 548 Number of newborns reported to have been sick (%) 818 (37.5) 780 (37.6) 255 (48.8) 279 (50.7) 207 (39.8) 257 (46.9) Reported care-seeking outside home Proportion of sick newborns reported to have been given any care in or outside home 92.9 93.7 93.3 93.2 93.2 95.3 Proportion of sick newborns for whom care was sought from outside home 66.1 66.4 82.8 81.4 82.6 77.4 Reported care-seeking from qualified providers ( Fig. 2 ) Proportion of sick newborns for whom care was sought from qualified providers 31.2 29.6 55.7 38.4 60.4 33.9 Odds ratio for care from qualified providers, intervention vs comparison (95% CI) 1.08 (0.86–1.34) (p=0.499) 2.02 (1.41–2.90) (p<0.0001) 2.98 (2.00–4.44) (p<0.0001) Chi-square trend test for care from qualified providers, intervention group Chi-square for linear trend=80.13, df=1, p<0.00001 Chi-square trend test for care from qualified providers, comparison group Chi-square for linear trend=3.42, df=1, p=0.065 Reported care-seeking from Kumudini Hospital ( Fig. 3 ) Proportion of sick newborns for whom care was sought from Kumudini Hospital 17.9 17.6 42.0 21.9 46.4 23.0 Odds ratio for care from Kumudini Hospital, intervention vs comparison (95% CI) 1.02 (0.78–1.33) (p<0.882) 2.58 (1.74–3.84) (p<0.0001) 2.90 (1.91–4.41) (p<0.0001) Chi-square trend test for care from Kumudini Hospital, intervention Group Chi-square for linear trend=93.40, df=1, p<0.00001 Chi-square trend test for care from Kumudini Hospital, comparison Group Chi-square for linear trend=4.47, df=1, p=0.035 Reported care-seeking from unqualified providers ( Fig. 4 ) Proportion of sick newborns for whom care was sought from unqualified providers 66.7 67.9 49.8 66.0 36.7 65.0 Odds ratio for care from unqualified providers, intervention vs comparison (95% CI) 0.95 (0.76–1.17) (p<0.609) 0.51 (0.36–0.74) (p=0.0002) 0.31 (0.21–0.47) (p<0.0001) Chi-square trend test for care from unqualified providers, intervention group Chi-square for linear trend=71.01, df=1, p<0.00001 Chi-square trend test for care from unqualified providers, comparison group Chi-square for linear trend=0.90, df=1, p=0.34 CI=Confidence interval; df=Degree of freedom Between the time of the baseline and the first adequacy survey, there was a significant increase in care-seeking in both intervention and comparison arms of the study (Row 4 of Table 2). This difference could be due to both increased awareness of the newborn's health problems and/or changes in how the survey was administered. Figure 2 demonstrates that there was a highly significant (p<0.00001) increase in the proportion of families that sought care from qualified providers for sick newborns in the intervention arm (Fig. 2 and Rows 5 and 7 of Table 2) and a non-significant increase in the comparison arm (Rows 5 and 8). Figure 3 shows that care-seeking for sick newborns specifically from the Kumudini Hospital increased significantly in both intervention and comparison arms, but the increase was of a much greater magnitude in the intervention arm (Fig. 3 and Row 9–12 of Table 2). Finally, Figure 4 demonstrates that the proportion of families who sought care from unqualified providers, such as unlicensed village doctors, remained unchanged in the comparison arm, but declined significantly in the intervention arm (Fig. 4 and Row 13–16 of Table 2). Fig. 2.Trend in proportion of sick newborns for whom care was sought from qualified providers*p<0.0001; Chi-square for linear trend (intervention) 80.13 (p<0.00001)\nOR=Odds ration Fig. 3.Trend in proportion of sick newborns for whom care was sought from Kumudini Hospital*p<0.0001; Chi-square for linear trend (intervention) 93.4 (p<0.00001)\nOR=Odds ratio Fig. 4.Trend in proportion of sick newborns for whom care was sought from unqualified providers*p<0.0001; Chi-square for linear trend (intervention) 71.01 (p<0.00001)\nOR=Odds ratio\n\nBODY.DISCUSSION:\nSignificant reductions in neonatal mortality must be made to reach the Millennium Development Goal for under-five mortality. One key to reducing neonatal mortality is to ensure that sick newborns are assessed and treated quickly either in the home (22, 23) or in a health facility. Practices of postpartum confinement of mothers and newborns found in many cultures, difficulties in transport, and patterns of household decision-making are among the factors that can delay or prevent care-seeking outside the home. Data presented in this paper demonstrate that it is possible to achieve high rates of care-seeking from hospitals or other qualified providers and to significantly decrease care-seeking from unqualified providers, even in a low-income rural area where all these factors are present. The trends observed in the intervention arm included increased care-seeking, increased proportion of sick newborns arriving at the Kumudini Hospital after self-referral rather than referral by a CHW, increased compliance after referral by the CHWs, increased care-seeking from the qualified providers (Fig. 2) and from the Kumudini Hospital (Fig. 3), and decreases in care-seeking from the unqualified providers (Fig. 4). In the comparison arm, an increase in care-seeking from the Kumudini Hospital was also observed, but the proportions seeking care from the qualified and unqualified providers did not change significantly. Reasons for the increasing trend in the proportion of cases in the intervention arm arriving at the Kumudini Hospital after self-referral have not yet been fully elucidated, but include increasing awareness of the signs of illness in newborns and experience with the services offered by the Kumudini Hospital. There also appeared to be some cases where the CHWs judged that the newborns did not require referral, but the family decided to seek care from the Kumudini Hospital anyway. In a number of these cases, the child had physiologic jaundice, a condition which the family felt warranted further investigation, despite reassurances provided by the CHWs. The project investigators are currently investigating this situation further. Substantial increases in referral compliance for newborn illness were likely related to (a) education of families on danger signs by the CHWs; (b) active surveillance for illness by the CHWs during routine postnatal home-visits; (c) facilitated referral by the CHWs, including counselling, use of referral slips along with improved linkages between community and hospital; (d) incentives for labour/birth notification; (e) enhanced capacity at the referral-care centre to manage sick newborns; and (f) availability of subsidized treatment. Sustained community-level education enhanced the empowerment of families towards decision-making for self-referral. In low-income countries with high rates of neonatal mortality, sick newborns can either be treated presumptively in the home (22, 23) or referred to health facilities. This paper demonstrates that it is possible to achieve high rates of compliance with referral, but to do this requires an extensive infrastructure of CHWs or other community contact persons (8) to assess newborns and facilitate referrals. Alternatively, an increased emphasis could be placed on community mobilization, education on danger signs, and facilitation of self-referral, perhaps with similar results. This paper is one of the only studies to provide data on levels of referral compliance achieved through facilitated referral (12, 14). Whether the emphasis is on treatment in facilities or treatment in the community, substantial investments will need to be made in the creation of demand with the community, community and family education, and facilitation of referral.\n\nBODY.ACKNOWLEDGEMENTS:\nThis study was supported primarily through the generous support of the Infectious Disease Initiative of the Wellcome Trust–Burroughs Wellcome Fund. Additional support was provided by the Department for International Development (DFID), UK; the United States Agency for International Development, Office of Health, Infectious Diseases, and Nutrition, Global Bureau through the Global Research Activity Cooperative Agreement (No. GHS-A-00-03-00019-00); the Government of Bangladesh (Improved Health for the Poor); and Save the Children-USA through a grant from the Bill and Melinda Gates Foundation. The authors thank the study participants in Mirzapur upazila, Bangladesh, who were generous with their time and patience with interviewers through the several rounds of interviews.\n\n**Question:** Compared to Comparison arm what was the result of Promotion by CHWs of maternal and newborn-care interventions on Care-seeking from the Kumudini Hospital for ill newborns ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
111
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Patients reaching HbA1c goals less than 7.0% and equal or less than 6.5%?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
137
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on HOMA-B?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
114
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Liraglutide (1.2 mg) plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Patients reaching HbA1c goals less than 7.0% ?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
108
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (0.6 mg) plus glimepiride on HbA1c level at 26 weeks?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
128
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on ADA postprandial plasma glucose goals less than 10.0 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
193
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Is the operative delivery rate in low-risk women dependent on the level of birth care? A randomised controlled trial\n\n ABSTRACT.OBJECTIVE:\nTo investigate possible differences in operative delivery rate among low-risk women, randomised to an alongside midwifery-led unit or to standard obstetric units within the same hospital.\n\nABSTRACT.DESIGN:\nRandomised controlled trial.\n\nABSTRACT.SETTING:\nDepartment of Obstetrics and Gynaecology, Østfold Hospital Trust, Tromsø, Norway.\n\nABSTRACT.POPULATION:\nA total of 1111 women assessed to be at low risk at onset of spontaneous labour.\n\nABSTRACT.METHODS:\nRandomisation into one of three birth units: the special unit; the normal unit; or the midwife-led unit.\n\nABSTRACT.MAIN OUTCOME MEASURES:\nTotal operative delivery rate, augmentation, pain relief, postpartum haemorrhage, sphincter injuries and intrapartum transfer, Apgar score <7 at 5 minutes, metabolic acidosis and transfer to neonatal intensive care unit.\n\nABSTRACT.RESULTS:\nThere were no significant differences in total operative deliveries between the three units: 16.3% in the midwife-led unit; 18.0% in the normal unit; and 18.8% in the special unit. There were no significant differences in postpartum haemorrhage, sphincter injuries or in neonatal outcomes. There were statistically significant differences in augmentation (midwife-led unit versus normal unit RR 0.73, 95% CI 0.59–0.89; midwife-led unit versus special unit RR 0.69, 95% CI 0.56–0.86), in epidural analgesia (midwife-led unit versus normal unit RR 0.68, 95% CI 0.52–0.90; midwife-led unit versus special unit RR 0.64, 95% CI 0.47–0.86) and in acupuncture (midwife-led unit versus normal unit RR 1.45, 95% CI 1.25–1.69; midwife-led unit versus special unit RR 1.45, 95% CI 1.22–1.73).\n\nABSTRACT.CONCLUSIONS:\nThe level of birth care does not significantly affect the rate of operative deliveries in low-risk women without any expressed preference for level of birth care.\n\nBODY.INTRODUCTION:\nOver the last few decades there has been an increasing trend towards the centralisation of childbirth in larger clinics in developed countries. As the level of available obstetric technology increases, the use of this technology increases as well, leaving researchers to suggest that low-risk women may receive excess interventions.1–4 Intervention rates for low-risk births might be higher than necessary, and there are large variations in inter-unit comparisons.5 In their intrapartum care guidelines, the UK's National Institute for Health and Clinical Excellence concluded that if a low-risk woman plans to give birth in a midwife-led unit she will have a higher likelihood of a normal birth with less intervention.6 As a counterbalance towards the trend of increased perinatal intervention, low-risk birth units or birth centres have been established. Low-risk birth units can either be freestanding, i.e. localised away from a hospital, or sit alongside, i.e. integrated within a hospital. These units are most often midwife led. Transfer from a low-risk birth unit to a standard care birth unit or hospital is required if medical services are necessary. Freestanding birth centres have been studied in different settings, concluding that birth centres are a safe alternative to hospital for low-risk women.7 It is also shown that general practitioners and midwives can identify a low-risk population that can deliver safely at maternity homes, with a low rate of operative deliveries and transfers.8 Freestanding, midwife-led birth centres report higher rates of normal births and lower rates of caesarean sections and episiotomies.9 Alongside birth units have also been studied widely. The Stockholm birth centre trial concludes that birth centre care is associated with less medical interventions, without statistically significant differences in health outcome.10 A Cochrane review on the topic concludes that an alternative birth setting versus conventional institutional birth setting is associated with reduced rates of medical interventions and increased maternal satisfaction, but states that there might be an increased risk for perinatal mortality.11 According to Gottvall et al.,12 there is no statistically significant difference in perinatal mortality between birth centres and standard care. A systematic review on low-risk units concludes that birth centres can offer the possibility of accessible, appropriate and personal maternity care for women and their families, but points to a strong need for randomised trials.13 Hatem et al.14 conclude in a Cochrane review that women who had midwife-led care were less likely to experience operative delivery, with no statistically significant differences in fetal or neonatal death overall. Studies reporting results from low-risk units often include participants early in pregnancy.10,15–18 This implies that a certain number of women included do not fulfil the selection criteria for midwife-led units at onset of labour, and therefore do not attend these units at all in labour. Following the important principle of intention to treat, the participants are still analysed according to the group they were originally allocated to.Waldenstrøm and Nilsson10 state that among women randomised to the midwife-led unit, 34% were transferred antepartum and 16% were transferred intrapartum. In this trial we wanted to study the effect of birth unit on birth outcome for low-risk women, and inclusion was therefore conducted at the onset of spontaneous labour. When searching for similar trials including women at onset of labour conducted in the last 20 years, only two randomised controlled trials were found: one from the USA and one from Hong Kong.19,20 Earlier data from several standard care obstetric departments in Norway show an operative delivery rate (caesareans, vacuum extractions and forceps deliveries) amongst low-risk women of ≥10%.21 At freestanding midwife-led units the operative delivery rate for the same group is approximately 5%.22 The aim of the present randomised controlled trial was to investigate if there were differences in operative delivery rates in low-risk women giving birth in an alongside, midwifery-led unit, compared with obstetric units. We hypothesised that it was possible to reduce the need for operative deliveries, with the same or better results for mother and child, if low-risk women were delivered in a separate low-risk unit.\n\nBODY.METHODS:\nIn 1999 the Norwegian Parliament decided to organise national birth care into three levels. Departments of obstetric and gynaecology with more than 1500 births per year, providing all birth care services with obstetricians, paediatricians and anaesthesiologists on duty at all times, and with a neonatal intensive care unit.Smaller obstetrical departments with 400–1500 births per year, providing low-risk birth care with obstetricians and anaesthesiologist on call.Midwife-led maternity homes with 40–400 births per year, providing birth care for healthy women with expected normal births. The Norwegian Parliament also advised obstetric departments to have low-risk units within hospitals.23 Therefore, the Department of Obstetrics and Gynaecology at Østfold Hospital Trust, with approximately 3000 births per year, was divided into three separate units, placed on separate floors, in 2004: The midwife-led unit (MU), the normal unit (NU) and the special unit (SU). The MU is organised for low-risk women with expected normal births who want as little intervention as possible. Restrictive selection criteria must be fulfilled to attend this unit. No epidural is offered nor augmentation, unless required for the second phase of the second stage. If extended surveillance is needed or if the birth needs to be taken over by an obstetrician, the woman will be transferred to either the NU or the SU. Obstetricians are not present at the unit unless called on for a specific reason. The NU is organised for women with expected normal births. The unit has access to extended surveillance, epidural and operative vaginal delivery. It also provides room for women with elective caesareans and inductions after spontaneous rupture of membranes. If extended surveillance is necessary throughout the birth at the NU, a transfer to the SU is not required. The SU is organised for women who are in need of extended surveillance in the antenatal period, during labour and after birth. Women expecting normal births may give birth at any of the three units, but at the MU only low-risk women are accepted. The MU has approximately 600 births annually, and the other two units have approximately 1200 births each. Each unit has its own separate staff, and midwives are responsible for all normal deliveries. All units provide both birth and postpartum care. To explore our hypothesis a randomised trial was carried out. The primary outcome was operative delivery rates. Secondary outcomes were: augmentation of labour, pain relief, and postpartum haemorrhage, and neonatal outcomes measured by an Apgar score <7 at 5 minutes, metabolic acidosis defined as an umbilical artery pH <7.05 and BE (Base Excess) <−12 mmol/l,24 and transfers to the neonatal intensive care unit (NICU). Information about the trial was sent to all women planning to give birth at Østfold Hospital Trust when being called for a routine ultrasound examination. At the routine ultrasound examination at 18–20 weeks of gestation, all women roughly suited for the trial received additional written and verbal information about the trial. If eligible for the trial and willing to participate, she was recruited for the trial. If she fulfilled the inclusion criteria at the onset of spontaneous labour, she was randomised to one of the three units. The inclusion criteria for this study were similar to the selection criteria at the MU. Healthy, low-risk women without any disease known to influence the pregnancy, one fetus in cephalic presentation, a pre-pregnant body mass index (BMI) ≤32, not smoking more than ten cigarettes per day, no prior operation on the uterus, no prior complicated deliveries, and spontaneous onset of labour between 36+1 and 41+6 weeks of gestation. Written informed consent was obtained from all study participants. All 10 902 women who gave birth at the Østfold Hospital Trust during the study period were given written information on the trial when invited to ultrasound screening at 18 weeks of gestation. As the trial includes only healthy women, a certain number were excluded according to the inclusion criteria. Of the 2884 possible candidates assessed as being both eligible and willing to participate, 1773 did not meet the inclusion criteria by the time of onset of spontaneous labour for the following reasons: no longer considered to be at low risk because of pre-eclampsia, placenta praevia, intrauterine growth retardation, breech presentation, haemorrhage in third trimester, and pre- and post-term pregnancies and inductions (n = 697); changed their minds about participating (n = 300); the study was paused during summer and Christmas vacations because the MU was closed (n = 254); and for other reasons (n = 522). This led to a number of 1111 participants (Figure 1). Figure 1Flowchart of recruiting and inclusion process. The randomisation process was performed through a digital randomisation database developed by the Clinical Research Unit at the University Hospital of North Norway. The midwife who administered the randomisation entered the women's name and checked for eligibility before receiving the randomisation number and unit from the database. Allocation was concealed and the randomisation stratified between primiparous (para 0) and multiparous (para 1+) women (Table 1). As the SU serves women with extended needs, their capacity to receive low-risk women is limited. Because of this, randomisation was pre-specified to allocate 37.5, 37.5 and 25.0% to the NU, MU and SU, respectively. Table 1 Some basic characteristics of the participants Variable Midwife-led unit n = 282 (%) Normal unit n = 417 (%) Special unit n = 412 (%) Parity Nulliparous(P0) 278 (67.5) 285 (68.3) 184 (65.2) Multiparous(P+) 134 (32.5) 132 (31.7) 98 (35.4) Education Primary school 20 (4.9) 25 (6.0) 23 (8.2) High school 182 (44.2) 168 (40.3 112 (39.7) College/university 202 (49.0) 218 (52.3) 139 (49.3) Unknown 8 (1.9) 6 (1.4) 8 (2.8) Age <25 years 103 (25.0) 100 (24.0) 64 (22.7) 25–35 years 263 (63.8) 270 (64.7) 181 (64.2) >35 years 46 (11.2) 47 (11.3) 37 (13.1) Social status Married 155 (37.6) 165 (39.6) 120 (42.6) Cohabiting 236 (57.3) 229 (54.9) 152 (53.9) Single 19 (4.6) 20 (4.8) 9 (3.2) Unknown 2 (0.5) 3 (0.7) 1 (0.4) \n\nBODY.METHODS.DOCUMENTATION PROCESS:\nAll data were registered by the midwife in charge in the electronic journal system of the department, partus (Clinsoft®), as is routine for all births. A midwife at each unit monitored the entries and was responsible for the documentation in connection with the trial. As a third and last documentation control, all the participants' data were checked by a midwife not working at any of the three units.