Title: Combining experimental and non-experimental data to examine treatment effect heterogeneity
Authors: Elizabeth Stuart - Johns Hopkins Bloomberg School of Public Health (United States)
Carly Lupton-Smith - Johns Hopkins Bloomberg School of Public Health (United States) [presenting]
Abstract: Determining what works for whom is a key goal in prevention and treatment across a variety of areas, including mental health. Identifying effect moderator factors that relate to the size of treatment effects is crucial for the delivery of treatment and prevention interventions, but doing so is incredibly difficult using standard study designs. Randomized trials, the gold standard for estimating average effects, are typically underpowered to detect moderation. Large-scale nonexperimental studies may provide another way to examine the effect of moderation, but can suffer from confounding. Recent machine learning and Bayesian methods advances are described to combine randomized trials and electronic health record (EHR) data to examine effect heterogeneity. We present results from simulation studies comparing a set of recently proposed methods for combining data sources, with the goal of estimating conditional average treatment effects. We also provide an initial application of the methods to data from randomized trials and electronic health record data of individuals receiving medication treatment for major depressive disorder.