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 tri(...TRUNCATED) |
[
{
"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 tri(...TRUNCATED) |
[
{
"role": "assistant",
"content": "**Answer:** significantly decreased\n"
}
] |
significantly decreased
|
169
| [{"role":"user","content":"You are an expert medical assistant specialized in analyzing clinical tri(...TRUNCATED) |
[
{
"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 tri(...TRUNCATED) |
[
{
"role": "assistant",
"content": "**Answer:** significantly increased\n"
}
] |
significantly increased
|
142
| [{"role":"user","content":"You are an expert medical assistant specialized in analyzing clinical tri(...TRUNCATED) |
[
{
"role": "assistant",
"content": "**Answer:** no significant difference\n"
}
] |
no significant difference
|
The dataset consists of biomedical articles describing randomized control trials (RCTs) that compare multiple treatments. Each of these articles will have multiple questions, or 'prompts' associated with them. These prompts will ask about the relationship between an intervention and comparator with respect to an outcome, as reported in the trial. For example, a prompt may ask about the reported effects of aspirin as compared to placebo on the duration of headaches.
{
'TO:DO': ...,
...
}
TO:DO
@article{deyoung2020evidence,
title={Evidence inference 2.0: More data, better models},
author={DeYoung, Jay and Lehman, Eric and Nye, Ben and Marshall, Iain J and Wallace, Byron C},
journal={arXiv preprint arXiv:2005.04177},
year={2020}
}
Thanks to araag2 for adding this dataset.