期刊
ANNALS OF EPIDEMIOLOGY
卷 65, 期 -, 页码 101-108出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/j.annepidem.2021.07.003
关键词
Generalizability; Glycemic control; Heterogeneous treatment effects; Causal forests
资金
- US Department of Veterans Affairs [IK2-CX001907, 465-F, 2008]
- American Heart Association [17MCPRP33670728]
- National Science Foundation [DMS 1914937]
- National Cancer Institute of the US National Institutes of Health [R01 CA129102]
- National Institute of Diabetes and Digestive and Kidney Diseases of the US National Institutes of Health [K23DK109200]
- Veterans Affairs Cooperative Studies Program, Department of Veterans Affairs Office of Research and Development
- American Diabetes Association
- National Eye Institute
- Sanofi
- GlaxoSmithKline
- Novo Nordisk
- Roche
- Kos Pharmaceuticals
- Merck
- Amylin
The generalizability of heterogeneous treatment effects (HTE) derived from machine learning in different study samples is uncertain. In this study, the authors examined the generalizability of HTE detected using causal forests in two randomized trials in type II diabetes patients. They found that while the variable importance was correlated between the two trials, the HTE did not replicate in similar subgroups, suggesting limited generalizability.
Purpose Machine learning is an attractive tool for identifying heterogeneous treatment effects (HTE) of interventions but generalizability of machine learning derived HTE remains unclear. We examined generalizability of HTE detected using causal forests in two similarly designed randomized trials in type II diabetes patients.Methods We evaluated published HTE of intensive versus standard glycemic control on all-cause mortality from the Action to Control Cardiovascular Risk in Diabetes study (ACCORD) in a second trial, the Veterans Affairs Diabetes Trial (VADT). We then applied causal forests to VADT, ACCORD, and pooled data from both studies and compared variable importance and subgroup effects across samples.Results HTE in ACCORD did not replicate in similar subgroups in VADT, but variable importance was correlated between VADT and ACCORD (Kendall's tau-b 0.75). Applying causal forests to pooled individual-level data yielded seven subgroups with similar HTE across both studies, ranging from risk difference of all-cause mortality of-3.9% (95% CI-7.0,-0.8) to 4.7% (95% CI 1.8, 7.5).Conclusions Machine learning detection of HTE subgroups from randomized trials may not generalize across study samples even when variable importance is correlated. Pooling individual-level data may overcome differences in study populations and/or differences in interventions that limit HTE generalizability.Published by Elsevier Inc.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据