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nTo detect a statistically significant reduction in operative delivery rate for low-risk women, from an estimated >10% in standard care units to approximately 5%, which is closer to the estimated rate in freestanding birth units, a power calculation was conducted. With a power of 80% and a probability of P < 0.05, one would have to include 1642 low-risk women. The inclusion process proceeded slower than expected, and unfortunately the funding was running out. Hence the inclusion stopped the first week of March 2010, including just 1111 participants in the trial. All data were analysed by the principle of 'intention to treat'. Analyses presenting differences between the three units were performed by chi-squared tests, and Pearson's two-sided asymptomatic significance level P values were calculated. The MU was set as the reference unit, and all primary and secondary outcomes of this unit were compared with the outcomes of the NU and SU. The statistician who performed the statistical analysis was blinded to the participants' affiliation to the groups. Each result is presented with a risk ratio (RR) and a 95% confidence interval (95% CI). The analysis was conducted in statistical product and service solutions (SPSS) 17.\n\nBODY.RESULTS:\nOf the 1111 participants in this trial, 67.2% were primiparous and 32.8% were multiparous. Table 1 shows the baseline characteristics of the participants.\n\nBODY.RESULTS.MODE OF DELIVERY:\nThere was no statistically significant difference in mode of delivery between the three birth-care units (Table 2). At the MU, the total operative delivery rate was 16.3%, with 23.4% for primiparas. At the NU these figures were 18.0 and 25.6%, respectively, and at the SU the rates were 18.8 and 27.7% (Table 3). Table 2 Relative risk (RR) assessments, with the MU set as the reference Variable MU vs NU RR (95% CI) MU vs SU RR (95% CI) Operative delivery 0.90 (0.67–1.22) 0.87 (0.62–1.20) Operative vaginal delivery 0.85 (0.58–1.25) 0.98 (0.65–1.52) caesarean section 1.01 (0.58–1.75) 0.71 (0.41–1.24) Dystocia * 0.79 (0.65–0.96) 0.72 (0.59–0.89) Oxytocin augmentation 0.71 (0.58–0.87) 0.69 (0.55–0.86) Epidural 0.68 (0.51–0.90) 0.64 (0.47–0.86) N 2 O 0.99 (0.90–1.09) 0.92 (0.83–1.02) Acupuncture for pain relief 1.45 (1.25–1.69) 1.45 (1.22–1.73) Postpartum haemorrhage >1000 0.79 (0.30–2.09 0.59 (0.20–1.41) Episiotomy of all vaginal 0.85 (0.66–1.09) 0.78 (0.60–1.02) Third-or fourth-degree tear of all vaginal deliveries 0.56 (0.19–1.66) 0.67 (0.20–2.28) Apgar score <7 at 5 minutes 0.68 (0.19–2.37) 2.74 (0.31–24.37) Metabolic acidocis ** 0.78 (0.25–2.42) 1.10 (0.30–4.0) Transfers to NICU *** 1.25 (0.76–2.05) 1.15 (0.67–1.99) * Midwife or doctor recorded labour dystocia, according to the hospital criteria. ** Metabolic acidosis: sample taken from umbilical cord showing arterial pH <7.05 and BE <−12 mmol/l. *** Transfer of newborn to NICU within the first 2 hours postpartum. Table 3 Birth outcome within the first 2 hours postpartum at all three birth care units Variable MU n = 412 (%) NU n = 417 (%) SU n = 282 (%) P Mode of delivery Total number of spontaneous deliveries 345 (84.0) 342 (82.0) 229 (81.0) ns Total number of operative deliveries 67 (16.0) 75 (18.0) 53 (18.8) ns Number of operative deliveries (P0) 65/278 (23.4) 73/285 (25.6) 51/184 (27.7) ns Number of operative deliveries (P+) 2/134 (1.5) 2/132 (1.5) 2/98 (2.0) ns Indication for operative delivery Labour dystocia 39 (58.2) 31 (41.3) 32 (60.4) ns Fetal distress 19 (28.4) 26 (34.7) 13 (24.5) ns Total number of operative vaginal deliveries 43 (10.0) 51 (12.0) 30 (11.0) ns Number of operative vaginal deliveries (P0) 42/278 (15.1) 49/285 (17.2) 29/184 (15.8) ns Number of operative vaginal deliveries (P+) 1/134 (0.7) 2/132 (0.7) 1/98 (1.0) ns Indication for operative vaginal delivery Labour dystocia 26 (60.5) 23 (45.0) 21 (70.0) ns Fetal distress 14 (32.6) 20 (39.2) 9 (30.0) ns Total number of caesarean sections 24 (6.0) 24 (6.0) 23 (8.0) ns Number of caesarean sections (P0) 23/278 (8.3) 24/285 (8.4) 22/184 (12.0) ns Number of caesarean sections (P+) 1/134 (0.7) 0/132 (0.0) 1/98 (1.0) ns Indication for caesarean section Labour dystocia 13 (54.2) 8 (33.3) 11 (47.8) ns Fetal distress 5 (20.8) 6 (25.0) 4 (17.4) ns Labour * 120 (29.0) 154 (37.0) 114 (40.0) <0.01 Oxytocin augmentation 108 (26.2) 153 (36.7) 107 (38.0) <0.01 Epidural 65 (16.0) 97 (23.0) 70 (25.0) <0.01 N 2 O 270 (66.0) 275 (66.0) 201 (71.0) ns Acupuncture for pain relief 227 (55.0) 158 (38.0) 107 (38.0) <0.001 Postpartum haemhorrage >1000 ml 7 (1.7) 9 (2.2) 9 (3.2) ns 500–999 ml 33 (8.0) 38 (9.0) 36 (13.0) ns 1000–1500 ml 4 (1.0) 6 (1.0) 3 (3.0) ns >1500 ml 3 (1.0) 3 (1.0) 6 (2.0) ns Episiotomy, of all vaginal deliveries 88/388 (23.0) 105/393 (27.0) 75/259 (29.0) ns Third- or fourth-degree tear, all vaginal deliveries 5 (1.0) 9 (2.0) 5 (2.0) ns Intrapartum transfer ** 117 (28.0) Apgar score <7 at 5 minutes 4 (1.0) 6 (1.0) 1 (0.5) ns Metabolic acidocis *** 5 (2.0) 7 (3.0) 4 (2.0) ns Transfers to NICU **** 32 (8.0) 26 (6.0) 19 (7.0) ns * Midwife or doctor recorded labour dystocia, according to the hospitals criteria. ** Intrapartum transfer from the MU. *** Metabolic acidosis: sample from umbilical cord showing arterial pH <7.05 and BE (Base Excess) <−12 mmol/l. **** Transfer of newborn to NICU within the first 2 hours postpartum. ns, not significant; P0, primiparous; P+, multiparous. Of all 24 women delivered by caesarean section at the MU, 23 were primiparous. The main reason for the intervention was dystocia (54.2%). At the NU there were 24 caesarean sections, all of them among nulliparous women. Dystocia was the reason for 33.3% of the operations at this unit. At the SU, one multiparous and 22 nulliparous women were delivered by caesarean section, and the main reason given for this intervention was dystocia (47.8%) (Table 3). Regarding operative vaginal delivery at the MU, 42 out of 43 deliveries were for primiparous women, and the main indication was dystocia. Of the women having an operative vaginal delivery at the NU, only two out of the 49 were multiparous, and the main reason for intervention was dystocia. At the SU, one of the 30 women who had an operative vaginal delivery was multiparous, and dystocia was the main indication for the interventions (Table 3).\n\nBODY.RESULTS.MODE OF DELIVERY.PERINEAL OUTCOME:\nThere was no significant difference between the three groups concerning the number of episiotomies or the incidence of sphincter injuries (Table 2). An episiotomy was performed on 22.7, 26.7 and 29.0% of the women in the MU, NU and SU, respectively (Table 3). A sphincter injury occurred in 1.3, 2.3 and 1.9% of the vaginal deliveries at the MU, NU and SU, respectively (Table 3). Of the five women with a sphincter injury at the MU, none had an episiotomy, one had an operative vaginal delivery and four had spontaneous delivery. Of the nine women with sphincter injuries at the NU, four had both an episiotomy and operative vaginal delivery, one had spontaneous delivery with episiotomy and four had spontaneous delivery with no episiotomy. At the SU, five women had sphincter injuries: three had an operative vaginal delivery and episiotomy, one had an episiotomy and spontaneous delivery, and one had spontaneous delivery and no episiotomy.\n\nBODY.RESULTS.MODE OF DELIVERY.LABOUR DYSTOCIA:\nLabour dystocia was evaluated and recorded by the midwives or the doctors. According to the hospital guidelines, dystocia is defined as progression of <1 cm dilatation of the cervix per hour in the active phase of the first stage (defined as 3–4 cm dilatation of the cervix and regular contractions until a cervix dilatation of 10 cm). Dystocia in the second stage is recorded if the expulsion phase lasts more than 60 minutes for both nulliparous and multiparous women. Dystocia in the second stage is also recorded if the second stage lasts longer than 2 hours for nulliparous women without epidural or multiparous women with epidural, or more than 3 hours for nulliparous women with epidural or more than 60 minutes for multiparous women without epidural. In the MU dystocia was recorded in 29.1% of the cases, which is a significantly lower rate than 36.9% in the NU (RR 0.79, 95% CI 0.65–0.96) and 40.4% in the SU (RR 0.72, 95% CI 0.59–0.89) (Table 2). Of all women allocated to the MU, 26.2% were given oxytocin infusion for augmentation of labour, which was significantly lower than 36.7% in the NU (RR 0.73, 95% CI 0.59–0.89) and 38.0% in the SU (RR 0.69, 95% CI 0.56–0.86) (Table 2). Labour dystocia was the main reason for all operative deliveries (Table 3). The mean time for the active phase of the first stage was 4.9, 4.6 and 4.8 hours in the MU, NU and SU, respectively. The mean time for the expulsion phase of all vaginal deliveries was 40.4, 39.2 and 40.1 minutes in the MU, NU and SU, respectively.\n\nBODY.RESULTS.MODE OF DELIVERY.PAIN RELIEF:\nOf all women randomised to the MU, 15.8% had an epidural, which is a significantly lower rate than 23.3% in the NU (RR 1.47, 95% CI 1.11–1.96) and 24.8% in the SU (RR 1.57, 95% CI 1.16–2.13). The women randomised to the MU had acupuncture in 55.1% of the cases, a significantly higher rate compared with those randomised to the NU (37.9%; RR 1.45, 95% CI 1.25–1.69) and SU (37.9%; RR 1.45, 95% CI 1.22–1.73) (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.HAEMORRHAGE:\nThere was no statistically significant difference in the rate of postpartum haemorrhage between the three units (Table 2). The vast majority of all participants had normal postpartum haemorrhage of 500 ml or less (MU 90.3%, NU 88.7% and SU 84.0%; Table 3). Of the 25 women with a haemorrhage of 1000 ml or more, 17 were caused by atonic postpartum haemorrhage (five operative vaginal deliveries, 11 spontaneous deliveries and one caesarean section), three were caused by a retained placenta (two operative vaginal deliveries and one spontaneous delivery) and for five women no indication was stated.\n\nBODY.RESULTS.MODE OF DELIVERY.NEONATAL OUTCOMES:\nNeonatal outcomes were evaluated by Apgar score <7 at 5 minutes, metabolic acidosis and transfer to NICU within 2 hours of birth. An Apgar score <7 at 5 minutes was observed in 1.0, 1.4 and 0.4% of cases in the MU, NU and SU, respectively. An umbilical cord pH test was taken in 57.7, 68.8 and 77.3% of the cases in the MU, NU and SU, respectively. Metabolic acidosis was stated in 2.2, 2.8 and 2.0% in the MU, NU and SU, respectively. Transfers to the NICU were conducted in 7.8, 6.2 and 6.7% of the cases in the MU, NU and SU, respectively (Table 3). None of these outcomes showed a statistically significant difference between the units (Table 2).\n\nBODY.RESULTS.MODE OF DELIVERY.INTRAPARTUM TRANSFER:\nOf the 412 women randomised to the MU, 117 (28.4%) were transferred intrapartum to a higher level of care, either to the NU or SU (Table 3). The reasons for transfer were need for pain relief (39.3%), stained amniotic fluid (18.8%), fetal distress (9.4%), labour dystocia (23.9%) and other reasons (8.5%). Mean dilatation of the cervix was 6.4 cm at the time of transfer; 51% were transferred with a cervix dilatation of <7 cm. Of all women transferred intrapartum, 61 (52.0%) had an operative delivery, and among these, 39.3% were delivered by caesarean section and 60.7% were delivered by operative vaginal delivery. Of those transferred for labour dystocia, 60.8% had an operative delivery and 39.2% had a spontaneous delivery.\n\nBODY.DISCUSSION:\nIn this randomised controlled trial three birth units within the same hospital were compared concerning birth care for low-risk women. The results when including 1111 participants showed no statistically significant differences in the total operative delivery rate, nor did it show differences in postpartum haemorrhage or neonatal outcomes between the three units. Operative delivery rate is often used as a measure of the quality of birth care,7–11,14,16,19,20,22,25,26 but it is a subtle way of measuring quality, as it predicts poor quality if the operative delivery rate is low but gives a negative outcome, or if the rate is high without improving the outcome or even increasing the complications for the mother or newborn, yet it predicts good quality if performed when needed. Finding the right level or percentage of operative delivery will always be a challenge. Operative delivery rates differ between countries and institutions. Data from the Medical Birth Registry of Norway (MBRN) from 2008 show an average total operative delivery rate for low-risk women of approximately 13.8%, but varies between institutions. It is worth noting that the birth population in Norway 2006–2009 consisted of 42.2% primiparous and 57.9% multiparous women.21 During the study period the Department of Obstetrics and Gynaecology at Østfold Hospital Trust had a high overall operative delivery rate (29.2%) compared with most hospitals in Norway.21 This fact is reflected in the high numbers of caesarean deliveries in this study in all three birth units. The overall high risk of having an operative delivery for low-risk nulliparas with no expressed preferences for level of birth care, leave birth attendants with the challenge of focusing on low-risk primiparous women, guiding them safely through their first labour. Statistically significant differences were found for dystocia and augmentation of labour by oxytocin, and the use of epidural and acupuncture as pain relief. Moen et al.27 studied augmentation for all low-risk women in a retrospective study conducted at a large hospital in Norway. They found that low-risk women were given oxytocin in 39% of the cases (62% of the primiparous and 24% of the multiparous women), many of them without any documented indication. In a debate article in the BMJ in 2002, the authors state that medical interventions have become routine in normal childbirth, without evidence of effectiveness.4 This view is supported by others.2 A strength of this trial is the time for randomisation when comparing intrapartum birth care and birth outcome in low-risk birth units and standard care units. All participants were defined as low risk when entering the trial at onset of spontaneous labour, making sure that only those fulfilling the selection criteria were included. As far as we know no similar trial has been conducted in Europe during the last two decades. A possible limitation of this trial is the fact that the number of women included was less than estimated by the power calculations, based on the primary outcome: operative delivery. This also might be the reason for the wide confidence interval for the primary outcome. However, the differences between the three units were so small that even if the total number of participants were included, it is considered unlikely that the differences would be significant. Only small non-significant differences in total operative delivery rate were found (total operative delivery rate, MU versus SU P= 0.57 and MU versus SU P= 0.44). There is a challenge in recruiting participants to studies like this because of the fact that women today often have their own preference for place of birth.28 This fact led to a longer recruiting period than expected in this trial.\n\nBODY.CONCLUSION:\nThe operative delivery rate, the risk of having a postpartum haemorrhage of more than 1000 ml and the outcome for the newborn were not affected by the level of care for low-risk women without prelabour preferences for level of care. The participants randomised to the MU had a significantly higher chance of giving birth without interventions like augmentation by oxytocin or epidural analgesia. Further research is needed to determine the influence of women's own preference for birth care unit.\n\n**Question:** Compared to Normal unit & Special unit what was the result of Special unit on Perineal outcome: the number of episiotomies or the incidence of sphincter injuries?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
159
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Pilot study of Lokomat versus manual-assisted treadmill training for locomotor recovery post-stroke\n\n ABSTRACT.BACKGROUND:\nWhile manually-assisted body-weight supported treadmill training (BWSTT) has revealed improved locomotor function in persons with post-stroke hemiparesis, outcomes are inconsistent and it is very labor intensive. Thus an alternate treatment approach is desirable. Objectives of this pilot study were to: 1) compare the efficacy of body-weight supported treadmill training (BWSTT) combined with the Lokomat robotic gait orthosis versus manually-assisted BWSTT for locomotor training post-stroke, and 2) assess effects of fast versus slow treadmill training speed.\n\nABSTRACT.METHODS:\nSixteen volunteers with chronic hemiparetic gait (0.62 ± 0.30 m/s) post-stroke were randomly allocated to Lokomat (n = 8) or manual-BWSTT (n = 8) 3×/wk for 4 weeks. Groups were also stratified by fast (mean 0.92 ± 0.15 m/s) or slow (0.58 ± 0.12 m/s) training speeds. The primary outcomes were self-selected overground walking speed and paretic step length ratio. Secondary outcomes included: fast overground walking speed, 6-minute walk test, and a battery of clinical measures.\n\nABSTRACT.RESULTS:\nNo significant differences in primary outcomes were revealed between Lokomat and manual groups as a result of training. However, within the Lokomat group, self-selected walk speed, paretic step length ratio, and four of the six secondary measures improved (p = 0.04–0.05, effect sizes = 0.19–0.60). Within the manual group, only balance scores improved (p = 0.02, effect size = 0.57). Group differences between fast and slow training groups were not revealed (p ≥ 0.28).\n\nABSTRACT.CONCLUSION:\nResults suggest that Lokomat training may have advantages over manual-BWSTT following a modest intervention dose in chronic hemiparetic persons and further, that our training speeds produce similar gait improvements. Suggestions for a larger randomized controlled trial with optimal study parameters are provided.\n\nBODY.BACKGROUND:\nStroke is the leading cause of serious, chronic disability in the United States and Canada. While two-thirds of people who suffer a stroke regain ambulatory function, the resulting gait pattern is typically asymmetrical, slow, and metabolically inefficient [1,2]. These characteristics are associated with difficulty advancing and bearing weight through the more affected limb, leading to instability and an increased risk of falls [3]. Secondary impairments, including muscle disuse and reduced cardiorespiratory capacity, often contribute to further functional declines in gait. Hence, improved walking is one of the most frequently articulated goals of rehabilitation and interventions that effectively enhance locomotor function are essential to improve quality of life for many stroke survivors and their families [4,5]. Nevertheless, the effectiveness of locomotor training still remains unclear and the need to conduct randomized controlled trials to definitively answer this question is paramount. To best determine the key parameters of such a large-scale study, preliminary data must first be collected in the form of a pilot study. Manually-assisted body-weight supported treadmill training (BWSTT) is a contemporary approach to gait rehabilitation wherein an individual walks on a treadmill with body-weight partially supported by an overhead harness. One to three therapists/trainers manually facilitate hemiparetic limb and trunk control in an effort to normalize upright, reciprocal stepping and dynamic postural control. Advantages of this approach are that little to no ambulatory function is required to initiate locomotion and early post-stroke training effects are transferred to improvements in overground gait including: symmetry, speed, and endurance as well as motor impairment and balance scores [6,7]. These positive outcomes can be maintained even at 6 months post-locomotor training [8]. However, because locomotor training involves repetition of hundreds of steps within one session, facilitation of a symmetrical, patterned gait can be very labor intensive for both therapist(s) and participant and further, presents a non-trivial risk of injury to the trainers. Moreover, the repetition of kinematically consistent stepping patterns is hindered by inconsistencies in motor performance of the therapists assisting movement. Conflicting evidence within 15 randomized controlled trials comparing BWSTT and traditional gait training (i.e. overground gait training, motor relearning) in persons post-stroke highlight the difficulty in interpreting the effectiveness of manually applied cues during repetitive stepping [9]. In response to the challenges presented in administering manual-BWSTT, robotic devices, such as the Lokomat® (Hocoma, Inc., Zurich, Switzerland), have recently emerged as a means to automate locomotor training in neurorehabilitation. Using robotic assistance, an exoskeleton facilitates a bilaterally symmetrical gait pattern as the individual actively attempts to advance each limb while walking on the treadmill. The preprogrammed walking pattern corresponds with normal gait kinematics including: gait cycle timing (i.e. stance vs. swing phase), inter-limb and inter-joint coordination, appropriate limb loading, and afferent signaling [10]. Animal models have demonstrated that afferent signals derived from limb movement and loading converge at the level of the spinal cord to trigger and control locomotor pattern generators (LPGs) [11,12]. Previous work in persons with spinal cord injuries underscores the importance of the accuracy of relevant timed peripheral inputs to induce changes in locomotor function [13]. Accordingly, the rhythmic and repetitive stepping pattern provided by robotic assistance, combined with active limb loading and kinematic consistency has been shown to promote plasticity of LPGs at the spinal cord level [14] as well as supraspinal structures [15]. Still, despite recent interest in automated locomotor training, there remains very little evidence to support the superiority of this technique over traditional gait training. Previous comparisons between robotic-BWSTT and manual-BWSTT, overground gait training, and traditional approaches result in equivocal findings based, in part, on differences in outcome measures, subject characteristics, and gait training protocols [16-20]. However, separation of the general effects of locomotor training from true automated training effects requires standardization of BWSTT parameters, i.e. BWS percentage and stiffness, treadmill speed, and use of handrails [21], and a comparison between the application of manual or robotic limb guidance with the intent of approximating normal gait kinematics in a well-defined subject population. In controlling these variables, we hypothesize that Lokomat training will produce greater improvements in gait speed and symmetry than manual training. Extending the notion of task-specificity underlying both Lokomat and manual-BWSTT, one particular variable of interest is training speed. If the therapeutic goal is increased overground walking speed, then training must occur at speeds that exceed habitual overground walking speed for a person with hemiparesis. The majority of the current models of the Lokomat robotic orthosis offer treadmill belt speeds up to 0.83 m/s (3 km/h), thus it is yet unknown whether training at higher Lokomat speeds produces similar positive gait changes as revealed in earlier studies [8,22]. Here, we hypothesize that the addition of external timing cues and kinesthetic input induced by Lokomat training and manual BWSTT at training speeds of up to 1.4 m/s (5 km/h) will produce greater improvements in spatio-temporal gait parameters, postural control, and clinical outcomes than groups trained at slower speeds. Objectives of this pilot study were to: 1) compare the efficacy of Lokomat versus manual assisted-BWSTT in persons with chronic locomotor deficits post-stroke and 2) probe the effect of locomotor training at speeds corresponding with overground gait in non-disabled individuals to habitual self-selected walking speed in persons post-stroke. Since self-selected overground gait speed and step length symmetry are important indicators of locomotor performance, and further, are related to function and quality of life following stroke [23,24], these variables were selected as our primary variables of interest. Secondary outcomes included fast overground walking speed, a battery of clinical and functional measures, and a quality of life indicator.