Keith R. Abrams

The risk of colorectal cancer in ulcerative colitis: a meta-analysis

BACKGROUND AND AIMS Controversy surrounds the risk of colorectal cancer (CRC) in ulcerative colitis (UC). Many studies have investigated this risk and reported widely varying rates. METHODS A literature search using Medline with the explosion of references identified 194 studies. Of these, 116 met our inclusion criteria from which the number of patients and cancers detected could be extracted. Overall pooled estimates, with 95% confidence intervals (CI), of cancer prevalence and incidence were obtained using a random effects model on either the log odds or log incidence scale, as appropriate. RESULTS The overall prevalence of CRC in any UC patient, based on 116 studies, was estimated to be 3.7% (95% CI 3.2–4.2%). Of the 116 studies, 41 reported colitis duration. From these the overall incidence rate was 3/1000 person years duration (pyd), (95% CI 2/1000 to 4/1000). The overall incidence rate for any child was 6/1000 pyd (95% CI 3/1000 to 13/1000). Of the 41 studies, 19 reported results stratified into 10 year intervals of disease duration. For the first 10 years the incidence rate was 2/1000 pyd (95% CI 1/1000 to 2/1000), for the second decade the incidence rate was estimated to be 7/1000 pyd (95% CI 4/1000 to 12/1000), and in the third decade the incidence rate was 12/1000 pyd (95% CI 7/1000 to 19/1000). These incidence rates corresponded to cumulative probabilities of 2% by 10 years, 8% by 20 years, and 18% by 30 years. The worldwide cancer incidence rates varied geographically, being 5/1000 pyd in the USA, 4/1000 pyd in the UK, and 2/1000 pyd in Scandinavia and other countries. Over time the cancer risk has increased since 1955 but this finding was not significant (p=0.8). CONCLUSIONS Using new meta-analysis techniques we determined the risk of CRC in UC by decade of disease and defined the risk in pancolitics and children. We found a non-significant increase in risk over time and estimated how risk varies with geography.

Pharmacological and lifestyle interventions to prevent or delay type 2 diabetes in people with impaired glucose tolerance: systematic review and meta-analysis

Objective To quantify the effectiveness of pharmacological and lifestyle interventions to prevent or delay type 2 diabetes in people with impaired glucose tolerance. Data sources Medline, Embase, and the Cochrane library searched up to July 2006. Expert opinions sought and reference lists of identified studies and any relevant published reviews checked. Study selection Randomised controlled trials that evaluated interventions to delay or prevent type 2 diabetes in individuals with impaired glucose tolerance. Results 21 trials met the inclusion criteria, of which 17, with 8084 participants with impaired glucose tolerance, reported results in enough detail for inclusion in the meta-analyses. From the meta-analyses the pooled hazard ratios were 0.51 (95% confidence interval 0.44 to 0.60) for lifestyle interventions v standard advice, 0.70 (0.62 to 0.79) for oral diabetes drugs v control, 0.44 (0.28 to 0.69) for orlistat v control, and 0.32 (0.03 to 3.07) for the herbal remedy jiangtang bushen recipe v standard diabetes advice. These correspond to numbers needed to treat for benefit (NNTB) and harm (NNTH) of 6.4 for lifestyle (95% credible interval, NNTB 5.0 to NNTB 8.4), 10.8 for oral diabetes drugs (NNTB 8.1 to NNTB 15.0), 5.4 for orlistat (NNTB 4.1 to NNTB 7.6), and 4.0 for jiangtang bushen (NNTH 16.9 to NNTB 24.8). Conclusions Lifestyle and pharmacological interventions reduce the rate of progression to type 2 diabetes in people with impaired glucose tolerance. Lifestyle interventions seem to be at least as effective as drug treatment.

