Bayesian meta-analysis of multiple treatment comparisons: an introduction to mixed treatment comparisons

Abstract

Recently, mixed treatment comparisons (MTC) have been presented as an extension of traditional meta-analysis by including multiple different pairwise comparisons across a range of different interventions. MTC allow for indirect comparisons and can therefore provide very useful information for clinical and reimbursement decision-making in the absence of head-to-head data. In this article, we provide an introductory overview of MTC illustrated with example analyses of different drug treatments in rheumatoid arthritis using a continuous patient-reported end point. As a background, we start with an overview of the traditional meta-analyses for pairwise trials, and the difference between a traditional approach and a Bayesian approach. Next, the Bayesian MTC for continuous outcomes are presented. We finish with a discussion of how MTC can best be presented in order to maximize acceptance by target audiences, i.e., clinicians and market access decision-makers.