\n\nBODY.METHODS.PARTICIPANTS:\nSixteen persons with hemiparesis resulting from a single cortical or subcortical stroke (confirmed by CT or MRI) greater than 6 months prior to the study, who were categorized as at least unlimited household ambulators (e.g. > 0.3 m/s) [4] participated. Exclusion criteria included: 1) unstable cardiovascular, orthopedic, or neurological conditions, 2) uncontrolled diabetes that would preclude exercise of moderate intensity, or 3) significant cognitive impairment affecting the ability to follow directions. Participants were recruited from local hospitals, rehabilitation centers, and stroke associations. All procedures were approved by the Stanford University Institutional Review Board and all participants provided written, informed consent prior to study involvement.\n\nBODY.METHODS.ALLOCATION PROCEDURES:\nIn an effort to achieve our primary research goal, participants were randomized into either a Lokomat (n = 8) or manual (n = 8) group using a computer-generated random order. To reach our secondary goal, an equal number of participants within each group were randomly assigned to either a fast (n = 8) or slow (n = 8) training group. The randomization list was overseen by one of the investigators (CP) who had no contact with participants until group assignment was revealed. Further, group assignment was not revealed to study personnel until the participant was consented and baseline testing was complete.\n\nBODY.METHODS.INTERVENTION:\nBoth groups received 12 sessions (3×/wk over 4 weeks) involving 30 min of stepping per session. At least one 2–3 minute break was provided after 15 min. Total set-up and treatment time never exceeded 1 hr. Training speeds were maintained below 0.69 m/s (2.5 km/h) in the slow groups and above 0.83 m/s (3 km/h) in the fast groups. Within the fast groups, locomotor training was either started at 0.83 m/s or progressed to this speed as early as possible (e.g. by Session 3) while maintaining gait quality, i.e. symmetrical, foot clearance, without knee buckling. Treadmill speed was progressed in 0.2 km/hr increments approximately every 5 min as long as the above-mentioned gait quality was observed by the therapists. If a new high speed could not be maintained for an extended period, training would ensue in 2–3 minute intervals at the higher speed followed by 2–3 minutes at a lower speed. BWS was initiated at 35%. The Lokomat system used for this study includes the Lokolift, a compliant, electromechanical body-weight support system that monitors and adjusts unweighting in real time to maintain BWS at the prescribed level. This BWS system contrasts with the stiff, counterweighted support system used in the original Lokomat models. A compliant system adjusts to the participant's center of gravity throughout the gait cycle, enabling vertical pelvic movement similar to overground gait, supporting symmetrical movement and producing kinetics similar to overground walking [21,25]. If the maximal treadmill speed, 0.69 m/s (2.5 km/h) in the slow group or 1.4 m/s (5 km/h) in the fast group, was reached, BWS was reduced in increments of 5% as long as gait quality was maintained. Our goal during training was to improve gait kinematics. To achieve this objective, all participants trained without an ankle-foot orthosis, assistance was reduced once safety was no longer a concern, and rest periods were provided if gait quality was noted to deteriorate. In addition, handrail use has been shown to significantly alter the gait pattern and thus was strongly discouraged [25]. Participants assigned to the Lokomat group trained in a robotic orthosis. Thigh and leg straps secured the Lokomat exoskeleton to the participant; motors on each robotic leg facilitated movement of the hip and knee joints with trajectories programmed by the manufacturer based on a single, healthy individual's gait pattern. Only when necessary to maintain foot clearance, the ankle was maintained in neutral dorsiflexion by means of an elastic foot strap. Force sensors within the Lokomat hip and knee joints provided output on a visual display that was monitored by the treating physical therapist. In an effort to maintain consistency in training parameters, Lokomat assistance was provided at 100% bilateral guidance force for all participants throughout all training sessions. Participants were provided verbal encouragement to actively step in conjunction with the movement presented by the Lokomat. Participants in the manual-BWSTT group were treated by 1–2 skilled physical therapists/trainers who provided manual guidance of the more affected limb, trunk stabilization/alignment, and verbal and visual cues to normalize stepping kinematics. Our intent in using this number of therapists was to mimic clinic feasibility and training in previous reports [20]. The target gait pattern included: adequate trunk alignment, weight shift, acceptance to and from the paretic limb and temporal symmetry between limbs. The treating therapist individualized treatment to facilitate trunk and limb control throughout the gait cycle. Common cues included coaching to: increase plantarflexion propulsion and/or hip flexion at swing initiation, increase dorsiflexion and knee extension at heel strike, and maintain neutral knee alignment (i.e. avoid hyperextension) at midstance. A second trainer provided pelvic stabilization and assistance with weight shift/acceptance as needed. Participants in both groups were provided visual feedback via a full-length mirror placed at the front of the treadmill.\n\nBODY.METHODS.MEASUREMENT:\nParticipants were assessed before and after the 4-week intervention. Self-selected overground walking speed and fast overground walking speed were recorded using a 4.3 m GaitRite mat (CIR Systems, Havertown, Pennsylvania, USA). Participants walked an additional 0.5 m on both ends of the walkway to allow for acceleration and deceleration and were instructed to walk either: \"as if taking a comfortable walk in the park\" for self-selected walking speed or \"as if they were in the middle of the intersection and the light had just changed to red\" for fast walking speed. The mean of 3 trials was calculated. Step length of the paretic (P) and nonparetic (NP) limb was also recorded and later used to calculate absolute (ABS) step length asymmetry during self-selected walking speed as follows: This calculation is a modification of the paretic step length ratio (SLR) [26] and can range from 0 to 1, with an index of 0 reflecting perfect symmetry. The 6-minute walk test was recorded as a measure of gait endurance. Participants were instructed to cover as much distance as possible within a 6-minute period while walking safely. This test was completed along a level carpeted corridor with one turn-around point every 39 meters. For all overground gait assessments, ambulation without an assistive device or lower extremity orthoses was encouraged. However, use of these assistive devices was allowed if deemed necessary for safety. Device usage was consistent between pre- and post-testing. Secondary outcomes were selected to target impairment, activity, and participation according to the World Health Organization classifications. Motor impairment was evaluated with the lower extremity Fugl-Meyer assessment, which is a valid and reliable measure in persons post-stroke [27,28]. Activities were assessed with the short physical performance battery and the Berg Balance Scale. The short physical performance battery produces a summary score (range 0–12) reflecting scores on 3 timed tasks: walking 8-ft, rising from a chair 5 times, and maintaining a static posture (feet together, semi-tandem, tandem) [29]. Good to excellent reliability and predictive validity have been demonstrated for these tests [30,31]. The Berg Balance Scale is comprised of 14 static and dynamic balance tasks with a maximum score of 56. This measure demonstrates good reliability and validity in a population post-stroke [32,33]. Participation in life events was assessed using the Late Life Function and Disability Instrument (LLFDI) [34], which is composed of a disability section assessing limitation and frequency of performance and a function section measuring difficulty in performing certain physical tasks. Good reliability and validity has also been demonstrated for this measure in a population with a range of functional limitations [35,36].\n\nBODY.METHODS.DATA ANALYSIS:\nStatistical analyses were conducted using SPSSv15.0 (SPSS, Inc., Chicago, Illinois, USA). Given the small sample size, non-parametric statistics were used. Baseline characteristics between groups were compared using the Mann-Whitney U test for continuous and ordinal variables and the Fisher's exact test for categorical variables. Between group comparisons (Lokomat vs. Manual groups and Fast vs. Slow Training groups) were assessed with the Mann-Whitney U-test using pre-post change scores in ordinal variables. Within group comparisons (Pre vs. Post training) were assessed using the Wilcoxon Signed Ranks Test. Statistical significance was established at α < 0.05. To determine whether a statistically significant difference is of practical concern, effect sizes and percent change were calculated. Effect sizes were calculated as the difference between the means of the two groups (Lokomat and manual) or between the mean pre-test and post-test values of the same group divided by the common standard deviation (SD) at pre-test. Results were interpreted following standards established by Cohen [37] where 0.2 is indicative of a small effect, 0.5 a medium, and 0.8 a large effect size.\n\nBODY.RESULTS:\nAll sixteen participants completed the study and the twelve training sessions were well tolerated with two exceptions. First, following the eleventh session, one participant in the manual group complained of ankle pain on the hemiparetic side and failed to complete the final training session. Second, despite using a regular rotation of two treating therapists, one therapist suffered a repetitive strain injury of the rotator cuff while training the third manual group participant. Participant characteristics are enumerated in Table 1. Group equivalency (i.e. Lokomat vs. manual and fast vs. slow) was established with no significant baseline differences, p ≥ 0.13. In the Lokomat group removal of the foot strap was possible in 3 participants. One participant advanced to walking without the foot strap for approximately 54% of sessions, while two additional participants advanced to no foot strap for 25% of sessions. Table 1 Baseline characteristics and training parameters Lokomat (n = 8) Manual (n = 8) p value Age, mean (SD), y 58.6 (16.9) 55.1 (13.6) 0.72 a Women, n (%) 2 (25) 1 (12.5) 1.0 b Time since stroke, mean (SD), mo 43.8 (26.8) 36.8 (20.3) 0.72 a Stroke location, n MCA territory (multiple locations) 3 4 1.0 b Frontal lobe 0 1 1.0 b Temporoparietal lobe 1 0 1.0 b Parietal lobe 1 1 1.0 b Basal Ganglia 3 1 1.0 b Thalamus 0 1 1.0 b Pons 0 1 1.0 b Type of Stroke, n Ischemic 3 5 1.0 b Hemorrhagic 5 3 1.0 b Left sided hemiparesis, n 4 5 1.0 b LE Fugl-Meyer total score, mean (SD) 83.3 (7.3) 80.6 (6.3) 0.13 a Self-selected walking speed, mean (SD), m/s 0.62(0.31) 0.62 (0.28) 0.80 a Training speed, mean (SD), m/s 0.82 (0.2) 0.67 (0.2) 0.16 a Training BWS, mean (SD) 29.4 (5.9) 31 (9.1) 0.28 a a Mann-Whitney U test; b Fisher's exact test Our first aim of this pilot study was to compare the effectiveness of Lokomat versus manual-assisted BWSTT on gait-related outcomes. Overall results revealed no significant differences between Lokomat and manual training group improvements on self selected walk speed, p = 0.72, absolute paretic step length ratio, p = 0.28, or secondary variables, p = 0.54–0.96. However, within the Lokomat group, a greater number of variables demonstrated significant pre- vs. post-test differences compared with the manual group (Table 2). Table 2 Group Comparisons of selected outcomes Variable Lokomat Group (n = 8) Manual Group (n = 8) Pre-Test Post-Test Pre-Test Post-Test SSWS (m/s) 0.62 ± 0.31 (0.26–1.04) 0.72 ± 0.38* (0.3–1.38) 0.62 ± 0.28 (0.24–0.91) 0.65 ± 0.29 (0.30–1.02) FWS (m/s) 0.87 ± 0.55 (0.32–1.85) 0.96 ± 0.66* (0.33–2.28) 0.72 ± 0.37 (0.26 ± 1.2) 0.70 ± 0.33 (0.35–1.13) 6 MWT (m) 267.3 ± 187.2 (71–625.5) 278.1 ± 176.5 (89.3–638.0) 234.3 ± 141.2 (66.4–452.7) 212.4 ± 113.5 (86.5–362.9) SLR abs 0.53 ± 0.58 (0.03–1.87) 0.37 ± 0.46 * (0.06–1.46) 0.39 ± 0.37 (0.05–1.10) 0.34 ± 0.35 (0.02–1.04) LE FM (/35) 23.0 ± 4.3 (15–28) 25.6 ± 5.0 * (19–34) 21.4 ± 5.1 (14–29) 22.4 ± 5.2 (14–29) SPPB (/12) 6.9 ± 3.4 (2–12) 7.9 ± 3.2 * (4–12) 7.8 ± 3.0 (4–12) 8.5 ± 3.1 (4–12) BBS (/56) 46.9 ± 7.5 (38–56) 48.3 ± 6.8 * (41–56) 47.0–7.0 (38–55) 51.0–5.4 † (40–56) LLFDI Disability Frequency (/100) 52.6 ± 8.1 (41.4–65.1) 52.8 ± 7.9 (41.4–62.3) 49.7 ± 11.4 (29.2–70.6) 53.5 ± 10.2 (35.2–66.7) Limitation (/100) 59.4 ± 7.0 (49.2–69.2) 62.3 ± 8.5 (49.9–71.3) 61.6 ± 9.1 (46.4–75.6) 66.4 ± 10.2 (47.9–77.6) Function 51.3 ± 7.7 52.0 ± 8.6 48.6 ± 6.0 54.1 ± 4.8 (/100) (43.1–64.0) (42.5–66.8) (41.9–58.7) (46.1–61.6) Note: values are mean ± SD (range) * Pre-post difference within Lokomat group, p < 0.05; † difference within manual group, p < 0.05 Abbreviations: SSWS = self selected walking speed; FWS = Fast walking speed; 6 MWT = 6 minute walk test; SLR abs = Absolute step length ratio; LE FM = Lower extremity Fugl-Meyer; SPPB, short physical performance battery; BBS = Berg Balance Scale; LLFDI = late life function and disability instrument. Although an equal number of participants (n = 7) produced a training related increase in self-selected overground walking speed in each group, a significant difference, p = 0.04, was revealed only in the Lokomat group with a pre-post intervention difference of 0.10 m/s and an effect size of 0.32 which contrasted with a 0.03 m/s difference and 0.11 effect size in the manual group (Figure 1A; Table 2). Figure 1Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Self-selected walk speed. B. Absolute step length ratio (negative change scores represent a shift towards symmetrical step lengths). Extreme values are greater than 3 times the interquartile distance.* Significant difference only within the Lokomat group (p < 0.05). Absolute paretic step length ratio (SLRabs) during self-selected overground walking speed was also significantly reduced (i.e. closer to an SLRabs of 0) from pre- to post-test in the Lokomat group, p = 0.05, effect size 0.26, reflecting improved symmetry in 6 of 8 Lokomat group participants (Figure 1B; Table 2). With the exception of the 6-minute walk test and LLFDI, p ≥ 0.16, all secondary measures revealed significant improvements within the Lokomat group, yet only one improvement was noted in the manual group (Table 2). Fast overground walk speed improved from pre- to post-training in 6 of 8 Lokomat participants, p = 0.05, with a small effect size of 0.15 (Figure 2A). Lower extremity Fugl-Meyer score improvements were also noted, p = 0.04, with an effect size of 0.60 and higher scores in 5 of 8 Lokomat group participants (Figure 2B). Similarly, short physical performance battery scores were improved in the Lokomat group, p = 0.04, with an effect size of 0.29 and improvements in 5 of 8 participants. Berg Balance Scale scores significantly improved in both the Lokomat group, p = 0.04, effect size 0.19 (5 participants improved), and manual group, p = 0.02, effect size 0.57 (7 participants improved) (Figure 2C). Figure 2Medians and lower and upper quartiles for pre-post differences in the manual and Lokomat group. A. Fast Walk speed. B. Lower Extremity Fugl-Meyer scores (higher scores represent improved sensorimotor recovery). C. Berg Balance Scale (higher scores represent improved balance). D. Six minute walk test (distance covered). * Significant difference within Lokomat group between pre- and post-test (p < 0.05). † Significant difference within manual group between pre- and post-test (p < 0.05). Participation in life events, as measured by the LLFDI, also demonstrated improvements, but statistical differences were attained only as a main effect of visit (i.e. pre vs. post) and were not specific to either the Lokomat or manual-BWSTT group. The disability component reflects two dimensions: limitation and frequency. Our data revealed that participants felt less limited in their participation in activities at home and in the community, p = 0.02, with an effect size of 0.49. Interestingly, the frequency of self-reported participation in these tasks remained unchanged from pre-test to post-test, p ≥ 0.11. Participants also perceived less difficulty in terms of the performance of certain functional tasks including: dressing, walking a mile, and climbing stairs, p = 0.004, with an effect size of 0.47. In an effort to differentiate changes in motor control from aerobic conditioning effects, we conducted two post-hoc correlations: 1) self-selected overground walking speed and 6-minute walk test, and 2) Berg Balance Scale and 6-minute walk test. Due to the influence of gait speed and balance in a chronic population (mean 5.5 years post-stroke), previous work has cautioned against interpreting the 6-minute walk test as an indicator of aerobic capacity [38]. However, in our study of participants who averaged 3.3 years post-stroke, no significant relationship was identified between either changes in 6-minute walk test and self selected gait speed, r = 0.14, p = 0.61, or changes in 6-minute walk test and balance (Berg Balance Scale), r = 0.27, p = 0.32. Therefore, improvements in gait speed and balance detected in the present study could be attributed to enhanced locomotor control and were not likely due to changes in endurance as measured using the 6-minute walk test. Our second aim was to assess locomotor-training effects at faster vs. slower treadmill speeds. As anticipated, independent of whether training occurred in the Lokomat or manual-BWSTT mode, average weekly training speeds within the fast and slow groups were similar, p ≥ 0.29 (Table 3). Therefore, data from both Lokomat and manual groups were collapsed to isolate the effects of training speed. On average, participants in the fast group trained at speeds that were 50% above their baseline overground walking speed, while the training speed in the slow group was similar to their baseline overground walking speed. Despite these differences in absolute and relative between-group training speeds, no group differences were noted on primary or secondary outcome measures, p ≥ 0.28. Table 3 Treadmill training speeds and self-selected walking speeds of fast and slow training groups Treadmill training speed (m/s) Final overground SSWS (m/s) Group Initial overground SSWS (m/s) Week 1 Week 2 Week 3 Week 4 Mean Fast 0.6 ± 0.2 (0.2–1.0) 0.8 ± 0.1 (0.5–1.1) 0.9 ± 0.1 (0.7–1.2) 0.94 ± 0.0 (0.7–1.2) 1.0 ± 0.1 (0.8–1.3) 0.9 ± 0.2 (0.7–1.2) 0.7 ± 0.4 (0.3–1.4) Robot 0.6 ± 0.3 (0.3–1.0) 0.9 ± 0.1 (0.8–1.1) 1.0 ± 0.1 (0.9–1.2) 1.0 ± 0.1 (0.9–1.2) 1.1 ± 0.2 (0.9–1.3) 1.0 ± 0.1 (0.9 ± 1.2) 0.7 ± 0.5 (0.4–1.4) Manual 0.6 ± 0.3 (0.2–0.9) 0.7 ± 0.2 (0.5–0.8 0.8 ± 0.1 (0.7–0.9) 0.9 ± 0.11 (0.7–1.0) 1.0 ± 0.1 (0.8–1.1) 0.8 ± 0.1 (0.7 ± 0.9) 0.7 ± 0.3 (0.3–0.9) Slow 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.6 ± 0.1 (0.3–0.7) 0.7 ± 0.3 (0.3–1.0) Robot 0.7 ± 0.3 (0.3–0.9) 0.6 ± 0.1 (0.6–0.7) 0.7 ± 0.1 (0.6–0.7) 0.7 ± 0.0 (0.6–0.7) 0.7 ± 0.0 (0.7–0.7) 0.7 ± 0.0 (0.7 ± 0.7) 0.8 ± 0.3 (0.3–1.0) Manual 0.6 ± 0.3 (0.3–0.9) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.1 (0.3–0.6) 0.5 ± 0.2 (0.3–0.7) 0.6 ± 0.1 (0.4–0.7) 0.5 ± 0.1 (0.3 ± 0.6) 0.7 ± 0.4 (0.3–1.0) Note: values are mean ± SD (range) Abbreviations: SSWS = self selected walking speed \n\nBODY.DISCUSSION:\nThe primary purpose of this pilot study was to compare the efficacy of locomotor training implemented using a Lokomat robotic gait orthosis versus manual-BWSTT in a sample with chronic locomotor deficits post-stroke. In conducting this study, we sought to determine the key parameters and reveal challenges in future randomized controlled trials with larger cohorts. Although statistically significant differences were not apparent between Lokomat and manual groups in this small, pilot trial, our data revealed significantly greater training-related improvements within the Lokomat, but not the manual group. Differential treatment effects produced include: 1) Lokomat group improvements in: self-selected overground walking speed, gait symmetry (SLRabs), fast overground walking speed, lower extremity motor impairment (Fugl-Meyer), function (short physical performance battery), and balance (Berg Balance Scale), and 2) manual group improvements solely in balance outcomes (Berg Balance Scale).