Bayesian meta-analysis of multiple treatment comparisons: An introduction to mixed treatment comparisons
Bayesian meta-analysis of multiple treatment comparisons: An introduction to mixed treatment comparisons
复制标题
DOI：
10.1111/j.1524-4733.2008.00347.x
复制
发表时间：
2008-09-01
期刊：
影响因子：
4.5
通讯作者：
Stam, Wiro
中科院分区：
文献类型：
--
作者：
Jansen, Jeroen P.;Crawford, Bruce;Stam, Wiro
最近，混合治疗比较(MTC)被提出作为传统荟萃分析的扩展，它包括了一系列不同干预措施的多个不同的成对比较。MTC允许间接比较，因此在缺乏逐一数据的情况下，可以为临床和报销决策提供非常有用的信息。在这篇文章中，我们提供了MTC的介绍性概述，并使用患者报告的连续终点对类风湿性关节炎的不同药物治疗进行了实例分析。作为背景，我们首先概述了传统的配对试验的荟萃分析，以及传统方法和贝叶斯方法之间的差异。其次，给出了连续结果的贝叶斯MTC。最后，我们讨论了如何最好地呈现MTC，以便最大限度地被目标受众，即临床医生和市场准入决策者所接受。
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.