Abstract
Medical treatments tailored to a patient's baseline characteristics hold the potential of improving patient outcomes while reducing negative side effects. Learning individualized treatment rules (ITRs) often requires aggregation of multiple datasets(sites); however, current ITR methodology does not take between-site heterogeneity into account, which can hurt model generalizability when deploying back to each site. To address this problem, we develop a method for individual-level metaanalysis of ITRs, which jointly learns site-specific ITRs while borrowing information about feature sign-coherency via a scientifically-motivated directionality principle. We also develop an adaptive procedure for model tuning, using information criteria tailored to the ITR learning problem. We study the proposed methods through numerical experiments to understand their performance under different levels of between-site heterogeneity and apply the methodology to estimate ITRs in a large multi-center database of electronic health records. This work extends several popular methodologies for estimating ITRs (A-learning, weighted learning) to the multiple-sites setting.
Original language | English (US) |
---|---|
Pages (from-to) | 171-198 |
Number of pages | 28 |
Journal | Proceedings of Machine Learning Research |
Volume | 193 |
State | Published - 2022 |
Event | 2nd Machine Learning for Health Symposium, ML4H 2022 - Hybrid, New Orleans, United States Duration: Nov 28 2022 → … |
Bibliographical note
Funding Information:JJC was supported by an NLM training grant to the Computation and Informatics in Biology and Medicine Training Program (NLM 5T15LM007359). Research reported in this work was partially funded through a Patient-Centered Outcomes Research Institute (PCORI) Award (ME-2018C2-13180). The views in this work are solely the responsibility of the authors and do not necessarily represent the views of the Patient-Centered Outcomes Research Institute (PCORI), its Board of Governors or Methodology Committee.
Publisher Copyright:
© 2022 P.N. Argaw, E. Healey & I.S. Kohane.
Keywords
- Causal inference
- Individualized treatment rule
- Metaanalysis
- Personalized medicine