Empirical assessment of effect of publication bias on meta-analyses

Abstract Objective: To assess the effect of publication bias on the results and conclusions of systematic reviews and meta-analyses. Design: Analysis of published meta-analyses by trim and fill method. Studies: 48 reviews in Cochrane Database of Systematic Reviews that considered a binary endpoint and contained 10 or more individual studies. Main outcome measures: Number of reviews with missing studies and effect on conclusions of meta-analyses. Results: The trim and fill fixed effects analysis method estimated that 26 (54%) of reviews had missing studies and in 10 the number missing was significant. The corresponding figures with a random effects model were 23 (48%) and eight. In four cases, statistical inferences regarding the effect of the intervention were changed after the overall estimate for publication bias was adjusted for. Conclusions: Publication or related biases were common within the sample of meta-analyses assessed. In most cases these biases did not affect the conclusions. Nevertheless, researchers should check routinely whether conclusions of systematic reviews are robust to possible non-random selection mechanisms.

Contour-enhanced meta-analysis funnel plots help distinguish publication bias from other causes of asymmetry

OBJECTIVES To present the contour-enhanced funnel plot as an aid to differentiating asymmetry due to publication bias from that due to other factors. STUDY DESIGN AND SETTING An enhancement to the usual funnel plot is proposed that allows the statistical significance of study estimates to be considered. Contour lines indicating conventional milestones in levels of statistical significance (e.g., <0.01, <0.05, <0.1) are added to funnel plots. RESULTS This contour overlay aids the interpretation of the funnel plot. For example, if studies appear to be missing in areas of statistical nonsignificance, then this adds credence to the possibility that the asymmetry is due to publication bias. Conversely, if the supposed missing studies are in areas of higher statistical significance, this would suggest the cause of the asymmetry may be more likely to be due to factors other than publication bias, such as variable study quality. CONCLUSIONS We believe this enhancement to funnel plots (i) is simple to implement, (ii) is widely applicable, (iii) greatly improves interpretability, and (iv) should be used routinely.

Bayesian methods in meta-analysis and evidence synthesis.

This paper reviews the use of Bayesian methods in meta-analysis. Whilst there has been an explosion in the use of meta-analysis over the last few years, driven mainly by the move towards evidence-based healthcare, so too Bayesian methods are being used increasingly within medical statistics. Whilst in many meta-analysis settings the Bayesian models used mirror those previously adopted in a frequentist formulation, there are a number of specific advantages conferred by the Bayesian approach. These include: full allowance for all parameter uncertainty in the model, the ability to include other pertinent information that would otherwise be excluded, and the ability to extend the models to accommodate more complex, but frequently occurring, scenarios. The Bayesian methods discussed are illustrated by means of a meta-analysis examining the evidence relating to electronic fetal heart rate monitoring and perinatal mortality in which evidence is available from a variety of sources.

Meta‐analysis: colorectal and small bowel cancer risk in patients with Crohn's disease

Background  Crohns disease is associated with small bowel cancer whilst risk of colorectal cancer is less clear.

Effectiveness of neuraminidase inhibitors in treatment and prevention of influenza A and B: systematic review and meta-analyses of randomised controlled trials

Abstract Objective To review the clinical effectiveness of oseltamivir and zanamivir for the treatment and prevention of influenza A and B. Design Systematic review and meta-analyses of randomised controlled trials. Data sources Published studies were retrieved from electronic bibliographic databases; supplementary data were obtained from the manufacturers. Selection of studies Randomised controlled, double blind trials that were published in English, had data available before 31 December 2001, evaluated treatment or prevention of naturally occurring influenza with zanamivir or oseltamivir (if given using the formulation and dosage licensed for clinical use), and reported at least one end point of relevance. Review methods The main outcome measures were the median time to the alleviation of symptoms (for treatment trials) and number of flu episodes avoided (for prevention trials). Three population groups were defined: children aged 12 years and under; otherwise healthy individuals aged 12 to 65 years; and “high risk” individuals (those with certain chronic medical conditions or aged 65 years and older). Results Seventeen treatment trials and seven prevention trials identified met the inclusion criteria. All trials included compared one of the drugs against placebo or standard care. Treatment of children, otherwise healthy individuals, and high risk populations with zanamivir reduced the median duration of symptoms in days respectively by 1.0 (95% confidence interval 0.5 to 1.5), 0.8 (0.3 to 1.3), and 0.9 (−0.1 to 1.9) for the intention to treat population. The corresponding results, in days, for oseltamivir were 0.9 (0.3 to 1.5), 0.9 (0.3 to 1.4), and 0.4 (−0.7 to 1.4). The effect of giving zanamivir and oseltamivir prophylactically resulted in a relative reduction of 70-90% in the odds of developing flu, depending on the strategy adopted and the population studied. Conclusions Evidence from randomised controlled trials consistently supports the view that both oseltamivir and zanamivir are clinically effective for treating and preventing flu. However, evidence is limited for the treatment of certain populations and for all prevention strategies.