\n\nBODY.DISCUSSION.CHANGES IN SELF-SELECTED WALKING SPEED:\nModest improvements in self-selected overground walking speed were not unexpected considering that participants were in the chronic post-stroke phase in which recovery is expected to be minimal. The minimal detectable change (MDC) necessary to conclude clinically significant change in gait speed has occurred ranges from 0.07–0.36 m/s in a post-stroke population [39]. Therefore, the 0.1 m/s increase from the mean baseline value revealed in the Lokomat group was not only statistically significant, but also clinically important with an effect size of 0.32. This modest, but significant, effect is especially notable considering the small treatment dose in this preliminary work. Despite the statistically non-significant between-group difference, it is also notable that participants in the Lokomat group increased overground gait speed by 16% over baseline, whereas those in the manual group advanced by only 4.8%. The magnitude of this difference suggests a potential clinical advantage of Lokomat training. While the overall outcome of this pilot study provides further evidence for the efficacy of locomotor training, the lack of statistical evidence supporting superiority of either Lokomat or manual form of locomotor training highlights inconsistencies between previous studies. Our results agree with investigations during the acute and subacute post-stroke stages using the Lokomat [18] and a robotic gait trainer [17] in which differences were noted within groups, but no differences were identified in the extent of improvement between robot and manual groups. However, in their recent publication, Hornby et al. [20] studied a sample of hemiparetic individuals of greater chronicity (i.e. 4–6 yrs post-stoke) and with lower baseline function (i.e. 0.4 m/s preferred gait speed) than our participant pool and reported greater increases in overground gait speed in a manual-BWSTT group compared with a Lokomat trained group. While speculative at this point, a secondary reduction in cardiorespiratory capacity of chronic stroke survivors [38] suggests that participants with long-term functional deficits may benefit from the aerobic training induced by the higher metabolic cost required for manual-BWSTT [40]. Results of the 6-minute walk test highlight this potential effect. A statistically significant improvement of 34 m, indicative of an aerobic conditioning effect, was found in the manually-trained group of Hornby et al., while a statistically non-significant reduction of 24 m was found in our manually-trained group. Further, a lack of correlation between change scores on the 6 minute walk test and self-selected walking speed suggests that increases in gait speed revealed in the present study are more likely to have resulted from factors other than increased physical capacity, including enhanced neural control, and reflect a change in the underlying locomotor pattern. Moreover, our decision to remove the AFO from all participants during locomotor training appears to have proven effective in improving gait symmetry. In contrast, Hornby and co-workers elected not to focus on improving kinematics, performed locomotor training with AFOs in place, and failed to detect changes in gait symmetry. Future investigations comparing Lokomat versus manual training with a common goal of improved kinematics at different stages of chronicity, may provide more definitive insight into an approximate timeline of beneficial use of one approach over the other.\n\nBODY.DISCUSSION.CHANGES IN GAIT SYMMETRY:\nOur intent throughout locomotor training, whether delivered using the Lokomat or manually, was to normalize gait kinematics during stepping, while simultaneously controlling for variables of BWS and stiffness and treadmill speed. Consistency of training variables in both groups enabled us to discern important differences between motor learning induced by Lokomat and manual-BWSTT. Kinematic improvements in paretic step length symmetry were noted only in the Lokomat group, suggesting greater benefits of consistent, normalized kinesthetic input delivered automatically at a constant guidance force to both lower extremities during gait. In contrast, the inconsistency in both kinematic stepping patterns and manual cues to the hemiparetic leg with therapist-determined level of assistance appears to be a limitation to improvements in gait symmetry, thereby supporting previous research [20]. Further improvements in gait symmetry within the Lokomat group may have arisen from the safe removal of the foot straps in 3 participants. Foot straps are included as part of the standard Lokomat package and are meant to passively set the ankle in neutral and enable foot clearance. Generation of paretic leg propulsive forces is correlated with gait speed, effective step length symmetry [26] and plantarflexion activity during late stance [41]. For these reasons, we strongly encouraged active plantarflexion/push-off and provided verbal and tactile cues in an effort to induce motor learning and voluntary execution of plantarflexion. Examining individual subject changes in gait speed and symmetry, we noted that two of the three participants who were able to train without foot straps demonstrated the most remarkable improvements in step length symmetry. Though we searched for other commonalities between these participants, including sensorimotor impairment scores, initial functional level, location and type of lesion, time since stroke, and age, the one similarity was the removal of the foot strap during training. From a biomechanical perspective, the automated symmetrical step length of the Lokomat would have forced the propulsive forces of the ankle plantarflexors to be initiated posterior to the subject's center of mass (COM) at preswing. A strong relationship between step length symmetry and propulsive force symmetry in addition to the importance of the plantarflexors to propulsive force supports this premise [26,42]. However, further investigations conducted without the use of the foot straps in a larger cohort are necessary to address this issue definitively. At this point we are only able to speculate that a more significant training effect was induced by the opportunity to experience active ankle movement and a normal range of ankle motion while in the Lokomat.\n\nBODY.DISCUSSION.CHANGES IN BALANCE:\nResults also revealed significantly improved balance scores producing small to moderate effect sizes on the BBS in both groups. Scores fell within the range in which each 1-pt increase translates to a 6–8% decrease in fall risk. Therefore, the 1.4-pt improvement following Lokomat training and the 4-pt improvement following manual training equates to an 8–14% and 24–32% reduction in fall risk, respectively [43]. These results are not surprising given that treadmill training with or without the Lokomat exposes the central nervous system to several sources of conflicting sensory information, thereby constantly challenging sensory re-weighting processes. Throughout training, proprioceptive inputs from the lower extremity mimic an appropriate stepping pattern on a moving support surface while vestibular and visual cues remain relatively stable. Sensory integration training in such challenging situations may have also translated to improved balance scores in our subject sample. Moreover, the importance of active lateral stabilization to the control of static and dynamic posture and prevention of falls is well established. In this respect, the manual group had a particular advantage in inducing balance improvements with increased lateral freedom compared to the constraints imposed by the Lokomat.\n\nBODY.DISCUSSION.COMPARISON OF GAIT TRAINING SPEEDS:\nThe second purpose of this study was to assess effects of training at speeds comparable to preferred walking speeds of non-disabled individuals versus speeds comparable to persons post-stroke. Against our hypothesis, our data revealed no differences attributable to training speed on primary or secondary variables. Our hypothesis was based, in part, on a related study by Sullivan et al. [8], who found that training at speeds approaching normal walking speed (0.89 m/s) improved preferred overground gait speed compared with a considerably slower training speed (0.22 m/s). It is possible that since the mean training speed in our slow group at 0.58 m/s was higher, yet more functional, than the slow group in Sullivan et al., the difference between fast and slow groups was not sufficient to reveal training-related differences. Nevertheless, the slow speed in the current study was representative of the pre-intervention comfortable over ground walking speed of the participants, while the fast speed corresponded to a normal (e.g. non-disabled) gait speed of 1.3 m/s [44]. In this view, the two studies are complementary with results supporting training at or above participants' comfortable over ground walking speed rather than non-functional speeds that are below mean overground gait speed of individuals with stroke.\n\nBODY.DISCUSSION.STUDY LIMITATIONS AND IMPLICATIONS:\nIt may be argued that the automaticity of the Lokomat may have afforded the opportunity to take more steps and, in turn, receive quantitatively more gait training. However, since the mean training speed did not differ between groups, the difference in the number of steps taken would likely be minimal. Moreover, our goal was to evaluate the effectiveness of the Lokomat compared to manual training within a 30 min time frame typically allotted in clinical settings. As with most pilot studies, the small sample size and resultant low statistical power limit interpretation of this study. However, given that participants demonstrated significant improvements after only 12 treatment sessions in the chronic post-stroke stage, the small to moderate effect sizes are promising. Our results support the original intent of the present pilot study, which was to determine if a larger clinical trial was plausible and should be conducted. This study was different from previous studies because we controlled for many factors such as handrail use, orthotic use, the amount of body weight support, and we placed emphasis on normalizing kinematics during training in order to isolate the specific effects of automated vs. manually-assisted treadmill training. Thus, we were able to show that subjects benefited from training with the Lokomat for a number of performance metrics. One product of our pilot study is tangible results from which to project requisite sample size(s) for future randomized controlled trials designed to definitively evaluate the efficacy of Lokomat compared to manual training. Our primary outcome, self-selected overground walking speed, revealed a between group effect size of 0.59 favoring Lokomat vs. manual training with a probability of 0.6. From this we determined that 51 subjects per group are necessary to detect significant between-group differences. For paretic step length ratio, the demonstrated between-group effect size was 0.73 favoring Lokomat vs. manual training with a probability of 0.70 which translates to a projected sample size of 34 subjects per group. Finally, for fast walking speed, our data revealed a between-group effect size of 0.70 favoring Lokomat vs. manual training at a probability of 0.69 which projects to a sample size of 37 subjects per group to detect between group differences. All sample sizes were projected assuming 80% power at a 5% level of significance.\n\nBODY.DISCUSSION.RECOMMENDATIONS:\nWhile these early, positive findings are encouraging, taken together with the disparate findings reported in the current literature [18-20,45,46], there is a clear need to pursue both the questions regarding efficacy of locomotor training, in general, and robotic-driven locomotor training specifically. We recommend a follow-up study based on our sample size calculations to: probe whether these findings will be reproduced in a larger sample, determine additional differential effects that may not have been revealed in this short pilot trial and test for retention of training effects over an extended period of weeks to months post-training. Further, the advantages and disadvantages of each approach to locomotor training should be weighed in terms of cost-effectiveness, ease of application, and consistency of treatment before definitive conclusions regarding Lokomat use in stroke rehabilitation settings may be drawn. Early evidence favoring locomotor training [9] as an effective intervention post-stroke is tempered by the personnel costs involved (2–4 therapists/trainers), which are unrealistic for the majority of clinical settings. Indeed, many clinics and laboratories that deliver locomotor training depend on considerable volunteer and/or student manpower to simply conduct locomotor training [47] let alone achieve financial feasibility [48]. Equally important is the considerable risk of injury to the trainers representing a significant liability for health care administrators. In this light, equivalent functional outcomes achieved between Lokomat and manual locomotor training represent an favorable result in which Lokomat training may be used in place of manual training to benefit a larger proportion of affected individuals. Further, as demonstrated in the present study, when administered carefully and systematically, robotic-driven motor learning appears to promote adaptation at the level of the locomotor pattern rather than simply offering aerobic conditioning or non-specific changes that contribute to increased gait speed. Long-term retention of these locomotor adaptations is desired and the target of future investigation beyond this initial pilot study. Further research is required to identify the ideal population (i.e. hemiparetic chronicity, severity) for locomotor training, especially robotic-driven approaches to locomotor training, and to elaborate the critical parameters of effective locomotor training, including the ideal amount of variability in kinematic guidance and the most effective schedule for adjusting and ultimately withdrawing kinematic guidance.\n\nBODY.CONCLUSION:\nWhile this pilot study revealed no between-group differences in efficacy of Lokomat versus manual locomotor training, significant within-group effects reveal positive effects of locomotor training and suggest that Lokomat training may offer a potential advantage of this mode over manual BWSTT. A modest dose of Lokomat training is effective for improving overground walking speed and gait symmetry, and other lower extremity impairments and physical function in persons with chronic hemiparesis post-stroke. Consequently, larger, randomized controlled trials are warranted.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nKPW assisted in experimental design, conducted the experiments and data collection, analyzed the data, and was responsible for the initial drafting of the manuscript. CP conceived the study and experimental design, assisted with the experiments and data collection, and helped draft the manuscript. Both authors read and approved the final manuscript.\n\n**Question:** Compared to Body-weight supported treadmill training combined with Lokomat (Pre-test) what was the result of Body-weight supported treadmill training combined with Lokomat (Post-test) on 6-minute walk test?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
188
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Tissue examination by routine pathology?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
134
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Proinsulin : insulin ratio?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
177
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Cure rate at day 28?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
185
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Anti-TNF-α treatment for deep endometriosis-associated pain: a randomized placebo-controlled trial\n\n ABSTRACT.BACKGROUND:\nEndometriosis is associated with an inflammatory response. Hence infliximab, an anti-TNF-α monoclonal antibody, might relieve pain.\n\nABSTRACT.METHODS:\nA randomized placebo-controlled trial was designed with 21 women with severe pain and a rectovaginal nodule of at least 1 cm. After 1 month of observation, three infusions of infliximab (5 mg/kg) or placebo were given. Surgery was performed 3 months later and follow-up continued for 6 months. The primary end-point was pain (dysmenorrhea, deep dyspareunia and non-menstrual pain) rated at each visit by the clinician and on a daily basis by the patient who in addition scored pain by visual analog pain scale and analgesia intake. Secondary end-points included the volume of the endometriotic nodule, pelvic tenderness and the visual appearance of endometriotic lesions at laparoscopy.\n\nABSTRACT.RESULTS:\nPain severity decreased during the treatment by 30% in both the placebo (P < 0.001) and infliximab groups (P < 0.001). However, no effect of infliximab was observed for any of the outcome measures. After surgery, pain scores decreased in both groups to less than 20% of the initial value.\n\nABSTRACT.CONCLUSIONS:\nInfliximab appears not to affect pain associated with deep endometriosis. Treatment is associated with an important placebo effect. After surgery, pain decreases to less than 20%. Trials registration number ClinicalTrials.gov: NCT00604864.\n\nBODY.INTRODUCTION:\nEndometriosis is associated with pelvic pain, especially if deep and/or ovarian cystic lesions are present (Koninckx et al., 1991b, 1994). Whether subtle lesions cause pain is not yet substantiated. The association of pain and typical endometriosis was derived from observational studies in which women with pelvic pain have a higher incidence of endometriosis (range: 40–80%) than women with infertility without pain (20–50%) or control groups (5–20%) (Koninckx et al., 1991b). Surgical ablation of typical endometriosis has been reported to decrease pain in several observational studies and in a randomized controlled trial (Sutton et al., 1994, 1997; Jacobson et al., 2001). The strong association between cystic ovarian and deep endometriosis with severe pelvic pain was invariably noted in observational studies, and logistic regression showed deep and cystic endometriosis to be the strongest predictors of pelvic pain (Koninckx and Martin, 1994; Vercellini et al., 1996). Following the surgical excision, pain invariably decreased by some 80% (Donnez et al., 1995; Koninckx and Martin, 1997; Brouwer and Woods, 2007; Darai et al., 2007; Kristensen and Kjer, 2007). The pathophysiology of the association between endometriosis and pain is poorly understood. Several hypotheses have been put forward. First, as endometriosis is a hormonally responsive tissue similar to endometrium, it is reasonable to assume that mini-menstrual bleedings (Brosens, 1997) cause pain because of pelvic irritation by blood, by an inflammatory reaction or by the tension in the micro cysts of the lesions. This hypothesis is supported by a series of observations. During menstruation pain typically worsens and deep lesions feel tender (Koninckx et al., 1996a). At laparoscopy, endometriotic lesions were observed to bleed during menstruation (personal observation). Natural menopause and all medical treatments, which inactivate the endometrium (Vercellini et al., 1997, 2007a), prevent menstruation or decrease menstrual blood loss, including GnRH agonists (Shaw, 1991) and oral contraceptives decrease pain. Inflammatory reaction and neo angiogenesis (Oosterlynck et al., 1993) around endometriotic lesions have been observed during laparoscopy and by pathology. Secondly, in deep lesions, the observed endometriotic invasion of nerve fibers and the association with mast cells (Anaf et al., 2000, 2002, 2004, 2006) might explain the severe pain. Finally, especially deep endometriosis can cause sclerotic compression of ureters and of nerve fibers, as demonstrated by the excision of endometriosis surrounding the sciatic nerve (Batt et al., 2004; Possover and Chiantera, 2007) or the pudendal nerve in cases of menstrual sciatalgia or Alcock syndrome (Robert et al., 1998; Possover and Chiantera, 2007). TNF-α, a pro-inflammatory cytokine, has been implicated in the pathophysiology of endometriosis (Agic et al., 2006). TNF-α levels are increased in peritoneal fluid of women with endometriosis (Bedaiwy et al., 2002), and the levels correlate with severity of disease (Richter et al., 2005). Peritoneal fluid TNF-α is produced locally by activated peritoneal macrophages (Koninckx et al., 1999). TNF-α induces IL-8 secretion by peritoneal mesothelial cells (Arici, 2002). The peritoneal fluid concentrations of TNF-α and IL-8 correlate with the size and the number of active peritoneal lesions (Bullimore, 2003). Serum TNF-α levels are increased, and monocytes from patients with endometriosis release more TNF-α in vitro compared with monocytes from controls (Braun et al., 1996). Peritoneal fluid levels of MCP-1 are increased in patients with endometriosis. TNF-α, IL-8 and MCP-1 drive an inflammatory Th-1 type response in the peritoneal fluid of patients with endometriosis (Akoum et al., 1995). The anti-inflammatory effect of blocking TNF-α by monoclonal antibodies (e.g. infliximab) or by soluble TNF-α receptors (e.g. etanercept) has been demonstrated in vivo in animal models and also in the human. The clinical effectiveness of blocking TNF-α has been demonstrated in inflammation driven conditions including Crohn's disease and rheumatoid arthritis but not in severe endometriosis (Shakiba and Falcone, 2006). In baboons with laparoscopically confirmed endometriosis, TNF-α blockade with p55 soluble TNF-α receptors results in inhibition of the development and growth of endometriotic implants (D'Hooghe et al., 2006). The size of peritoneal red lesions was decreased in comparison with a control group (Barrier et al., 2004), but there was no increase in pregnancy rates (Falconer et al., 2007). In rats with ectopically transplanted endometrial tissue, the administration of recombinant human TNF-α binding protein-1 (r-hTBP-1) resulted in defective development of implants compared with controls (D'Antonio et al., 2000). TNF-α mediated inflammation may be a causal factor in the pain associated with endometriosis and blocking TNF-α appears to inhibit the development of the disease in animal models. We evaluated the effect of infliximab on pain in women with rectovaginal endometriosis at a dose proven to be effective in inflammatory bowel disease and rheumatoid arthritis.\n\nBODY.MATERIALS AND METHODS.PATIENTS:\nAll patients (aged 18–50 years) were recruited from a single, tertiary referral hospital at Leuven University, Belgium. All women suffered from pelvic pain and were scheduled for surgical excision of a rectovaginal endometriotic nodule of at least 1 cm in diameter with or without cystic ovarian endometriosis. None of the women had previously been operated for deep endometriosis. All women had a regular cycle (25–40 days) and moderate to severe pelvic pain as defined by their score on the Biberoglu–Behrman scale. If previously treated with hormonal medication, including progestagens, GnRH analogs, Danazol or oral contraceptives, at least 3 months had elapsed and they had at least two menstrual cycles since stopping treatment. The study was reviewed and approved by the institutional review board of KULeuven. Written informed consent was obtained from each subject. If not sterilized the patient had to agree to use a double-barrier method of contraception for the duration of the study, and up to 6 months after receiving the last infusion with infliximab. In view of infliximab's known side-effect profile, the following were exclusion criteria: (i) old or currently active TB; (ii) evidence of serious infections in the previous 3 months; (iii) documented HIV infection, active hepatitis-B or C, or an opportunistic infection (e.g. herpes zoster, cytomegalovirus, pneumocystis carinii, aspergillosis, histoplasmosis or mycobacteria other than TB) in the previous 6 months; (iv) previous transplant surgery, a lymphoproliferative disorder or other malignancy; (v) positive cervical cytology in the previous 6 months; (vi) previous treatment with infliximab or, any drug known to affect TNF-α levels, e.g. pentoxifylline, thalidomide and etanercept, or any human/murine recombinant products; (vii) known allergy to murine products; (viii) recent use of other investigational drugs within 1 month of recruitment or within five half-lives of the investigational agent, whichever was longer and (ix) any hematological or biochemical abnormalities on routine screening. Subjects were also excluded if there was pelvic pathology on transvaginal ultrasound (TVU) scan other than small uterine fibroids (<4 cm in diameter) or an ovarian endometrioma or endometriotic nodule.