All Times EDT
Keywords: Causal inference, Individualized treatment regimen, RMST, Personalized medicine
In this presentation we provide an overview and evaluation of machine learning methods for estimating individualized treatment regimens (ITR) for time-to-event outcomes maximizing restricted mean survival time (RMST) in observational studies with non-randomized treatment assignment. We present extensive simulation studies that closely mimicked real-world data under a set of scenarios representing different degrees of alignment between the observed regimen, which reflects the actual prescribing practice, and the optimal ITR. The simulation results include performance characteristics of the candidate methods in terms of their ability to recover the true optimal ITR and various empirical measures of RMST gain based on the comparison between the estimated ITR and the actual prescribing practice.