Conference Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 480 - Causal Inference and Optimal Decision-Making
Type: Contributed
Date/Time: Wednesday, August 10, 2022 : 2:00 PM to 3:50 PM
Sponsor: Biometrics Section
Abstract #320720
Title: One-Stage Dynamic Treatment Regimes in Longitudinal Studies with Covariate-Driven Observation Times
Author(s): Janie EM Coulombe* and Erica EM Moodie and Susan M Shortreed and Christel Renoux
Companies: McGill University and McGill University and Kaiser Permanente Washington Health Research Institute and Lady Davis Institute
Keywords: Dynamic treatment regime; Observation times; Confounding; Inverse intensity of visit weight; Causal inference

The sequential treatment decisions made by physicians to treat chronic diseases are formalized in the statistical literature as dynamic treatment regimes. To date, methods for dynamic treatment regimes have been developed under the assumption that observation times are determined by study investigators. That assumption is often not satisfied in electronic health records data in which the outcome, the observation times and the treatment mechanism are driven by patients' characteristics. The treatment and observation processes can lead to spurious associations between the treatment of interest and the outcome to be optimized. We address these associations by incorporating two inverse weights that are functions of patient's covariates into dynamic weighted ordinary least squares to develop optimal one-stage dynamic treatment regimes. The method is used to develop an optimal dynamic treatment regime that chooses between two antidepressants to optimize a utility function related to the change in body mass index. We find a small benefit in using our proposed method to tailor treatment to individuals, as compared to estimators that do not account for the irregular observation times.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2022 program