Evidence Synthesis for Decision Making 3: Heterogeneity Subgroups, Meta-Regression, Bias, and Bias-Adjustment

Sofia Dias*, Alex J. Sutton, Nicky J Welton, A E Ades

*Corresponding author for this work

Research output: Contribution to journalArticle (Academic Journal)

171 Citations (Scopus)
313 Downloads (Pure)

Abstract

In meta-analysis, between-study heterogeneity indicates the presence of effect-modifiers and has implications for the interpretation of results in cost-effectiveness analysis and decision making. A distinction is usually made between true variability in treatment effects due to variation in patient populations or settings and biases related to the way in which trials were conducted. Variability in relative treatment effects threatens the external validity of trial evidence and limits the ability to generalize from the results; imperfections in trial conduct represent threats to internal validity. We provide guidance on methods for meta-regression and bias-adjustment, in pairwise and network meta-analysis (including indirect comparisons), using illustrative examples. We argue that the predictive distribution of a treatment effect in a new trial may, in many cases, be more relevant to decision making than the distribution of the mean effect. Investigators should consider the relative contribution of true variability and random variation due to biases when considering their response to heterogeneity. In network meta-analyses, various types of meta-regression models are possible when trial-level effect-modifying covariates are present or suspected. We argue that a model with a single interaction term is the one most likely to be useful in a decision-making context. Illustrative examples of Bayesian meta-regression against a continuous covariate and meta-regression against baseline risk are provided. Annotated WinBUGS code is set out in an appendix.

In meta-analysis, between-study heterogeneity indicates the presence of effect-modifiers and has implications for the interpretation of results in cost-effectiveness analysis and decision making. A distinction is usually made between true variability in treatment effects due to variation in patient populations or settings and biases related to the way in which trials were conducted. Variability in relative treatment effects threatens the external validity of trial evidence and limits the ability to generalize from the results; imperfections in trial conduct represent threats to internal validity. We provide guidance on methods for meta-regression and bias-adjustment, in pairwise and network meta-analysis (including indirect comparisons), using illustrative examples. We argue that the predictive distribution of a treatment effect in a new trial may, in many cases, be more relevant to decision making than the distribution of the mean effect. Investigators should consider the relative contribution of true variability and random variation due to biases when considering their response to heterogeneity. In network meta-analyses, various types of meta-regression models are possible when trial-level effect-modifying covariates are present or suspected. We argue that a model with a single interaction term is the one most likely to be useful in a decision-making context. Illustrative examples of Bayesian meta-regression against a continuous covariate and meta-regression against baseline risk are provided. Annotated WinBUGS code is set out in an appendix.

In meta-analysis, between-study heterogeneity indicates the presence of effect-modifiers and has implications for the interpretation of results in cost-effectiveness analysis and decision making. A distinction is usually made between true variability in treatment effects due to variation in patient populations or settings and biases related to the way in which trials were conducted. Variability in relative treatment effects threatens the external validity of trial evidence and limits the ability to generalize from the results; imperfections in trial conduct represent threats to internal validity. We provide guidance on methods for meta-regression and bias-adjustment, in pairwise and network meta-analysis (including indirect comparisons), using illustrative examples. We argue that the predictive distribution of a treatment effect in a new trial may, in many cases, be more relevant to decision making than the distribution of the mean effect. Investigators should consider the relative contribution of true variability and random variation due to biases when considering their response to heterogeneity. In network meta-analyses, various types of meta-regression models are possible when trial-level effect-modifying covariates are present or suspected. We argue that a model with a single interaction term is the one most likely to be useful in a decision-making context. Illustrative examples of Bayesian meta-regression against a continuous covariate and meta-regression against baseline risk are provided. Annotated WinBUGS code is set out in an appendix.

In meta-analysis, between-study heterogeneity indicates the presence of effect-modifiers and has implications for the interpretation of results in cost-effectiveness analysis and decision making. A distinction is usually made between true variability in treatment effects due to variation in patient populations or settings and biases related to the way in which trials were conducted. Variability in relative treatment effects threatens the external validity of trial evidence and limits the ability to generalize from the results; imperfections in trial conduct represent threats to internal validity. We provide guidance on methods for meta-regression and bias-adjustment, in pairwise and network meta-analysis (including indirect comparisons), using illustrative examples. We argue that the predictive distribution of a treatment effect in a new trial may, in many cases, be more relevant to decision making than the distribution of the mean effect. Investigators should consider the relative contribution of true variability and random variation due to biases when considering their response to heterogeneity. In network meta-analyses, various types of meta-regression models are possible when trial-level effect-modifying covariates are present or suspected. We argue that a model with a single interaction term is the one most likely to be useful in a decision-making context. Illustrative examples of Bayesian meta-regression against a continuous covariate and meta-regression against baseline risk are provided. Annotated WinBUGS code is set out in an appendix.

Original languageEnglish
Pages (from-to)618-640
Number of pages23
JournalMedical Decision Making
Volume33
Issue number5
DOIs
Publication statusPublished - Jul 2013

Bibliographical note

Date of Acceptance: 20/12/2012

Keywords

  • cost-effectiveness analysis
  • Bayesian meta-analysis
  • comparative effectiveness
  • systematic reviews
  • individual patient data
  • treatment comparison
  • mixed treatment comparison
  • level data
  • empirical evidence
  • controlled trials
  • clinical trials
  • aggregate data
  • outcomes

Projects

Activities

  • 3 Participation in workshop, seminar, course

INSERM Workshop 234: Network meta-analysis

Sofia Dias (Invited speaker)

4 Jun 2015

Activity: Participating in or organising an event typesParticipation in workshop, seminar, course

Evidence Synthesis for Decision Making Short Course

Nicky J Welton (Participant)

20 Oct 2013

Activity: Participating in or organising an event typesParticipation in workshop, seminar, course

35th Annual Meeting of the Society for Medical Decision Making

Sofia Dias (Speaker)

20 Oct 2013

Activity: Participating in or organising an event typesParticipation in workshop, seminar, course

Cite this