\n\nBODY.MATERIALS AND METHODS.STUDY DESIGN:\nThis study was a single center, randomized, double-blind, placebo-controlled pilot study in 21 women with deep endometriosis-associated pain in whom excisional surgery was planned as therapy. Randomization was performed in a 2–1 ratio for active and placebo treatments, respectively, 14 women thus receiving active treatment and seven receiving placebo. In one patient of the infliximab group, with a deep nodule diagnosed by TVU only, no deep endometriotic nodule was found during surgery. Both groups were similar for age, weight, height, blood pressure, heart rate, days of bleeding, age of menarche, number of pregnancies and spontaneous abortions, leucocyte and blood cell count and liver function tests. Patients receiving placebo (n = 7) and infliximab (n = 13) were 30.7 ± 5.5 and 28.4 ± 4.5 years old with a weight of 52.7 + 5.4 and 62.5 ± 7.4 kg (P = 0.002), a height of 161 + 5 and 162 + 5 cm, a cycle length of 29 + 2 and 32 + 5 days, a systolic blood pressure of 127 ± 15 and 120 ± 12 mm of mercury, a diastolic blood pressure of 78 ± 11 and 78 ± 7 mm of mercury and a heart rate of 79 ± 14 and 83 ± 12, respectively. The study period consisted of 40 weeks, i.e. at least 4 weeks pre-treatment evaluation, a 12 week treatment period followed by surgery and 24 weeks follow-up period. Visits were scheduled at least 4 weeks before the start of treatment (Visit 1, Week 4), at the start of treatment (Visit 2, Week 0), then 2 (Visit 3), 4 (Visit 4), 8 (Visit 5) and 12 (Visit 6) weeks after the start of treatment and 6 (Visit 7) and 12 (Visit 8) weeks after surgery. Infliximab or placebo was administered as a slow infusion of 250 ml at the beginning of the cycle (Week 0 or Visit 2) and repeated after 2 (Visit 3) and 6 weeks (Visit 4) reflecting the typical induction treatment scheme of 0, 2 and 6 weeks given in other inflammatory pathologies, such as Crohn's disease and rheumatoid arthritis. Women were monitored for adverse effects for 1 h post-infusion. A pregnancy test was performed prior to the infusion and on Week 8. At each visit and during the follow-up period, safety was monitored through standard blood tests, vital signs and breast examination. Adverse events were reviewed by a Safety Monitoring Committee every 3 months. The primary end-point was the effect of infliximab treatment upon pelvic pain including the intake of pain killers. Secondary end-points included the volume of endometriotic nodules assessed clinically and on TVU, the macroscopical appearance of endometriotic lesions during surgery and the extend of endometriosis. The revised American Fertility (rAFS) classification system was not used to score endometriosis since the severity of deep endometriosis is poorly reflected in the rAFS score.\n\nBODY.MATERIALS AND METHODS.CLINICAL EVALUATIONS OF ENDOMETRIOSIS AND PAIN ASSESSMENT:\nPain was assessed by one gynecologist (PK) at each visit using a modified Biberoglu–Behrman scale, scoring from 0 (no pain) to 3 (severe pain) dysmenorrhea, deep dyspareunia, chronic pelvic pain, pelvic tenderness and pelvic induration. In addition the patients independently recorded daily dyspareunia, dysmenorrhea and pelvic pain and the intake of Ibuprofen 100 mg tablets. In addition, they recorded weekly by visual analog pain scale (VAS), the average maximum tolerated pain (i.e. before intake of a pain killer) over the last 7 days. Ibuprofen was taken as required up to a maximum of 2.4 g/day; additional pain medication was permitted with documentation. A TVU was performed during the screening period and at Visits 2, 3, 5 and 6 to measure deep endometriosis volume and endometrial thickness (Timmerman et al., 2002). Patients recorded daily the amount of vaginal blood loss.\n\nBODY.MATERIALS AND METHODS.TREATMENTS, RANDOMIZATION AND BLINDING:\nInfliximab an IgG monoclonal anti-TNF antibody was supplied by Centocor as a lyophilized solid containing 100 mg of infliximab IgG, 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water for injection. The placebo was supplied as a lyophilized solid containing 0.5 g of sucrose, 6.1 mg of dibasic sodium phosphate dihydrate, 2.2 mg of monobasic sodium phosphate monohydrate and 0.5 mg of polysorbate 80 in a 20 ml vial for reconstitution in 10 ml of sterile water. The vials of infliximab/placebo were supplied by Centocor, stored at 2–8°C and reconstituted immediately before each administration. All investigators, research nurses and patients were blinded throughout the study. Randomization (prepared by Centocor Paris) was performed by consecutive sealed envelopes opened by the pharmacist prior to the preparation of medication. Randomization code was broken only after the database had been locked.\n\nBODY.MATERIALS AND METHODS.SURGERY AND OTHER PROCEDURES:\nSurgery for endometriosis was performed as reported (Koninckx and Barlow, 1999) 4–6 weeks after the last infliximab dose. A follow-up visit was planned 4–9 weeks after surgery (Visit 7) and a final visit to assess safety was performed between 26 and 29 weeks (Visit 8). During surgery, an endometrial biopsy was taken and subsequently processed for routine pathology.\n\nBODY.MATERIALS AND METHODS.STATISTICS:\nThis study was an exploratory trial, and thus not powered to detect small differences. An important decrease of pain would have been detected, since with a SD of 2, a difference in BB score of 3 would have been detected with a power of 90%. To detect small differences, e.g. of one point with a power of 80% a RCT of 120 women would have been necessary. Statistical analysis was performed with the SAS system (SAS/STAT users guide, 1988). Wilcoxon Rank sum test was used to evaluate differences of means at each visit for each variable. Since in this study obviously two possible effects were present simultaneously, i.e. the effect of Infliximab treatment and the effect of placebo or surgery, a two-way analysis of variance (proc GLM, general linear methods) was performed, analysing simultaneously for each end-point the effect of treatment (control or anti-TNF-α) and the placebo or surgery effect (the difference between two treatment periods). Baseline was defined as the mean of Visits 1 and 2, the early treatment period as the mean of Visits 3 and 4 and the late treatment period as mean of Visits 5 and 6. For the effect of surgery, baseline, early and late treatment periods were compared with the post-operative period (mean of Visits 7 and 8). Since pain was exacerbated during menstruation, the menstrual period, defined as the first 4 days of the cycle was analysed separately. A menstrual cycle was defined as starting with the first day of bleeding and lasting for 28 days. The effect upon pain was evaluated from the 5 BB entries made by the physician, and the 3 BB entries, the VAS scale and the intake of ibuprofen and other painkillers recorded by the patients. Analysis of pain killer intake was done twice: a first analysis was done considering only the ibuprofen intake (the number of tablets of ibuprofen taken); in a second analysis other painkiller intake was taken into account: if other painkillers had been taken the number of tablets taken was added to the number of ibuprofen tablets taken; if other strong pain killers had been injected, e.g. a morphine product, these injections were arbitrarily scored as six tablets in order to obtain the total score. In addition, the effect of treatment upon two calculated total pain scores combining the individual BB entries and pain killer intake was calculated. A first total pain score consisted of the sum of dysmenorrhea, deep dyspareunia and pelvic pain (both as assessed by the clinician and by the patients). In order to take also the ibuprofen intake into account, a second total pain score was calculated by multiplying the total daily pain score with the number +1 (in order to avoid to multiply by zero) of ibuprofen tablets taken during that day. Both an intention to treat analysis, considering all 21 patients included, and an analysis of the 20 women with endometriosis was performed. Since results were identical only the latter will be given in the manuscript. Means and SE are given unless indicated otherwise. For the safety analysis, obviously all 14 women treated with Infliximab were included. Results are presented as mean + SE. Spearman correlation was used for correlation analysis.\n\nBODY.RESULTS:\nThese women with endometriosis had very severe pain before treatment with a total BB score of 12.2 on a scale of 15 (Figs 1 and 2). The baseline BB scorings by the clinician were calculated as 2.7 + 0.09 for dysmenorrhea, 2.3 + 0.19 for deep dyspareunia, 2.2 + 0.12 for chronic pain, 2.2 + 0.14 for pelvic tenderness, 2.8 + 0.07 for pelvic induration, with a sum of the pain scores of 7.1 + 0.24 and a total BB score of 12.2 + 0.28. Figure 1:Dysmenorrhea, deep dyspareunia and chronic pelvic pain, as assessed by the clinician (upper graphs) and by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment: NS, baseline versus late treatment: >0.003 for all. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. Figure 2:Induration, pelvic tenderness and total Biberoglu–Behrman score together with VAS scales as recorded at each visit and weekly by the patient in her diary, before treatment, during the 12 week treatment period (shaded area) and after surgery.Baseline versus early treatment, NS; baseline versus late treatment, >0.003 for all except NS for VAS dysmenorrhea. Baseline and late treatment versus post-surgery: P < 0.001 for all. Infliximab: NS for all. As shown in Figs 1, 2 and 3, during the 12 week treatment period a similar exponential decrease in pain of some 25–30% was observed in both the control and the infliximab group, compatible with a placebo effect. No statistically significant differences between placebo and infliximab treatment could be identified. The strong and significant placebo effect and the absence of an infliximab effect were consistently found for all pain estimations in this study, i.e. the five scorings by the clinician and the calculated total scores (i.e. dysmenorrhea, deep dyspareunia, chronic pain, pelvic tenderness, the sum of the 3 BB pain scores and the total BB score) and the pain recorded in the dairy by the patients (i.e. the 3 BB scores, the visual analog scales, the pain killer intake and both calculated total scores, i.e. with or without taking pain killer intake into account). The placebo effect was not significant for the early treatment period (Visits 3 and 4) but highly significant for the late treatment period (Visits 5 and 6) both by two way analysis of variance (P < 0.003 to 0.001 for all) and when the placebo (Wilcoxon, P < 0.001) and the infliximab group (Wilcoxon, P < 0.001) were analysed separately. No effect of treatment was found upon the mean diameters of the nodules as measured by TVU. For the placebo group (n = 7) and the infliximab group (n = 13), the diameters were 15.2 ± 4.6 and 13.6 ± 3.2 mm, during Visit 3, 15.1 ± 5.12 and 14.25 ± 3.5 mm, during Visit 5, 13.5 ± 4.9 and 15.6 ± 3.5 mm and during Visit 6, 13.2 + 3.4 and 15.1 + 2.38 mm. Endometrial thickness was not affected by treatment, being at baseline and at the end of the treatment period for the infliximab group 5.2 (range 1.3–18) and 7.8 (1.9–11) mm and for the placebo group 7.7 (1.8–23) and 8.2 (3–15) mm, respectively. During surgery, no obvious differences were observed in the extend of the disease, the macroscopic aspect of endometriosis (vascularization and sclerosis), the duration of surgery and bleeding estimates. Routine pathology (FC) also showed no obvious differences between the two groups. After surgery, all pain estimates decreased to less than 10% of the baseline in both groups (Figs 1 and 2), and no differences were found between the placebo and the infliximab group (two-way analysis of variance). This decrease of pain after surgery was highly significant (P < 0.001) for all pain estimates at all visits. During treatment all side-effects were reviewed by the safety committee. One patient had 2 days after the second infliximab infusion an acute tonsillitis, which resolved quickly by antibiotic treatment. One patient had a mild (infliximab) infusion reaction during the 3rd infusion. One patient developed an acute leukemia 4 months after the last infliximab infusion. Two infliximab patients, who failed to use contraception, became pregnant 6 and 10 weeks after surgery, respectively; one miscarried spontaneously at 10 weeks and the other delivered a healthy baby at term. One infliximab patient had myalgia for a few days after the second infusion and another infliximab patient had a bad taste in the mouth for a few days; both events were considered unrelated to the drug by the safety review committee. There were no AEs reported in the placebo patients. Figure 3:Ibuprofen intake and total pain calculated from the patient dairy. A Spearman correlation between all entries of the whole dataset was performed. We realize that this crude analysis is strictly incorrect since all entries were used as independent variables, and that this blind analysis carries the risk of spurious correlations. Since correlations were so strong, some seem worth mentioning. There was a strong intercorrelation (P < 0.001 for all) between all pain estimates by the physician (dysmenorrhea, deep dyspareunea and chronic pain) and by the patients (dysmenorrhea, deep dyspareunea, chronic pain, VAS scales and ibuprofen intake), suggesting that pain estimates are not entirely independent. Over the whole observation period, the infliximab group had a slightly higher intake of pain killers (P < 0.01), and higher dysmenorrhea scores (P < 0.001 for physician assessment, for patient VAS scales and for patient diary). The volume of the nodule assessed by TVU correlated with the pelvic induration assessed by the physician (P = 0.04) but surprisingly not with any of the pain estimates nor with ibuprofen intake. Unexpected correlations were found between weight and temperature (P < 0.001), between temperature and dysmenorrhea (P < 0.001) and deep dyspareunea (P < 0.001), and between pulse rate and pain estimates (P < 0.001).\n\nBODY.DISCUSSION:\nTo the best of our knowledge, this is the first randomized, placebo-controlled trial to assess the effect of an anti-TNF-α drug in the treatment of deep endometriosis-associated pain. Women with deep lesions were chosen as the study group for two reasons. First, these lesions were diagnosed on clinical examination rather than at laparoscopy and the women participated in the study while awaiting definitive surgical treatment. Second, for deep endometriosis the association between pain and endometriosis is much stronger than for other disease types (Koninckx et al., 1991a; Vercellini et al., 2007b). Women with deep endometriosis have severe pain close to the maximum on a BB painscale, the painful nodules can be confirmed by clinical exam and less than 5% is pain free (Koninckx et al., 1996b). A study of women with typical lesions only would carry a much higher risk of including women in whom pain is not caused by the endometriosis. In typical endometriosis pain is highly variable, is rarely very severe and 30–50% of women are pain free. Women with deep endometriosis may thus be a preferred group to evaluate drug effects on endometriosis-associated pain. The observed placebo effect was unexpectedly high in these women, and is consistent with previous reports albeit in women with less severe pain (Sutton et al., 1994, 1997). Placebo effect was observed for all pain measures, including tenderness on pelvic examination. The absence of effect upon pelvic induration, indirectly confirms that the effect on pain was a placebo effect and that the clinician remained objective. The strong placebo effect can be explained by the patient perception of the importance of an intravenous infusion followed by the close observation in hospital for 1 h. In addition, the enthusiasm of the researchers who became convinced of the efficacy of infliximab could have been conveyed to the patients. Indeed, two-thirds of the patients reported a greater than 50% decrease in pain, with little effect in the remaining third. Understanding the mechanisms involved in this important decrease of pain by more than 50% (Fuente-Fernandez et al., 2006; Pacheco-Lopez et al., 2006; Beauregard, 2007; Benedetti, 2007; Koshi and Short, 2007; Lidstone and Stoessl, 2007; Olshansky, 2007) could lead to clinical effective treatments of endometriosis related pain (Rostkowska-Nadolska, 2007). The lack of efficacy for infliximab as a treatment for deep endometriosis-associated pain was unexpected because of the widely held belief that inflammation is a major cause of pain in endometriosis (Vercellini et al., 2007a). However, the pathophysiology of the severe pain associated with deep endometriosis may be different from that caused by typical lesions, i.e. inflammation might be more important in superficial peritoneal endometriosis whereas nerve invasion or compression is more important in deep lesions (Anaf et al., 2000, 2002, 2004, 2006). This absence of effect upon pain is consistent with the absence of effect during surgery or after examination by routine pathology. Whether another treatment protocol or a higher dose would be effective cannot be excluded. We have scrutinized the literature on the medical treatment of endometriosis-associated pain. The evidence of efficacy may be weak as the blinding in most studies appears inadequate. Researchers and patients were able to guess whether individuals were randomized to placebo or active treatment if menstruation was prevented or if there were major side-effects such as hot flushes, or recognizable physical signs such as vaginal atrophy. In addition, conclusions are usually based upon a reduction in the total pain score and all drugs that abolish menstruation will thus by definition be effective in reducing dysmenorrhea. Given the strong correlation between pain symptoms it remains uncertain whether these treatments are effective for all pain symptoms associated with endometriosis or simply dysmenorrhea alone. The correlations found should be regarded cautiously since the study is small, and since some might be spurious. It was surprising not to find a correlation between the size of the nodules measured by TVU and the pain estimates. Second, that dysmenorrhea correlated negatively with age and age of menarche is an intriguing observation as are the systematic correlations of pain estimates with temperature, blood pressure and pulse rate. That anticipation of a clinical exam could have increased blood pressure and pulse rate more in women with more severe pain remains speculative. When designing this study, we were concerned about the theoretical possibility of increasing post-operative complication rates as a result of infliximab's effect on the immune system. The existing evidence was reassuring, i.e. there were no differences in length of hospital stay or surgical complications between patients with Crohn's disease who received infliximab 2 months before surgery (n = 22) or 1 month after surgery (n = 13) compared with matched controls (Parsi et al., 2002). Since then, two retrospective studies in patients with Crohn's disease have similarly concluded that the use of infliximab, as well as steroids or immunomodulators, before abdominal surgery does not increase the risk for post-operative complications (Colombel et al., 2004; Marchal et al., 2004). In our study, there were no differences in post-operative complication rates between the groups. Given that we only recruited women with deep endometriosis, we accept the possibility that anti-TNF-α treatment might have an effect on other types of endometriosis, e.g. minimal disease with a marked inflammatory component. However, we urge caution about conducting a study to evaluate the effect of anti-TNF-α drugs in such patients. We are not convinced that the potential benefits outweigh the risk of serious side-effects, the high cost of anti-TNF-α drugs and the ethical problems associated with not treating minimal disease surgically at the time of diagnosis. This study confirmed the effectiveness of surgical excision of deep endometriosis upon pain (Koninckx and Martin, 1994; Redwine and Wright, 2001; Wright and Redwine, 2002; Donnez et al., 2004; Garry, 2004). We do not know to what extend a placebo effect contributes to the surgical outcome. In conclusion, infliximab appears to have no important beneficial effect upon pain associated with deep endometriosis. We observed an overall placebo effect of 25%, which reached over 50% in two-thirds of the women, emphasizing the need for well conducted, double-blind, randomized, placebo-controlled studies when evaluating novel treatments for pain. The efficacy of surgical excision upon pain was confirmed, as was the safety of infliximab treatment in the pre-operative period.\n\nBODY.FUNDING:\nThis trial was performed as an investigator initiated trial. Support was received from Centocor.\n\n**Question:** Compared to Placebo what was the result of Infliximab on Macroscopic aspect of the tissue?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
175