A comparison of summary patient-level covariates in meta-regression with individual patient data meta-analysis

OBJECTIVES To compare meta-analysis of summary study level data with the equivalent individual patient data (IPD) analysis when interest lies in identification of binary patient characteristics related to treatment efficacy. DESIGN A simulation study comparing meta-regression with IPD analyses of randomized controlled trials. METHODS Twenty-seven different meta-analysis situations were simulated with 1000 repetitions in each case. The following parameters were varied: (1) the treatment effect magnitude for different patient risk groups; (2) sample sizes of individual studies; and (3) number of studies. The meta-regression and IPD results were then compared for each situation. RESULTS The statistical power of meta-regression was dramatically and consistently lower than that of IPD analysis, with little agreement between the parameter estimates obtained from the two methods. Only in meta-analyses of large numbers of large trials, did meta-regression detect differential treatment effects between risk groups with any consistency. CONCLUSIONS Meta-analysis of summary data may be adequate when estimating a single pooled treatment effect or investigating study level characteristics. However, when interest lies in investigating whether patient characteristics are related to treatment, IPD analysis will generally be necessary to discover any such relationships. In these situations practitioners should try to obtain individual-level data.

Bayesian methods for evidence synthesis in cost-effectiveness analysis

Recently, health systems internationally have begun to use cost-effectiveness research as formal inputs into decisions about which interventions and programmes should be funded from collective resources. This process has raised some important methodological questions for this area of research. This paper considers one set of issues related to the synthesis of effectiveness evidence for use in decision-analytic cost-effectiveness (CE) models, namely the need for the synthesis of all sources of available evidence, although these may not ‘fit neatly’ into a CE model.Commonly encountered problems include the absence of head-to-head trial evidence comparing all options under comparison, the presence of multiple endpoints from trials and different follow-up periods. Full evidence synthesis for CE analysis also needs to consider treatment effects between patient subpopulations and the use of nonrandomised evidence.Bayesian statistical methods represent a valuable set of analytical tools to utilise indirect evidence and can make a powerful contribution to the decision-analytic approach to CE analysis. This paper provides a worked example and a general overview of these methods with particular emphasis on their use in economic evaluation.

Methods in health service research: An introduction to bayesian methods in health technology assessment

This is the third of four articles Bayess theorem arose from a posthumous publication in 1763 by Thomas Bayes, a non-conformist minister from Tunbridge Wells. Although it gives a simple and uncontroversial result in probability theory, specific uses of the theorem have been the subject of considerable controversy for more than two centuries. In recent years a more balanced and pragmatic perspective has emerged, and in this paper we review current thinking on the value of the Bayesian approach to health technology assessment. A concise definition of bayesian methods in health technology assessment has not been established, but we suggest the following: the explicit quantitative use of external evidence in the design, monitoring, analysis, interpretation, and reporting of a health technology assessment. This approach acknowledges that judgments about the benefits of a new technology will rarely be based solely on the results of a single study but should synthesise evidence from multiple sources—for example, pilot studies, trials of similar interventions, and even subjective judgments about the generalisability of the studys results. A bayesian perspective leads to an approach to clinical trials that is claimed to be more flexible and ethical than traditional methods,1 and to elegant ways of handling multiple substudies—for example, when simultaneously estimating the effects of a treatment on many subgroups.2 Proponents have also argued that a bayesian approach allows conclusions to be provided in a form that is most suitable for decisions specific to patients and decisions affecting public policy.3 #### Summary points Bayesian methods interpret data from a study in the light of external evidence and judgment, and the form in which conclusions are drawn contributes naturally to decision making Prior plausibility of hypotheses is taken into account, just as when interpreting the results of a diagnostic test Scepticism about large treatment effects can be formally …