Laboratoire Techniques de l'Imagerie Médicale et de la Complexité (TIMC-IMAG; UMR 5525), French National Centre for Scientific Research (CNRS), University Grenoble Alpes, La Tronche, France.
OWKIN, Paris, France.
Environ Health Perspect. 2020 May;128(5):55001. doi: 10.1289/EHP6240. Epub 2020 May 6.
Mediation analysis is used in epidemiology to identify pathways through which exposures influence health. The advent of high-throughput (omics) technologies gives opportunities to perform mediation analysis with a high-dimension pool of covariates.
We aimed to highlight some biostatistical issues of this expanding field of high-dimension mediation.
The mediation techniques used for a single mediator cannot be generalized in a straightforward manner to high-dimension mediation. Causal knowledge on the relation between covariates is required for mediation analysis, and it is expected to be more limited as dimension and system complexity increase. The methods developed in high dimension can be distinguished according to whether mediators are considered separately or as a whole. Methods considering each potential mediator separately do not allow efficient identification of the indirect effects when mutual influences exist among the mediators, which is expected for many biological (e.g., epigenetic) parameters. In this context, methods considering all potential mediators simultaneously, based, for example, on data reduction techniques, are more adapted to the causal inference framework. Their cost is a possible lack of ability to single out the causal mediators. Moreover, the ability of the mediators to predict the outcome can be overestimated, in particular because many machine-learning algorithms are optimized to increase predictive ability rather than their aptitude to make causal inference. Given the lack of overarching validated framework and the generally complex causal structure of high-dimension data, analysis of high-dimension mediation currently requires great caution and effort to incorporate biological knowledge. https://doi.org/10.1289/EHP6240.
中介分析被用于流行病学中，以确定暴露如何影响健康的途径。高通量（组学）技术的出现为高维协变量池进行中介分析提供了机会。
我们旨在强调高维中介分析这个扩展领域的一些生物统计学问题。
用于单个中介的中介技术不能直接推广到高维中介。中介分析需要关于协变量之间关系的因果知识，并且随着维度和系统复杂性的增加，预计这种知识会更加有限。根据是否将中介分别考虑，可以将高维中开发的方法区分开来。分别考虑每个潜在中介的方法在中介之间存在相互影响时，不允许有效地识别间接效应，而这在许多生物（例如，表观遗传）参数中是预期的。在这种情况下，同时考虑所有潜在中介的方法，例如基于数据减少技术，更适合因果推理框架。它们的代价可能是无法单独确定因果中介。此外，中介预测结果的能力可能会被高估，特别是因为许多机器学习算法被优化以提高预测能力，而不是它们进行因果推理的能力。鉴于缺乏总体验证框架以及高维数据的一般复杂因果结构，目前对高维中介的分析需要非常谨慎和努力地纳入生物学知识。https://doi.org/10.1289/EHP6240.