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Dihydroartemisinin-piperaquine versus chloroquine to treat vivax malaria in Afghanistan: an open randomized, non-inferiority, trial\n\n ABSTRACT.BACKGROUND:\nAfghanistan's national guidelines recommend chloroquine for the treatment of Plasmodium vivax infection, the parasite responsible for the majority of its malaria burden. Chloroquine resistance in P. vivax is emerging in Asia. Therapeutic responses across Afghanistan have not been evaluated in detail.\n\nABSTRACT.METHODS:\nBetween July 2007 and February 2009, an open-label, randomized controlled trial of chloroquine and dihydroartemisinin-piperaquine in patients aged three months and over with slide-confirmed P. vivax mono-infections was conducted. Consistent with current national guidelines, primaquine was not administered. Subjects were followed up daily during the acute phase of illness (days 0-3) and weekly until day 56. The primary endpoint was the overall cumulative parasitological failure rate at day 56 after the start of treatment, with the hypothesis being that dihydroartemisinin-piperaquine was non-inferior compared to chloroquine (Δ = 5% difference in proportion of failures).\n\nABSTRACT.RESULTS:\nOf 2,182 individuals with positive blood films for P. vivax, 536 were enrolled in the trial. The day 28 cure rate was 100% in both treatment groups. Parasite clearance was more rapid with dihydroartemisinin-piperaquine than chloroquine. At day 56, there were more recurrent infections in the chloroquine arm (8.9%, 95% CI 6.0-13.1%) than the dihydroartemisinin-piperaquine arm (2.8%, 95% CI 1.4-5.8%), a difference in cumulative recurrence rate of 6.1% (2-sided 90%CI +2.6 to +9.7%). The log-rank test comparing the survival curves confirmed the superiority of dihydroartemisinin-piperaquine over chloroquine (p = 0.003). Multivariate analysis showed that a lower initial haemoglobin concentration was also independently associated with recurrence. Both regimens were well tolerated and no serious adverse events were reported.\n\nABSTRACT.CONCLUSIONS:\nChloroquine remains an efficacious treatment for the treatment of vivax malaria in Afghanistan. In a setting where radical therapy cannot be administered, dihydroartemisinin-piperaquine provides additional benefit in terms of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nABSTRACT.TRIAL REGISTRATION:\nThe trial was registered at ClinicalTrials.gov under identifier NCT00682578.\n\nBODY.BACKGROUND:\nPlasmodium vivax is associated with less mortality than Plasmodium falciparum, but still exerts a considerable burden of disease globally [1] and is a major cause of morbidity in Asia [2]. In endemic areas it is a particular problem of children and pregnant women in whom it is associated with poor outcomes, notably anaemia and low birth weight [3]. Control measures are confounded by the persistence of dormant hypnozoite stages in the liver, which cause relapses of the infection if radical therapy is not administered. Chloroquine remains the treatment of choice for treatment for the erythrocytic stage of P. vivax infection, but chloroquine resistance is spreading [4]. High level resistance is still confined mainly to Oceania [5] and Indonesia [6], but lower level resistance has been reported in other areas across Asia and South America [4]. Chloroquine was used for more than 50 years as the first-line drug for all forms of malaria in Afghanistan. Chloroquine continues to be first-line drug treatment as a mono-therapy for slide-confirmed P. vivax malaria and is also used in combination with sulphadoxine-pyrimethamine for presumptive treatment of clinical malaria episodes when accurate laboratory diagnosis is unavailable. Radical treatment with primaquine is not currently recommended because of the risk of oxidant haemolysis in patients with glucose-6-phosphate dehydrogenase (G6PD) deficiency, as testing for G6PD deficiency is not available. Limited access to prompt diagnosis and treatment, self-medication with low quality medicines [7] and non-adherence to the national treatment policy are all potential contributors to drug resistance in Afghanistan. To date, anti-malarial therapeutic monitoring in Afghanistan has largely been conducted at the Malaria Reference Centre, Jalalabad (Nangarhar province) in the eastern region of the country near the border with Pakistan. In this area, chloroquine resistance is established in P. falciparum [8] but appears not to be a major problem for P. vivax [9,10]. Relatively little data exists for the rest of the country; sulphadoxine-pyrimethamine has been shown to have good efficacy against P. falciparum in Kunduz province [11] and molecular studies indicate that P. vivax resistance to sulphadoxine-pyrimethamine is present at a relatively early stage in Nangarhar and Herat provinces[12]. Since 2004, artemisinin combination therapy (ACT) in the form of artesunate/sulphadoxine-pyrimethamine has been the recommended first-line treatment for P. falciparum infections in Afghanistan. As the correct malaria parasite species may not be identified in patients presenting with fever, P. vivax infections in Afghanistan will inevitably be treated with ACT [9]. For operational reasons, there may an argument for treating both vivax and falciparum malaria with the same drug regimen. The fixed-dose combination of dihydroartemisinin co-formulated with the bisquinoline piperaquine represents a promising alternative to chloroquine. Piperaquine is related to 4-aminoquinolines but it retains activity against chloroquine-resistant P. falciparum [13] and several studies from Indonesia and Papua New Guinea have indicated that dihydroartemisinin-piperaquine is also safe and effective for the treatment of chloroquine-resistant vivax malaria, with more long-lasting post-treatment prophylactic effects than other forms of ACT [5,14,15]. Dihydroartemisinin-piperaquine is relatively expensive (1-2 US$ per treatment course) but has a simple dosing schedule (daily doses for three days). For the purpose of evidence-based decision making, and to obtain better information on the effectiveness of available anti-malarial drugs against vivax malaria in Afghanistan, the relative therapeutic efficacy of chloroquine and dihydroartemisinin-piperaquine in the treatment of vivax malaria was assessed at three sites in Afghanistan.\n\nBODY.METHODS.STUDY AREA AND PARTICIPANTS:\nThe study was conducted from July 2007 to February 2009 at three provincial malaria control centres, one in the east and two in the north of the country. The epidemiology of malaria in Afghanistan is determined by the physical geography of the country, malaria being confined to lower lying areas with sufficient rainfall for mosquito survival consisting of the northern plains (bordering Turkmenistan, Uzbekistan and Tajikistan) [16], the Jalalabad basin to the east (bordering Pakistan) and river valleys that fringe the central mountains to the west and south [17]. The central area of Afghanistan, occupied by the western end of the Hindu Kush mountain range, is relatively free of malaria [18,19]. In Afghanistan, P. vivax remains endemic and accounts for more than 90% of all malaria cases [20]. Cases begin to present in the spring months (May onwards) consistent with periodic relapse from long latency hypnozoites, reach a peak in July and August, and few cases are seen after November. Jalalabad, capital of Nangarhar province, is a referral centre for the whole eastern region and lies adjacent to the Pakistani border where population movement in both directions takes place. The population is multi-ethnic with Pashtoon being the dominant group. The province as a whole (altitudes below 2,000 meters) is generally semiarid but where possible rice is cultivated. Taloqan is the capital of the north-east province of Takhar with a population that is mainly Tajik with significant proportions of Uzbek and Pashtoon. Rice is cultivated on the plain and malaria is a well-known health problem [21]. Maimana is the capital city of the north-west province of Faryab bordering Turkmenistan, with which there is no open border. The population is mainly Uzbek and Turkmen and the region is semi-arid.\n\nBODY.METHODS.ENROLMENT:\nThis was a prospective, open label, randomized controlled trial conducted in patients with microscopically confirmed symptomatic vivax malaria who were aged three months and older. All febrile patients over three months of age presenting to the sites were screened and enrolled according to preset criteria. A standard data sheet was used to record demographic information, details of symptoms and their duration, and previous anti-malarial medications. Clinical examination findings and vital signs were documented, including axillary temperature measured with a digital thermometer. Venous blood samples were obtained for haemoglobin measurement (Hemocue) and white cell count using the counting chamber method. Giemsa-staining of thick and thin blood films was performed to confirm parasite species and parasitaemia by a standard approximation method (40 × number of parasites per 200 white blood cells on the thick film). 10% of slides were cross-checked in the MORU (Bangkok) parasitology laboratory. Approximately 20 μl capillary blood was collected on filter papers for subsequent confirmation of species by PCR and future molecular studies. Slide examination results were considered to be negative after examination of 30 high-power fields of the thick film. The inclusion criteria were slide-confirmed infection with asexual stages of P. vivax, written informed consent by the patient or attending parent/guardian, and a negative urine pregnancy test in women of childbearing age. Exclusion criteria were any clinical or laboratory feature of severe malaria [22], haemoglobin concentration of less than 7 g/dl, concomitant disease that would mask treatment responses, known allergy to any of the study drugs, anti-malarial treatment in the previous month, mixed species Plasmodium infection, pregnancy (or unwillingness to undergo pregnancy testing), lactation, and anticipated inability or unwillingness to complete the 56 day follow-up.\n\nBODY.METHODS.RANDOMIZATION:\nPatients were allocated to the two treatment arms based on a pre-generated randomization list made in blocks of 20 that was produced and held independently of the field teams by a statistician. The individual allocations were kept in sealed, opaque envelopes and opened only after enrolment by the field team. Patients and clinical field workers were, therefore, not blinded to the treatment arm after allocation. Microscopists were blinded to treatment allocation at follow-up examinations.\n\nBODY.METHODS.DRUGS:\nPatients received either quality-controlled chloroquine (IDA, Netherlands) aiming for a target total dose of 25 mg base/kg in divided doses over three days, or dihydroartemisinin-piperaquine (Artekin®, each tablet containing 40 mg dihydroartemisinin and 320 mg piperaquine; Holleypharm, China) aiming for a target total dose of 6/48 mg/kg in divided doses over three days. According to the body weight, individual doses were either rounded to the nearest half or quarter tablet or, if necessary, tablets were crushed, mixed with 5 ml water and the appropriate volume was given. All doses were taken under supervision at the malaria treatment centre and patients were observed for 60 minutes after drug administration. Patients vomiting within this time received the same dose again. Patients who vomited the medication twice were withdrawn from the study.\n\nBODY.METHODS.FOLLOW-UP:\nThe subjects were seen on days 0 to 3 inclusive and weekly to 56 days, so that late recrudescence and relapses could be detected [23,24]. Patients were also requested to attend if they felt unwell on any other day during the 56 days of follow-up. At each follow up visit a clinical assessment was undertaken and the patient was asked about adverse events by the use of a standard symptom questionnaire. Thick and thin blood slides were examined and haemoglobin was measured. Other tests such as peripheral white blood cell count and urine examination were undertaken as indicated to rule out other conditions and investigate possible adverse effects of drugs. Patients showing parasitological failure with recurrence of P. vivax had capillary blood collected on filter paper for PCR analysis and were treated with chloroquine (25 mg base/kg over 3 days) and followed up by standard protocols. Patients with mixed P. falciparum/P. vivax infection were also classified as treatment failures but treated with artesunate/sulphadoxine-pyrimethamine. Patients were censored from the analysis if there was stated withdrawal of consent at any stage, persistent vomiting during the acute phase (necessitating parenteral treatment) or occurrence during the follow-up of concomitant disease that would interfere with a clear classification of the treatment outcome (including mono-infection with P. falciparum). Patients failing to attend follow-up visits received a visit at home and were asked to reattend the centre for assessment. Transportation was provided for all follow-up visits for all subjects. All enrolled patients were given one long-lasting insecticide treated bed net.\n\nBODY.METHODS.OUTCOMES:\nThe primary outcome was the difference in the proportion of patients with parasitologically-confirmed recurrence of P. vivax infection at or before day 56 between the two arms. Secondary outcomes were parasite and fever clearance times, recurrence at earlier time points, gametocytaemia at day 28 and 56, haemoglobin recovery, and safety and tolerability of the treatments.\n\nBODY.METHODS.SAMPLE SIZE:\nGiven the relatively high predicted efficacy of chloroquine, a non-inferiority design was used [23] with the aim of testing whether dihydroartemisinin-piperaquine was non-inferior to (i.e. equivalent or better than) chloroquine in terms of the proportion of patients with parasitological failure at 56 days; the non-inferiority margin (Δ) was set at 5%. The sample size was 550 patients (275 per arm), calculated assuming a 95% cure rate with chloroquine, a one-sided alpha of 0.05 and 80% power.\n\nBODY.METHODS.STATISTICAL ANALYSIS:\nData were double entered into Microsoft Access. All analyses were conducted using STATA version 9.0. The Student's t-test, Mann-Whitney U and chi-squared (or Fisher's exact) tests were used for comparison of baseline variables, as appropriate. Parasitological failure rates were assessed by survival analysis using the Kaplan-Meier method and Wilson confidence intervals for the difference in efficacy proportions were calculated using the effective sample size [25]. Dihydroartemisinin-piperaquine was considered non-inferior to chloroquine if the lower bound of the confidence interval of the difference was greater than 0.05 (the non-inferiority margin). Differences between treatment groups were estimated using the log-rank test. A sensitivity analysis, in which losses to follow-up were considered failures, was also undertaken [26]; patients who did not complete treatment were excluded. Cox regression including age (years), gender, recruitment site, treatment arm, admission haemoglobin level (g/dl), presence of gametocytes and parasitaemia as independent variables was performed to identify possible independent predictors of recurrence, using a stepwise elimination method.\n\nBODY.METHODS.SPECIES CONFIRMATION BY PCR:\nDNA was extracted from filter-paper blood spots and nested PCR performed to detect P. vivax and P. falciparum as described previously [27].\n\nBODY.METHODS.ETHICAL APPROVAL:\nThe study was approved by the Ethics Committee of the Faculty of Tropical Medicine, Mahidol University, Thailand, the Oxford Tropical Research Ethics Committee, Oxford University, UK and the Institutional Review Board of the Afghan Public Health Institute, Ministry of Public Health, Afghanistan. The trial was registered with the clinical trials website http://www.clinicaltrials.gov/ct as NCT00682578. This description of the trial describes recruitment of patients with uncomplicated infection with either P. falciparum or P. vivax, with treatments depending on the species detected. Recruitment of P. falciparum cases proved much slower than for P. vivax and the ongoing P. falciparum study will be presented elsewhere.\n\nBODY.RESULTS.RECRUITMENT:\nFrom July 2007 to February 2009, 536 patients were enrolled in the study with 268 receiving chloroquine and 268 dihydroartemisinin-piperaquine (Figure 1). The main reasons for not being enrolled in the study were lack of consent (n = 608; 37%), history of taking anti-malarial drugs in the past month (n = 394; 24%), home too far away for follow-up (n = 337; 20%), concomitant disease (n = 228; 14%), pregnancy or lactation (n = 113; 7%), mixed infection with P. falciparum (n = 44) and severe malaria (n = 12). The majority of patients (314/536 (58.6%)) were recruited in Jalalabad; 119 (22.2%) patients were recruited in Taloqan and 103 (19.2%) in Maimana. 73 (13.6%) patients were less than five years of age, 258 (48.1%) were 5-14 years of age and 205 (38.2%) were 15 or older. Figure 1Trial flow. At the reference laboratory 94% of baseline slides were confirmed as P. vivax monoinfection; the remaining slides were classed as Plasmodium infection of undetermined species because of slide quality. PCR confirmation was undertaken on an independent, randomly selected subset of paired blood samples from 10 patients with parasitological failure. All 10 baseline samples and 9 of 10 samples taken at recurrence contained P. vivax by this method. P. falciparum was not detected in any sample by either microscopic or molecular methods.\n\nBODY.RESULTS.BASELINE CHARACTERISTICS:\nPatient characteristics at baseline were broadly similar between the two treatment groups (Table 1) except that the median white blood cell count was lower in the chloroquine group compared with dihydroartemisinin-piperaquine (median 6.0 vs. 6.6 × 109/l respectively, p = 0.02). Table 1 Baseline characteristics of enrolled patients. Characteristic Treatment arm Number of patients randomized CQ (n = 268) DP (n = 268) P Gender: Male/Female (ratio) 126/142 (0.89) 132/136 (0.97) 0.60 Age, median years (range) 11 (0.25 -71) 12 (1 - 70) 0.38 Age Groups: 0.18 <5 years 43 (16.0) 30 (11.2) 5 -14 years 130 (48.5) 128 (47.8) >14 years 95 (35.5) 110 (41.0) Location: 0.61 Jalalabad 154 (57.5) 160 (59.7) Taloqan 58 (21.6) 61 (22.8) Maimana 56 (20.9) 47 (17.5) Weight, median kg (range) 30 (5-93) 33 (7-89) 0.69 Geometric mean parasitaemia/μL (95% CI) 3339 (3000-3716) 3236 (2940 -3560) 0.67 Number with gametocytes 218 (81.3) 203 (75.2) 0.12 Haemoglobin concentration, mean g/dl (SD) 10.9 (1.46) 10.9 (1.42) 0.99 Anaemia (haemoglobin concentration < 10 g/dl) 49 (18.4) 44 (16.5) 0.35 Median white blood cells ×10 9 /ml, median (range) 6.0 (3.6-54) 6.6 (3.0-12.4) 0.02 Body temperature °C, mean (95% CI) 37.3 (37.2-37.4) 37.3 (37.2-37.4) 0.77 Median systolic blood pressure, mmHg (range) 100 (80-160) 100 (80-170) 0.43 Median diastolic blood pressure, mmHg (range) 70 (50-100) 70 (50-100) 0.38 Median pulse rate, beat/min (range) 88 (60-140) 88 (60-140) 0.53 Jaundice 30 (11.3) 32 (12.1) 0.79 History of convulsions in last 24 hours 1 (0.37) 1 (0.37) Data for chloroquine (CQ) and dihydroartemisinin-piperaquine (DP) are number (%) unless otherwise indicated. \n\nBODY.RESULTS.RESPONSE TO TREATMENT AND FOLLOW-UP:\nPatients in the chloroquine group who completed treatment received a median total dose of 25.9 mg/kg base (IQR 25.0 - 27.3 mg/kg); for the dihydroartemisinin-piperaquine group the median total dihydroartemisinin dose was 6.0 mg/kg (IQR 5.45 - 6.67 mg/kg). Both treatments were generally well tolerated. Repeated vomiting of the study medication was not reported within 60 minutes of drug administration in any patient. No patient deteriorated or developed signs of severity. Five patients who received the first dose withdrew consent before completing treatment and were censored from analysis. Of the 531 individuals who completed treatment, 38 (7.2%) cases were lost to follow-up before day 56; 13 in the chloroquine arm and 25 in dihydroartemisinin-piperaquine arm (p = 0.04) (Figure 1).\n\nBODY.RESULTS.PARASITOLOGICAL FAILURES:\nBy the end of the 56-day follow-up period, there were 23 recurrences (parasitological failures) in the chloroquine group and 7 in the dihydroartemisinin-piperaquine group, giving a day 56 failure rate of 8.9% (95% CI 6.0 - 13.1%) in the chloroquine group and 2.8% (1.4 - 5.8%) in the dihydroartemisinin-piperaquine group (Figure 2). The difference in day 56 parasitological failure rates between chloroquine and dihydroartemisinin-piperaquine was 6.1% (2-sided 90% CI +2.6 to +9.7%). The lower bound of this confidence interval was not only higher than the prespecified non-inferiority margin (i.e. -5%), but also did not include zero, indicating that dihydroartemisinin-piperaquine was superior to chloroquine in terms of outcome (Figure 3) [26]. The superiority of dihydroartemisinin-piperaquine was confirmed by the log rank test (p = 0.003). Figure 2Survival curves. The proportion of subjects free from recurrence of P. vivax is displayed according to treatment arm; dihydroartemisinin-piperaquine (DP) and chloroquine (CQ). A sensitivity analysis (in which all losses to follow-up were classed as failures) yielded a difference in cumulative parasitological failure rate between chloroquine and dihydroartemisinin-piperaquine of 1.5% (2-sided 90% CI -3.3 to +6.3%); as predicted there was a wider 90% confidence interval than that based on survival analysis but also a lower point estimate for the difference in failure rate between the chloroquine and dihydroartemisinin-piperaquine groups caused by the greater number of losses to follow-up in the dihydroartemisinin-piperaquine group. The lower bound of the 90% confidence interval was still higher than the prespecified non-inferiority margin (5%), but included zero, indicating that dihydroartemisinin-piperaquine was not inferior to chloroquine even in this considerably more conservative analysis [26] (Figure 3). Figure 3Analysis of primary outcome (cumulative failure rate at day 56). Non-inferiority analysis refers to the pre-specified survival analysis.\n\nBODY.RESULTS.SECONDARY OUTCOMES:\nInitial parasitological responses were faster with dihydroartemisinin-piperaquine (Figure 4); in the dihydroartemisinin-piperaquine group 241/264 (91.3%) of patients cleared their parasitaemia at day 1 compared to 209/265 (78.9%) in the chloroquine group (p < 0.001, relative risk of clearance in chloroquine group = 0.87, 95% CI 0.81-0.93). At day 2, the groups were no longer significantly different with 259/265 (97.8%) of the dihydroartemisinin-piperaquine group and 257/265 (97.0%) in the chloroquine group having cleared their parasitaemia (p = 0.59). Two patients in the chloroquine arm remained parasitaemic at day 3. Figure 4Proportion with clearance of parasites (a) and fever (b) at day 1-3 after treatment. In terms of resolution of fever (defined as axillary temperature >37.0°C) dihydroartemisinin-piperaquine was again superior (Figure 4), with 29/266 (10.9%) of the dihydroartemisinin-piperaquine group febrile on day 1 compared to 45/268 (16.8%) in the chloroquine group (p = 0.049). By day 2 there was no longer a significant difference in the proportion with fever (3/265 (1.1%) for dihydroartemisinin-piperaquine, 9/264 (3.4%) for chloroquine, p = 0.08). At day 1, headache was less frequent in the dihydroartemisinin-piperaquine arm (105/265 (39.6%)) compared to the chloroquine arm (145/266 (54.5%), p = 0.001). The day 28 cure rate was 100% in both arms with the first recurrences observed at day 35 in the chloroquine group and day 42 in the dihydroartemisinin-piperaquine group. Twenty-one of 30 (70%) recurrent parasitaemias were associated with gametocytaemia, with no significant difference between treatment arms in terms of proportion of recurrent patients with gametocytaemia (16/23 and 5/7 for chloroquine and dihydroartemisinin-piperaquine respectively, p = 1.0).