Biomedical subjects

Lesley A Stewart

Publications and source records attributed to Lesley A Stewart.

5 recordsLinked to original sources

PubMed2005

Meta-analysis of individual patient data from randomized trials: a review of methods used in practice.

BACKGROUND: Meta-analyses based on individual patient data (IPD) are regarded as the gold standard for systematic reviews. However, the methods used for analysing and presenting results from IPD meta-analyses have received little discussion. METHODS: We review 44 IPD meta-analyses published during the years 1999-2001. We summarize whether they obtained all the data they sought, what types of approaches were used in the analysis, including assumptions of common or random effects, and how they examined the effects of covariates. RESULTS: Twenty-four out of 44 analyses focused on time-to-event outcomes, and most analyses (28) estimated treatment effects within each trial and then combined the results assuming a common treatment effect across trials. Three analyses failed to stratify by trial, analysing the data is if they came from a single mega-trial. Only nine analyses used random effects methods. Covariate-treatment interactions were generally investigated by subgrouping patients. Seven of the meta-analyses included data from less than 80% of the randomized patients sought, but did not address the resulting potential biases. CONCLUSIONS: Although IPD meta-analyses have many advantages in assessing the effects of health care, there are several aspects that could be further developed to make fuller use of the potential of these time-consuming projects. In particular, IPD could be used to more fully investigate the influence of covariates on heterogeneity of treatment effects, both within and between trials. The impact of heterogeneity, or use of random effects, are seldom discussed. There is thus considerable scope for enhancing the methods of analysis and presentation of IPD meta-analysis.

Data Interpretation, Statistical↗

PubMed2004

Investigating patient exclusion bias in meta-analysis.

BACKGROUND: Trial investigators frequently exclude patients from trial analyses which may bias estimates of the effect of treatment. Combining these estimates in a meta-analysis could aggregate any such biases. METHODS: To investigate how excluding patients from trials can affect the results of both trials and meta-analyses, we used 14 meta-analyses of individual patient data (IPD) that addressed therapeutic questions in cancer. These included 133 randomized controlled trials (RCT) and 21 905 patients. We explored whether exclusions were related to trial characteristics and categorized the reasons for exclusions. For each RCT and meta-analysis, we compared results of an intention-to-treat analysis of all randomized patients with an analysis based on those patients included in the investigators' analysis. RESULTS: In all, 92 trials (69%) excluded between 0.3 and 38% of patients randomized. Trials excluding patients tended to be older and larger than those that did not. Most patients were excluded because of ineligibility or protocol violations. Exclusions varied substantially by meta-analysis, more patients tending to be excluded from the treatment arm. Comparing trial analyses there was no clear indication that exclusion of patients altered the results more in favour of either treatment or control. However, comparing meta-analysis results, there was a tendency for those based on 'included' patients to favour the research treatment (P = 0.03). Inconsistency of trial results was often increased as a result of the investigators' exclusions. CONCLUSIONS: Trials, systematic reviews, and meta-analyses may be prone to bias associated with post-randomization exclusion of patients. Wherever possible, the level of such exclusions should be taken into account when assessing the potential for bias in trials, systematic reviews, and meta-analyses. Ideally, trials, systematic reviews, and meta-analyses should be based on all randomized patients.

Bias↗

PubMed2003

Publication bias and meta-analyses: a practical example.

OBJECTIVES: Publication bias is widely appreciated, but considerable time and effort are needed to locate and obtain data from unpublished randomized controlled trials (RCTs), those published in non-English language journals or those reported in the gray literature; for this publication, we will call this collection of trials the "gray+literature." However, excluding such trials from systematic reviews could introduce bias and give rise to misleading conclusions. METHODS: We aimed to explore and quantify the impact of inclusion of gray+ literature on the results of all completed individual patient data (IPD) reviews coordinated by our group (13 meta-analyses). For each IPD review, results were calculated for RCTs fully published in English language journals and RCTs fully published in English language journals and the gray+literature. RESULTS: The IPD meta-analyses based only on RCTs that were fully published in English language journals tended to give more favorable results than those that included RCTs from the gray+literature. Although in most cases the addition of gray+data gave less encouraging results, moving the estimated treatment effect toward a null result, the direction of effect was not always predictable. CONCLUSIONS: We recommend that all systematic reviews should at least attempt to identify trials reported in the gray+literature and, where possible, obtain data from them.

Humans↗

PubMed2002

Effects of adjusting for censoring on meta-analyses of time-to-event outcomes.

BACKGROUND: Systematic reviews of published time-to-event outcomes commonly rely on calculating odds ratios (OR) at fixed points in time and where actual numbers at risk are not presented. These estimates are usually based on the total numbers included in the published analysis and take no account of censoring. We have assessed the impact of adjusting for censoring on weighting, estimates and statistical heterogeneity of meta-analyses in cancer. METHODS: Meta-analyses of survival data for five meta-analyses of published trials in cancer were conducted. The OR and associated statistics were calculated based on unadjusted total numbers of participants and events. These were compared with calculations that first adjusted the numbers at risk for censoring using a simple model. RESULTS: Pooled OR were changed in 17/24 cases. On average, there was a 2.6% difference between the adjusted and unadjusted OR. Confidence intervals were frequently wider for the adjusted OR. Adjusting also reduced weighting of individual trials with immature follow-up. In 18/24 cases, adjusting reduced statistical heterogeneity and affected the associated P-values. CONCLUSIONS: Reviewers conducting meta-analyses of published time-to-event data where actual numbers at risk are not available should adjust the numbers at risk, estimated from total numbers analysed, to account for immature data and censoring.

Epidemiologic Research Design↗

PubMed2002

To IPD or not to IPD? Advantages and disadvantages of systematic reviews using individual patient data.

Systematic reviews and meta-analyses that obtain original research data on individual participants enrolled in trials have been described as the gold standard of review. However, they may take longer and be more resource intensive than other types of review. The authors describe potential advantages and disadvantages of the individual patient data (IPD) approach, including benefits from improved data quality, benefits afforded by the type of analyses that can be done, and advantages in achieving consensus around results and interpretation by an international multidisciplinary team. Disadvantages and barriers relating to resource and expertise, negotiating collaboration, and software requirements are also discussed. At the outset, reviewers should consider the methodological factors likely to influence results in their particular review setting, together with time and resource constraints, so that an active decision can be made about whether to extract data from published reports, collect additional or replacement summary data from trialists, or collect IPD.

Data Collection↗