随机对照试验中介分析方法导论。

An introduction to mediation analyses of randomized controlled trials.

机构信息

Centre for Pain IMPACT, Neuroscience Research Australia, Sydney, Australia; Prince of Wales Clinical School, University of New South Wales, Sydney, Australia.

Centre for Statistics in Medicine & Rehabilitation Research in Oxford, Nuffield Department of Orthopaedics Rheumatology and Musculoskeletal Sciences (NDORMS), University of Oxford, Oxford, UK; School of Medicine and Public Health, University of Newcastle, Newcastle, Australia.

出版信息

J Clin Epidemiol. 2021 May;133:161-164. doi: 10.1016/j.jclinepi.2021.02.014. Epub 2021 Feb 16.

DOI:10.1016/j.jclinepi.2021.02.014

PMID:33607244

Abstract

Mediation analyses of randomized controlled trials can be used to investigate the mechanisms by which health interventions cause outcomes. In this article we provide a brief introduction to mediation analysis in the context of randomized controlled trials. We introduce common target effects, causal assumptions, estimation approaches, and illustrate these concepts using a published mediation analysis of the Systolic Blood Pressure Intervention Trial. Well-conducted mediation analyses of randomized trials can provide meaningful insights to guide clinical and policy decisions.

摘要

随机对照试验的中介分析可用于研究健康干预措施导致结果的机制。本文在随机对照试验的背景下简要介绍了中介分析。我们介绍了常见的目标效应、因果假设、估计方法，并使用发表的收缩压干预试验的中介分析来说明这些概念。精心进行的随机试验中介分析可以为指导临床和政策决策提供有意义的见解。