\n\nBODY.RESULTS.ADVERSE EVENTS:\nThere were no serious adverse events recorded during the trial and no patient required hospitalization. Both study drugs appeared to be well tolerated. There was a significant increase in the proportion of patients with pruritus in the chloroquine arm compared to dihydroartemisinin-piperaquine on days 1, 2 and 3; on day 1, 15/268 subjects in the chloroquine arm had pruritus compared to 2/266 in the dihydroartemisinin-piperaquine arm (p = 0.002, relative risk 7.44, 95% CI 1.71-32.3), consistent with the known side-effects of chloroquine. None of the other signs or symptoms documented in the first three days of treatment were found to be significantly different between the groups. There were no significant differences between the two arms in haemoglobin concentration or occurrence of anaemia (haemoglobin < 10 g/dl) at any stage during follow-up (all p > 0.5).\n\nBODY.RESULTS.PREDICTORS OF TREATMENT FAILURE:\nA univariate analysis undertaken to identify variables associated with failure showed that treatment allocation (chloroquine rather than dihydroartemisinin-piperaquine), study site (recruitment in Maimana compared to Jalalabad), younger age and lower haemoglobin concentration at baseline were all significantly associated with recurrent infection. Admission parasitaemia, presence of gametocytes at admission and gender had no effect in this model (Table 2). Table 2 Univariate analysis of risk factors for treatment failure Univariate analysis Factor Hazard Ratio p value Chloroquine treatment 3.28 (1.41-7.63) 0.006 Female 0.93 (0.46-1.91) 0.85 Age (years) 0.96 (0.92-1.00) 0.03 Recruitment site (Jalalabad as reference) Taloqan 0.79 (0.26-2.43) 0.68 Maimana 3.06 (1.42-6.61) 0.004 Parasitaemia 0.86 (0.32-2.29) 0.76 Presence of gametocytes 1.13 (0.46-2.77) 0.784 Haemoglobin at admission (g/dl) 0.49 (0.37-0.65) <0.001 Multivariate analysis of the same seven variables entered into the univariate analysis indicated that treatment with chloroquine and lower haemoglobin concentration at baseline were the only two significant independent predictors of recurrent infection (Adjusted Hazard Ratio (AHR) 3.66, 95% CI 1.48-9.02, p < 0.001 for treatment allocation and AHR 0.50, 95% CI 0.37-0.66, p = 0.005 for haemoglobin concentration).\n\nBODY.DISCUSSION:\nThis trial in three separate malaria areas of Afghanistan confirmed that both chloroquine and dihydroartemisinin-piperaquine are well-tolerated and broadly efficacious treatments for vivax malaria. Initial parasite clearance was significantly faster after dihydroartemisinin-piperaquine, consistent with the pharmacodynamic properties of artemisinin-containing therapies observed in P. falciparum [28] and P. vivax [9,24]. Nevertheless 97% of patients in the chloroquine arm were parasite free and afebrile by day 2, and there were no recurrences in either arm before day 28, suggesting that P. vivax remains sensitive to chloroquine in the study area, which included locations both north and south of the Hindu Kush divide of central Afghanistan. These data extend the geographic range of efficacy monitoring beyond Eastern Afghanistan where chloroquine has been shown previously to be efficacious in clearing P. vivax parasitaemia [9,10]. These findings stand in marked contrast to data from Indonesia where P. vivax chloroquine-resistance manifests as frequent failure to clear parasites by day 4 [6,29-31] and recurrence rates by day 28 approximate 50% [29-31] or higher [6]. Over the 56-day follow-up period dihydroartemisinin-piperaquine proved superior to chloroquine in terms of the prespecified survival analysis of recurrence rates. Approximately 9% of cases had recurrent P. vivax infections in the chloroquine arm, compared to 3% in the dihydroartemisinin-piperaquine arm, with all failures occurring on or after day 35. Recurrences of P. vivax may consist of a mixture of relapses from liver hypnozoites, recrudescences of the erythrocytic infection (due to inadequate drug levels or resistance), and reinfections acquired from additional innoculations. It is not possible with current methodologies to distinguish reliably between these possibilities [32,33]. However, in studies undertaken in a neighbouring region of Pakistan, radical treatment with primaquine following chloroquine prevented the majority of recurrent infections over the course of 9-12 months, indicating that most recurrences following chloroquine monotherapy are likely to be relapses from liver hypnozoites [34-36]. In this study, primaquine was not given, and none of the treatments administered has activity against P. vivax hypnozoites. The rapid clearance of parasites in the chloroquine group, and the fact that failures were not seen before day 28, suggest that recrudescences associated with chloroquine-resistance did not contribute significantly to the number of recurrences. For these reasons, the majority of recurrences observed in this study are likely to have been relapses. The pattern of recurrences is consistent with the known properties of the drugs under study. Chloroquine is effective in preventing early relapses (<28 days) of vivax malaria in chloroquine-sensitive vivax malaria [4,9,10,36-39]. This is because chloroquine is eliminated very slowly (terminal half-life one to two months), and provides post-treatment prophylaxis against relapse for 3-4 weeks after treatment [39]. Piperaquine also has a very long terminal elimination half- [40]. In an area where chloroquine-resistant P. vivax is prevalent DHA-PPQ has been shown in several comparative trials to prevent recurrences of P. vivax over a six-week period more effectively than ACT containing partner drugs with shorter half-lives [5,14,15]. In these studies, the recurrence rate (typically measured over 42 days) can be correlated with the half-life of the partner drug; for example, recurrences are fewer in patients treated with dihydroartemisinin-piperaquine compared to artemether-lumefantrine [5,14] and artesunate-amodiaquine [15], presumably because the lumefantrine and amodiaquine components have shorter terminal elimination half-lives (approximately 10 and 18 days respectively) than piperaquine. In the only previous trial directly comparing dihydroartemisinin-piperaquine to chloroquine (combined with sulfadoxine-pyrimethamine, CQ-SP) for P. vivax infection in Papua New Guinea, high levels of chloroquine-resistance were present, as evidenced by prolonged parasite clearance times in the CQ-SP arm. There was an 87% rate of recurrence in the first 42 days after CQ-SP compared to 30.6% in the dihydroartemisinin-piperaquine arm [5], a difference that is likely to reflect both failure to clear initial parasitaemia (leading to recrudescence) as well as failure to suppress relapse. This study provides the first comparison of chloroquine and dihydroartemisinin-piperaquine in chloroquine-sensitive P. vivax, and confirms the longer lasting post-treatment prophylactic effect of dihydroartemisinin-piperaquine compared to chloroquine in this setting. The observed proportion of chloroquine-treated patients with recurrence over 56 days is less than in a study undertaken in the Jalalabad Malaria Reference Centre in 2004 [9] (where more than 40% of patients treated with chloroquine had recurrence from days 28-42 after treatment), for reasons that are unclear. Ancillary studies would help to shed further light on these issues, including pharmacological assessment of chloroquine and piperaquine levels in blood during the follow-up period. This would also allow the question of chloroquine resistance to be excluded more definitively. This study was not powered to undertake detailed assessments of factors associated with recurrence. In the univariate analysis (although not the multivariate), younger age was found to be a risk factor for recurrence, a finding consistent with previous studies examining this effect over longer follow-up periods [35,37]. Possible explanations for this include pharmacokinetic effects [39,41], reduced immunity compared to adults and higher burdens of hypnozoites. Patients recruited in Maimana had a significantly higher rate of failure than those from Jalalabad in the univariate analysis although the effect disappeared in the multivariate analysis, suggesting that other factors may have contributed to this finding. The data do not provide substantive support for the existence of chloroquine resistance at Maimana or any of the study sites. The finding of a strong association between lower baseline haemoglobin and recurrence of P. vivax infection was not anticipated and requires further investigation. It is possible that the action of dihydroartemisinin-piperaquine is simply to delay relapses of vivax malaria rather than prevent them; in other words the survival curves for recurrence with dihydroartemisinin-piperaquine and chloroquine will eventually merge. Studies with longer-term follow-up would be needed to determine if this is the case and if dihydroartemisinin-piperaquine offers tangible benefits in terms of long-term health of the individual (preventing relapse and associated anaemia) and possibly the community (by reducing transmission). Any health benefits have to be balanced against the relative cost of each treatment course, which is currently in favour of chloroquine use. These issues also have to be considered in the context of the challenges of treating patients with radical therapy in this region [35,36].\n\nBODY.CONCLUSION:\nBoth dihydroartemisinin-piperaquine and chloroquine are efficacious treatments for P. vivax malaria across three regions of Afghanistan. Consistent with the known pharmacological properties of the drugs, dihydroartemisinin-piperaquine provides a longer period of post-treatment prophylaxis, reducing the incidence of recurrence from 4-8 weeks after treatment.\n\nBODY.COMPETING INTERESTS:\nThe authors declare that they have no competing interests.\n\nBODY.AUTHORS' CONTRIBUTIONS:\nGRA, SP, MI, AMD, SJL, NPJD, PS, NJW and FK were involved in the conception and design of the study. GRA and FK were responsible for supervising patient recruitment and follow-up. MI undertook species confirmation by PCR. GRA, SP, CJW and SJL participated in the statistical analysis. GRA, SP, CJW, SJL and NJW drafted and critically revised the manuscript. All authors read and approved the final manuscript.\n\n**Question:** Compared to Chloroquine what was the result of Dihydroartemisinin-piperaquine on Fever resolution by day 2?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
115
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.8 mg) plus glimepiride on Fasting plasma glucose at week 26?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
127
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Placebo plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on ADA postprandial plasma glucose goals less than 10.0 mmol/l?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
131
|
[
{
"role": "user",
"content": "You are an expert medical assistant specialized in analyzing clinical trial conclusions. Your task is based on an article context and a Question created from a ICO (outcome, intervention, comparator) triplet, to arrive at the correct conclusion regarding their relation. \n\nYou will be given an article context preceded by **Article:**, which contains the Abstract and Body sections of a randomized controlled trial. **Question:** will denote the information present on the ICO triplet. Pay close attention to the details in the article to accurately assess the conclusion from the trial.\n\n**Article:** \n\nTITLE: Liraglutide, a once-daily human GLP-1 analogue, added to a sulphonylurea over 26 weeks produces greater improvements in glycaemic and weight control compared with adding rosiglitazone or placebo in subjects with Type 2 diabetes (LEAD-1 SU)\n\n ABSTRACT.AIM:\nTo compare the effects of combining liraglutide (0.6, 1.2 or 1.8 mg/day) or rosiglitazone 4 mg/day (all n ≥ 228) or placebo (n = 114) with glimepiride (2–4 mg/day) on glycaemic control, body weight and safety in Type 2 diabetes.\n\nABSTRACT.METHODS:\nIn total, 1041 adults (mean ± sd), age 56 ± 10 years, weight 82 ± 17 kg and glycated haemoglobin (HbA1c) 8.4 ± 1.0% at 116 sites in 21 countries were stratified based on previous oral glucose-lowering mono : combination therapies (30 : 70%) to participate in a five-arm, 26-week, double-dummy, randomized study.\n\nABSTRACT.RESULTS:\nLiraglutide (1.2 or 1.8 mg) produced greater reductions in HbA1c from baseline, (−1.1%, baseline 8.5%) compared with placebo (+0.2%, P < 0.0001, baseline 8.4%) or rosiglitazone (−0.4%, P < 0.0001, baseline 8.4%) when added to glimepiride. Liraglutide 0.6 mg was less effective (−0.6%, baseline 8.4%). Fasting plasma glucose decreased by week 2, with a 1.6 mmol/l decrease from baseline at week 26 with liraglutide 1.2 mg (baseline 9.8 mmol/l) or 1.8 mg (baseline 9.7 mmol/l) compared with a 0.9 mmol/l increase (placebo, P < 0.0001, baseline 9.5 mmol/l) or 1.0 mmol/l decrease (rosiglitazone, P < 0.006, baseline 9.9 mmol/l). Decreases in postprandial plasma glucose from baseline were greater with liraglutide 1.2 or 1.8 mg [−2.5 to −2.7 mmol/l (baseline 12.9 mmol/l for both)] compared with placebo (−0.4 mmol/l, P < 0.0001, baseline 12.7 mmol/l) or rosiglitazone (−1.8 mmol/l, P < 0.05, baseline 13.0 mmol/l). Changes in body weight with liraglutide 1.8 mg (−0.2 kg, baseline 83.0 kg), 1.2 mg (+0.3 kg, baseline 80.0 kg) or placebo (−0.1 kg, baseline 81.9 kg) were less than with rosiglitazone (+2.1 kg, P < 0.0001, baseline 80.6 kg). Main adverse events for all treatments were minor hypoglycaemia (< 10%), nausea (< 11%), vomiting (< 5%) and diarrhoea (< 8%).\n\nABSTRACT.CONCLUSIONS:\nLiraglutide added to glimepiride was well tolerated and provided improved glycaemic control and favourable weight profile.\n\nBODY.INTRODUCTION:\nMost drugs that target Type 2 diabetes (T2D) also cause weight gain or hypoglycaemia, or both, with the risk increasing with combination therapy. Glucagon-like peptide-1 (GLP-1)-based therapies stimulate insulin secretion and reduce glucagon secretion only during hyperglycaemia. GLP-1 also slows gastric emptying and reduces appetite [1]. Although American Diabetes Association (ADA)/European Association for the Study of Diabetes (EASD) guidelines recommend lifestyle and metformin as initial therapy for T2D [2], sulphonylureas are used widely, particularly when metformin or thiazolidinediones are not tolerated. Glycaemic control eventually deteriorates with sulphonylureas while hypoglycaemia and weight gain are common [3]. Incretin therapy improves glycaemic control with low hypoglycaemic risk, while delayed gastric emptying and reduced appetite can reduce weight [1,4]. Liraglutide is a once-daily human GLP-1 analogue with 97% linear amino-acid sequence homology to human GLP-1 [5] and half-life of 13 h after subcutaneous administration that produces 24-h blood glucose control [6]. Liraglutide monotherapy for 14 weeks reduced glycated haemoglobin (HbA1c) by 1.7% and fasting plasma glucose (FPG) by 3.4 mmol/l without causing hypoglycaemia, along with weight loss (∼3 kg) compared with placebo [7]. Improvements in pancreatic B-cell function [7–9] and blood pressure [7], along with decreased glucagon secretion [7,10], also occurred. As part of the phase 3 programme [the Liraglutide Effect and Action in Diabetes (LEAD) programme] with liraglutide in > 4000 subjects with T2D as monotherapy or in combination therapy, this 26-week trial examined liraglutide plus glimepiride compared with either placebo or rosiglitazone added to glimepiride on glycaemic control and body weight.\n\nBODY.SUBJECTS AND METHODS.STUDY PARTICIPANTS:\nInclusion criteria: T2D treated with oral glucose-lowering agents (OGLAs) for ≥ 3 months; 18–80 years of age; HbA1c 7.0–11.0% (previous OGLA monotherapy) or 7.0–10.0% (previous OGLA combination therapy); body mass index (BMI) ≤ 45.0 kg/m2. Exclusion criteria: used insulin within 3 months, impaired liver or renal function, uncontrolled hypertension (≥ 180/100 mmHg), cancer or used any drugs apart from OGLAs likely to affect glucose concentrations. Subjects provided written informed consent. The study was conducted in accordance with good clinical practice guidelines and approved by independent ethics committees.\n\nBODY.SUBJECTS AND METHODS.STUDY DESIGN:\nThe study was a 26-week, double-blind, double-dummy, randomized, active-control, five-armed parallel (116 sites in 21 countries, primarily Europe and Asia) trial enrolling 1041 subjects (1–37 subjects per centre), all receiving glimepiride (2–4 mg/day) in combination with (Fig. 1): FIGURE 1Overview of trial design and treatment arms. one of three liraglutide doses [0.6, 1.2 or 1.8 mg, injected subcutaneously (Novo Nordisk, Bagsvaerd, Denmark) and rosiglitazone placebo];liraglutide placebo and rosiglitazone placebo;liraglutide placebo and rosiglitazone 4 mg/day (rosiglitazone; AvandiaTM; GlaxoSmithKline, London, UK). The doses of rosiglitazone and glimepiride used were determined by the highest doses approved in all participating counties. After discontinuing previous OGLAs except glimepiride, separate 2-week titration and maintenance periods with glimepiride (open-label) preceded randomization (Fig. 1). Subjects were stratified according to previous treatment (monotherapy or combination therapy). After randomization, 2-week treatment titration and 24-week treatment (maintenance) phases (Fig. 1) were completed. Liraglutide was up-titrated weekly in 0.6-mg increments until allocated doses were reached. Glimepiride could be adjusted between 2 and 4 mg/day in case of hypoglycaemia or other adverse events (AEs), while other drug doses were fixed. Liraglutide (active and placebo) was supplied in 3-ml pre-filled pens with 31G needles (Novo Nordisk). Subjects were encouraged to inject liraglutide into the upper arm, thigh or abdomen at the same time each day. Rosiglitazone and glimepiride were taken in the morning or with the first meal.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.EFFICACY:\nThe primary endpoint was change from baseline HbA1c after 26 weeks of treatment. Secondary endpoints included: percentages of subjects reaching HbA1c (< 7.0%, ≤ 6.5%), FPG (5.0 to ≤ 7.2 mmol/l) and postprandial plasma glucose (PPG; 10.0 mmol/l) targets [11–13]; changes in body weight, FPG, mean PPG, indices of pancreatic B-cell function [pro-insulin : insulin ratio and homeostasis model assessment (HOMA)-B], HOMA-insulin resistance (HOMA-IR) and blood pressure (BP). HbA1c was measured centrally (MDS Pharma Services, King of Prussia, PA, USA) by high performance liquid chromatography while plasma glucose (PG) was self-measured using MediSense® glucose meters (Abbott Diagnostics Inc., Abbott Park, IL, USA). Insulin and C-peptide were measured by chemiluminescence, proinsulin by ELISA, while glucagon was measured in aprotinin-treated plasma by radioimmunoassay. The proinsulin : insulin ratio was calculated from fasting insulin and fasting proinsulin. HOMA-B and HOMA-IR were both calculated from FPG and fasting insulin. Samples measured centrally were collected and transported according to detailed procedures in the MDS Pharma Services manual. Samples stored at ambient temperature were shipped by courier to the central laboratory on the same day as collection, while frozen samples were shipped every 3 weeks.\n\nBODY.SUBJECTS AND METHODS.STUDY MEASUREMENTS.SAFETY:\nSafety variables included hypoglycaemic episodes based on PG levels (< 3.1 mmol/l), liraglutide antibodies including cross-reacting and neutralizing antibodies, tolerability (gastrointestinal complaints) and pulse. AEs, vital signs, electrocardiogram (ECG), biochemical and haematology measures including calcitonin were also monitored. Self-treated hypoglycaemic episodes were classified as minor, while those requiring third-party assistance were considered major. Serum antibodies against liraglutide were measured by radioimmunoprecipitation assay.\n\nBODY.SUBJECTS AND METHODS.STATISTICAL ANALYSES:\nAll efficacy and safety analyses were based on intent-to-treat criteria, defined as subjects who were exposed to ≥ 1 dose of trial product(s). Efficacy endpoints were analysed by ancova with treatment, country and previous glucose-lowering treatment as fixed effects and baseline values as covariates. Missing data were imputed by last observation carried forward (LOCF). Sample size calculations were based on predicted HbA1c and body weight after trial completion. As the three liraglutide + glimepiride groups were to be compared with both rosiglitazone + glimepiride and glimepiride monotherapy, two calculations were performed. These sample size calculations assumed a standard deviation of 1.2% of HbA1c, the non-inferiority/superiority margin vs. active control was set to 0.4% and the difference to detect (superiority vs. placebo) was set to 0.5%. For body weight, a coefficient of variation of 3% (based on phase 2a trials for liraglutide) and a difference to detect of 3% were assumed. A combined power (calculated as the product of the marginal powers for HbA1c and body weight) of at least 85% was required. These calculations indicated that at least 168 and 81 patients completing the study would be needed for the combination and glimepiride monotherapy groups, respectively. Assuming a drop-out rate of 25%, targets for randomization were 228 in each of the combination therapy groups and 114 in the placebo group (total n = 1026). To protect against Type 1 errors, HbA1c was analysed using hierarchical testing for descending doses of liraglutide. First, superiority of liraglutide 1.8 mg to placebo was tested and, only if superior to placebo, non-inferiority to rosiglitazone was tested. If non-inferiority was obtained, superiority to rosiglitazone for liraglutide 1.8 mg was tested and superiority to placebo for liraglutide 1.2 mg was tested. If superiority was confirmed, non-inferiority to rosiglitazone would be tested and so on (i.e. testing sequence was stopped when hypotheses could not be rejected). Superiority was concluded when upper limits of two-sided 95% confidence intervals (CIs) for treatment differences were below 0%; non-inferiority was concluded if these values were < 0.4%; for secondary endpoints, Type 1 errors were controlled by estimating simultaneous CIs using Dunnett's method. Proportions of subjects achieving HbA1c (HbA1c < 7.0%, and ≤ 6.5%) and FPG (5.0 ≤ FPG ≤ 7.2 mmol/l) targets [13] were compared between treatments using logistic regression with allocated treatment and baseline values as covariates. Chi-square analyses assessed differences in treatments for percentages of subjects achieving no, one, two or three PPG values < 10 mmol/l [13]. Hypoglycaemic episodes were analysed under the assumption that number per subject were negatively binomially distributed using a generalized linear model, including treatment and country as fixed effects. Other safety data were compared by descriptive statistics. Values for descriptive statistics are expressed as means ± sd, while ancova results are expressed as least square means ± SEM or with 95% CI unless otherwise noted. Significance levels were set to 5% for two-sided tests and 2.5% for one-sided tests.\n\nBODY.RESULTS.DISPOSITION AND DEMOGRAPHICS:\nThe treatment groups were well balanced (Table 1). Of 1712 subjects screened, 1041 were randomized and 1040 were exposed to trial drugs; 147 subjects (14.1%) withdrew (Fig. 2). Withdrawals were higher with placebo (27%) and rosiglitazone treatment (16%) compared with liraglutide 0.6 mg (11%), liraglutide 1.2 mg (14%) and liraglutide 1.8 mg (9%) treatment. Thirty-eight subjects (3.7%) withdrew as a result of AEs (Fig. 2). Table 1 Demographic characteristics of study participants Liraglutide 0.6 mg ( n = 233) Liraglutide 1.2 mg ( n = 228) Liraglutide 1.8 mg ( n = 234) Placebo ( n = 114) Rosiglitazone ( n = 232) Male : female (%) 54 : 46 45 : 55 53 : 47 47 : 53 47 : 53 Age (years) 55.7 ± 9.9 57.7 ± 9.0 55.6 ± 10.0 54.7 ± 10.0 56.0 ± 9.8 Duration of diabetes (years) 6.5 (4.0,10.2) 6.7 (4.0,10.7) 6.5 (3.7,10.5) 6.5 (4.5,10.6) 6.6 (4.3,10.7) Previous on mono : combi (%) 30 : 70 31 : 69 27 : 73 32 : 68 32 : 68 FPG (mmol/l) 10.0 ± 2.4 9.8 ± 2.7 9.7 ± 2.4 9.5 ± 2.0 9.9 ± 2.5 HbA 1c (%) 8.4 ± 1.0 8.5 ± 1.1 8.5 ± 0.9 8.4 ± 1.0 8.4 ± 1.0 Diabetic retinopathy (%) 17.2 14.9 12.0 13.2 16.4 Hypertension (%) 69.1 68.0 69.7 64.9 66.8 BMI (kg/m 2 ) 30.0 ± 5.0 29.8 ± 5.1 30.0 ± 5.1 30.3 ± 5.4 29.4 ± 4.8 Weight (kg) 82.6 ± 17.7 80.0 ± 17.1 83.0 ± 18.1 81.9 ± 17.1 80.6 ± 17.0 Systolic blood pressure (mmHg) 131 ± 16 133 ± 15 132 ± 16 131 ± 15.3 133 ± 15 Data are mean ± sd and percentages, except for duration of diabetes, where data are median, 25th and 75th percentile. BMI, body mass index; FPG, fasting plasma glucose; HbA 1c , glycated haemoglobin; mono : combi, previous treatment with either monotherapy or combination therapy; sd , standard deviation. FIGURE 2Flow of patients through the study.\n\nBODY.RESULTS.EFFICACY.HBA:\nHbA1c decreased rapidly with all doses of liraglutide when added to glimepiride compared with either rosiglitazone or placebo (i.e. glimepiride monotherapy), irrespective of previous therapy. The greatest decreases occurred with liraglutide 1.2 and 1.8 mg (Fig. 3a–c). After 26 weeks, HbA1c decreased by 1.1% from baseline (primary endpoint) with either liraglutide 1.2 or 1.8 mg, respectively, compared with either placebo (+0.2%) or rosiglitazone (−0.4%) (Fig. 3d). Estimated treatment differences and 95% CIs to placebo were: liraglutide 1.8 mg: −1.4% (1.6, −1.1); liraglutide 1.2 mg: −1.3% (1.5, −1.1); liraglutide 0.6 mg: −0.8% (−1.1, −0.6); rosiglitazone: −0.7% (−0.9, −0.4). All liraglutide doses were superior to placebo (P < 0.0001), while the two higher liraglutide doses were superior to rosiglitazone (P < 0.0001). Liraglutide 0.6 mg was non-inferior to rosiglitazone. Rosiglitazone also was superior to placebo (P < 0.0001). FIGURE 3Mean glycated haemoglobin (HbA1c) by treatment and week (intent-to-treat population with last observation carried forward): (a) overall population; (b) previously on monotherapy; or (c) previously on combination therapy; (d) mean changes in HbA1c from baseline after 26 weeks of treatment. Keys: (a–c) liraglutide 0.6 mg: grey dotted line with squares; liraglutide 1.2 mg: black solid line with triangles; liraglutide 1.8 mg: black dotted line with squares; rosiglitazone: grey solid line with circles; placebo: black solid line with circles. (d) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. ****P < 0.0001 compared with placebo; ††††P < 0.0001 compared with rosiglitazone. HbA1c decreases were greater for subjects who entered from monotherapy compared with combination therapy (Fig. 3d). However, because the increase with placebo was higher for individuals entering on combination therapy (0.7 vs. 0.23%), the differences between treatment groups in favour of liraglutide were similar irrespective of whether subjects were treated previously with monotherapy or combination therapy. Neither age, gender nor BMI affected these trends.\n\nBODY.RESULTS.EFFICACY.PERCENTAGE REACHING AN HBA:\nThe percentage of subjects reaching ADA [2] and International Diabetes Federation (IDF)/American Association of Clinical Endocrinologists (AACE) [11,12] treatment HbA1c goals with liraglutide was dose dependent (Fig. 4). At week 26, 42% and 21% of subjects treated with liraglutide 1.8 mg reached an HbA1c < 7.0% and ≤ 6.5%, respectively, compared with 8% and 4% for placebo (Fig. 4). The estimated proportion of subjects treated with either liraglutide 1.2 or 1.8 mg reaching ADA/EASD and IDF/AACE HbA1c targets was substantially greater compared with either placebo (P < 0.0001) or rosiglitazone (Fig. 4; P ≤ 0.0003), with more patients reaching < 7.0% with liraglutide 1.8 mg compared with 1.2 mg (P = 0.018). FIGURE 4Subjects achieving specified glycated haemoglobin (HbA1c) levels: (a) percentage reaching HbA1c < 7.0% (American Diabetes Association/European Association for the Study of Diabetes target); (b) percentage reaching HbA1c < 6.5% (International Diabetes Federation/American Association of Clinical Endocrinologists targets); (c) cumulative distribution of HbA1c at 26 weeks for the intent-to-treat (ITT) population; and (d) for the ITT last observation carried forward (LOCF) population. Keys: (a, b) liraglutide 0.6 mg: black stripes on white; liraglutide 1.2 mg: white stripes on black, liraglutide 1.8 mg: grey tint; rosiglitazone: white; placebo: black. (c, d) liraglutide 0.6 mg: pale grey solid line; liraglutide 1.2 mg: grey solid line, liraglutide 1.8 mg: black solid line; rosiglitazone: dotted black line; placebo: dotted grey line; baseline visit: long dashed black line. ****P < 0.0001 or **P < 0.01 compared with placebo; ††††P < 0.0001 or †††P = 0.0005 compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.FASTING PLASMA GLUCOSE:\nBy week 2, subjects treated with liraglutide had rapid and larger decreases in FPG vs. comparator treatment. At week 26, all doses of liraglutide decreased FPG more than did placebo (Fig. 5; P < 0.0001), while only liraglutide 1.2 or 1.8 mg produced greater reductions than rosiglitazone. FPG treatment differences to placebo were 1.7 mmol/l for liraglutide 0.6 mg and 2.6 mmol/l for both liraglutide 1.2 and 1.8 mg. An 0.7-mmol/l greater reduction in FPG was achieved with either liraglutide 1.2 or 1.8 mg compared with rosiglitazone (P ≤ 0.006) after 26 weeks. FIGURE 5Mean changes from baseline in fasting plasma glucose after 26 weeks of treatment. ****P < 0.0001 compared with placebo; ††P < 0.01 compared with rosiglitazone. The percentage of subjects achieving FPG values between 5.0 mmol/l and ≤ 7.2 mmol/l (ADA target) after 26 weeks was higher with liraglutide: 0.6 mg (19%; P = 0.002); 1.2 mg (37%; P < 0.001); and 1.8 mg (38%;P < 0.001) compared with placebo (7%). The liraglutide 1.2 and 1.8 mg treatment groups also had more subjects achieving the same FPG target at end of treatment compared with rosiglitazone (26%) (P = 0.007 and P = 0.01, respectively).\n\nBODY.RESULTS.EFFICACY.POSTPRANDIAL PLASMA GLUCOSE:\nPPG was reduced similarly after each meal. The greatest reductions in mean PPG values from baseline (average of values obtained 90 min after breakfast, lunch and evening meal) occurred with liraglutide 1.2 mg (2.5 mmol/l) and liraglutide 1.8 mg (2.7 mmol/l). By comparison, the reduction from baseline in mean PPG values was 1.8 mmol/l for rosiglitazone and liraglutide 0.6 mg and 0.4 mmol/l for placebo. Treatment differences for PPG were greater with all doses of liraglutide compared with placebo (1.5–2.4 mmol/l; P < 0.0001) and greater with liraglutide 1.2 mg (0.64 mmol/l; P = 0.043) and 1.8 mg (0.87 mmol/l;P = 0.0022) compared with rosiglitazone.\n\nBODY.RESULTS.EFFICACY.PPG MEASUREMENTS < 10.0 MMOL/L:\nThe percentage of subjects with one, two or three PPG measurements < 10.0 mmol/l (ADA target) were greater for all doses of liraglutide compared with placebo (P < 0.05) but not rosiglitazone.\n\nBODY.RESULTS.BODY WEIGHT:\nMean weight at baseline was 81.6 kg. Mean reductions in weight from baseline to end of treatment were 0.2 kg with liraglutide 1.8 mg and 0.1 kg with placebo treatment, while increases occurred with either liraglutide 0.6 mg (0.7 kg), liraglutide 1.2 mg (0.3 kg) or rosiglitazone (2.1 kg) (Fig. 6). Unlike rosiglitazone, weight did not increase substantially with liraglutide and the differences between rosiglitazone and liraglutide were statistically significant (−2.3 to −1.4 kg; P < 0.0001), although there were no significant differences compared with placebo. Gender appeared to have no influence on the results, as indicated when added as a fixed effect in the ancova model. FIGURE 6Mean changes in body weight from baseline after 26 weeks of treatment. *P < 0.05 compared with placebo; ††††P < 0.0001 compared with rosiglitazone.\n\nBODY.RESULTS.INDICES OF PANCREATIC B-CELL FUNCTION AND INSULIN RESISTANCE:\nReductions in the proinsulin : insulin ratio were greater with both liraglutide 1.2 and 1.8 mg compared with either rosiglitazone or placebo (Table 2; P ≤ 0.02). HOMA-B increased with liraglutide (1.8 or 1.2 mg) compared with rosiglitazone (P < 0.05), while this increase was only different to placebo with liraglutide 1.2 mg (P = 0.01) and not liraglutide 1.8 mg (P = 0.051). There were no significant differences between treatments for HOMA-IR. Table 2 Selected indices of pancreatic B-cell function Variable Treatment Baseline Week 26 (LOCF) Least square difference from placebo (95% CI) Least square difference from rosiglitazone (95% CI) Proinsulin : insulin ratio Liraglutide 0.6 mg 0.42 ± 0.22 0.38 ± 0.24 −0.05 (−0.11; 0.00) −0.02 (−0.06; 0.03) Liraglutide 1.2 mg 0.45 ± 0.31 0.33 ± 0.20 −0.10 (−0.16; −0.05) † −0.07 (−0.11; −0.02) * Liraglutide 1.8 mg 0.48 ± 0.33 0.36 ± 0.20 −0.09 (−0.15; −0.03) * −0.05 (−0.10; −0.01) * Placebo 0.44 ± 0.27 0.46 ± 0.29 Rosiglitazone 0.45 ± 0.29 0.40 ± 0.20 HOMA-B (%) Liraglutide 0.6 mg 51 ± 43.3 70 ± 88.6 15 (−19.10; 49.0) 11 (−16.7; 39.0) Liraglutide 1.2 mg 71 ± 254.3 99 ± 184.3 43 (8.10; 76.9) * 39 (10.3; 67.0) * Liraglutide 1.8 mg 56 ± 84.6 91 ± 108.2 34 (−0.23; 68.5) 30 (2.00; 58.6) * Placebo 56 ± 103.3 52 ± 107.3 Rosiglitazone 46 ± 36.2 59 ± 63.3 * P ≤ 0.05; † P < 0.0001. CI, confidence interval; HOMA, homeostatis model assessment; LOCF, last observation carried forward. \n\nBODY.RESULTS.BLOOD PRESSURE AND PULSE:\nAlthough decreases in systolic blood pressure occurred with either liraglutide 1.2 or 1.8 mg (2.6–2.8 mmHg), they were not significantly different from placebo or rosiglitazone (0.9–2.3 mmHg). Reductions in diastolic blood pressure also occurred with all treatments (0.7–1.4 mmHg), with no significant differences between treatments. Pulse increases above baseline ranged from 2 to 4 beats/min with the three doses of liraglutide and 1 beat/min with rosiglitazone, while pulse decreased by 1 beat/min with placebo. Changes in pulse for all doses of liraglutide were significant vs. placebo (P ≤ 0.002). This also was true with either liraglutide 1.8 or 1.2 mg compared with rosiglitazone (P < 0.01).\n\nBODY.RESULTS.SAFETY:\nThe most common treatment-emergent AEs that were considered by investigators to be either possibly or probably related to liraglutide were gastrointestinal (diarrhoea, nausea, dyspepsia and constipation) and nervous system disorders (headache and dizziness), particularly during the first 4 weeks. Nausea was highest with liraglutide 1.2 mg (10.5%) and lowest with placebo (1.8%). Vomiting (4.4%) and diarrhoea (7.9%) were also higher with liraglutide 1.2 mg. Withdrawals because of nausea ranged from 0.9–2.2%, vomiting 0.4–0.9% and diarrhoea 0–1.3%. Nausea was more common with liraglutide compared with placebo and rosiglitazone, particularly during the first 4 weeks (Fig. 7). Frequency of nausea was less in the liraglutide 0.6 mg treatment group compared with the higher doses of liraglutide. Generally, the occurrence of nausea dissipated from 4 to 26 weeks of treatment in all groups using liraglutide (Fig. 7). FIGURE 7Percentage of subjects experiencing nausea over the course of the study. Key: liraglutide 0.6 mg with glimepiride: black line with filled circles; liraglutide 1.2 mg with glimepiride: black line with filled triangles; liraglutide 1.8 mg with glimepiride: grey line with hollow circles; glimepiride grey lines with filled squares; rosiglitazone and glimepiride: grey line with hollow triangles. The incidence of serious AEs ranged between 3 and 5%: placebo (3%), rosiglitazone (3%), liraglutide 0.6 mg (3%), liraglutide 1.2 mg (4%) and liraglutide 1.8 mg (5%). Most treatment-emergent serious AEs were judged by investigators to be unlikely to be related to trial products. No deaths were reported during the trial. One subject developed chronic pancreatitis whilst taking liraglutide 0.6 mg; the person had no reported previous history of pancreatitis. The subject continued on liraglutide therapy and completed the trial. At screening, five patients had been previously diagnosed with pancreatitis. As pancreatitis was not an exclusion criterion, these patients were randomized as follows: one to liraglutide 0.6 mg, one to liraglutide 1.2 mg, two to liraglutide 1.8 mg and one to rosiglitazone + glimepiride. All five patients completed the trial without reporting pancreatitis as an adverse event. Hypoglycaemia was infrequent with all treatments. One major hypoglycaemic episode (self-measured blood glucose = 3.0 mmol/l) occurred 9 days after treatment started in a subject receiving liraglutide 1.8 mg in combination with glimepiride. Although medical assistance was not needed, the subject required third-party assistance. The investigator judged the episode as likely to be related to glimepiride and reduced the dose from 4 to 3 mg after the incident. Minor hypoglycaemia occurred in < 10% of subjects for any treatment. The proportion of subjects experiencing minor hypoglycaemia during the trial was lowest with placebo (i.e. glimepiride monotherapy 2.6%; 0.17 events/subject-year), comparable with liraglutide 0.6 mg (5.2%, 0.17 events/subject-year) and rosiglitazone (4.3%, 0.12 events/subject-year) groups and similar between the liraglutide 1.2 mg (9.2%, 0.51 events/subject-year) and liraglutide 1.8 mg (8.1%, 0.47 events/subject-year) treatment groups. Incidence was higher with liraglutide 1.2 mg (P = 0.0024) and 1.8 mg (P = 0.0065) compared with rosiglitazone and liraglutide 1.2 mg compared with placebo (P = 0.048), occurring in the setting of lower mean HbA1c values. Antibodies to liraglutide were found in 9–13% of subjects treated with liraglutide. No significant effects of these antibodies on HbA1c were found in pooled analyses of four trials including the current study. There were no clinically relevant changes in ophthalmoscopy, biochemistry, urinalysis, haematology or ECG assessments. No significant differences in calcitonin were found between the three groups treated with liraglutide when compared with either placebo or rosiglitazone at the end of the trial at week 26.\n\nBODY.DISCUSSION:\nTreatment with liraglutide plus glimepiride was superior to glimepiride monotherapy at all doses of liraglutide and superior to rosiglitazone plus glimepiride for the two higher liraglutide doses for improving HbA1c. Similar findings for reductions in FPG and PPG highlight improved 24-h glucose control with once-daily liraglutide, with substantially more subjects reaching glycaemic targets, particularly with liraglutide 1.8 mg. Improvements in pancreatic B-cell function were larger with liraglutide 1.2 and 1.8 mg compared with rosiglitazone. Liraglutide was well tolerated and occurrence of gastrointestinal AEs was low overall, particularly after week 4. Although rates of hypoglycaemia were low in all treatment groups (< 10%), minor hypoglycaemic events occurred more often in patients treated with glimepiride plus liraglutide 1.2 or 1.8 mg than with glimepiride alone. It should be noted, however, that patients treated with liraglutide 1.2 or 1.8 mg achieved a lower HbA1c than those receiving glimepiride monotherapy. At lower HbA1c levels, sulphonylureas are known to elicit hypoglycaemia more readily than at higher levels. In clinical practice it may be possible to reduce the dose of sulphonylurea (when used with liraglutide) to minimize risk of hypoglycaemia and maintain HbA1cimprovements. Although weight effects were modest, liraglutide produced more favourable weight effects compared with rosiglitazone, which produced substantial weight gain. In other studies with liraglutide, subjects adding a 1.8-mg dose to metformin lost 2.8 kg [14], while those adding both metformin and glimepiride lost 1.8 kg compared with placebo [15] (both over 26 weeks) and those on liraglutide monotherapy (1.8 mg) lost 2.45 kg over 52 weeks [16]. In our study, because sulphonylureas usually cause weight gain, inclusion or optimization of glimepiride but not metformin may have mitigated the weight benefits typically associated with liraglutide. Lack of weight effects could be secondary to lower baseline body weight, withdrawal of previous metformin treatment or defensive snacking to minimize risk of hypoglycaemia. It might have been expected that the greater weight gain with rosiglitazone compared with liraglutide 1.8 mg would be associated with a concurrent increase in insulin resistance with rosiglitazone. The absence of this effect could reflect the insulin-sensitizing nature of rosiglitazone. Improvements in pancreatic B-cell function associated with liraglutide are consistent with other studies [7–9]. Study strengths include inclusion of both placebo and active (rosiglitazone) comparators and that OGLAs were optimized (not maximized) before randomization to minimize risk of hypoglycaemia. Limitations of the study include short duration of the trial and restriction on glimepiride and rosiglitazone in some countries that precluded maximal dosing. The impact of using other GLP-1-based treatments [such as exenatide, or the dipeptidyl peptidase-4 (DPP-4) inhibitor, sitagliptin] with sulphonylureas in subjects with T2D has been studied. In a 30-week American trial where exenatide twice a day was added to sulphonylureas, HbA1c was reduced by 0.46% from baseline with 5 μg and 0.86% with 10 μg [17] compared with 1.1% with liraglutide 1.8 or 1.2 mg. This reduction in HbA1c with liraglutide is consistent with other LEAD trials investigating liraglutide as monotherapy or in combination with various OGLA drugs. In these trials, HbA1c was reduced by 1–1.5%[14,16,18–20]. Reductions in FPG with exenatide were 0.3 and 0.6 mmol/l from baseline with 5 μg and 10 μg, respectively, compared with 1.4 mmol/l with liraglutide 1.8 mg; weight loss of 1.6 kg occurred with exenatide 10 μg compared with 0.2 kg for liraglutide 1.8 mg [17]. Differences in weight effects may be as a result of lower baseline weight in this trial (82 kg) compared with exenatide (96 kg) and discontinuation of previous metformin therapy, unlike the exenatide trial where exenatide was added to previous sulphonylurea monotherapy [17]. Other large-scale trials with liraglutide in combination with sulphonylureas have demonstrated weight loss of 2–3 kg [18,20]. Withdrawals from exenatide trials ranged from 24–30% compared with 9–14% with liraglutide in this study. Nausea with exenatide ranged from 39% with 5 μg to 51% with 10 μg [17] compared with 10.5% for liraglutide. Furthermore, 41% were positive for anti-exenatide antibodies compared with 9–13% with anti-liraglutide antibodies. With sitagliptin 100 mg once daily for 24 weeks, HbA1c decreased by 0.3% from baseline in subjects receiving glimepiride, with 11% achieving an HbA1c < 7.0%[21]. Reductions in FPG and PPG from baseline were 0.05 and 1.4 mmol/l, respectively, while weight increased by 0.8 kg and the prevalence of nausea was < 1%. Although head-to-head trials are required to test true differences between these agents, the marked effects of liraglutide on FPG may be as a result of consistent blood levels of liraglutide maintained over 24 h compared with exenatide which has to be administered 60 min before breakfast and dinner and has a half-life of 1.5–3.6 h [22]. In a recent 26-week head-to-head trial comparing liraglutide with exenatide, liraglutide produced a 0.3% greater decrease on HbA1c (P < 0.0001) [20]. Because DPP-4 inhibitors inhibit the degradation of GLP-1, the efficacy of sitagliptin is dependent on levels of endogenous GLP-1 which is physiologically low compared with the much higher pharmacological levels of liraglutide. Pharmacological levels may be needed to induce satiety, weight loss and possibly larger HbA1c reductions. Liraglutide is an effective and well-tolerated once-daily human GLP-1 analogue that improves overall glycaemic control and indices of pancreatic B-cell function with minimal weight gain and risk of hypoglycaemia when used in combination with a sulphonylurea for T2D.\n\nBODY.COMPETING INTERESTS:\nThe study was funded by Novo Nordisk, the manufacturer of liraglutide. In collaboration with the investigators, Novo Nordisk was responsible for the study design, protocol, statistical analysis plans, oversight, analysis and reporting of the results. Data were recorded at the clinical centres and maintained by the sponsor. The LEAD-1 SU study group had full access to the data. Final responsibility for the decision to submit the manuscript for publication was the authors. MM has received lecture fees from Novo Nordisk, Servier, MSD; JS has received honoraria, grants and lecture fees from Novo Nordisk; MB, WMWB and NAK have no conflicts to declare; JS has received lecture fees from Novo Nordisk; MZ is employed by, and holds stock in, Novo Nordisk; TLT is employed by Novo Nordisk; SC is a member of the international advisory board on liraglutide for Novo Nordisk and has received lecture fees from Novo Nordisk.\n\n**Question:** Compared to Rosiglitazone plus glimepiride what was the result of Liraglutide (1.2 mg) plus glimepiride on Proinsulin : insulin ratio?\n\nPlease output \"significantly increase\", \"no significant difference\" or \"significantly decrease\" corresponding to the correct option. Be as accurate as possible.\n"
}
] |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.