Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine
This work addresses the challenge of personalizing sequential treatment decisions in medicine, particularly for patient data from electronic health records, though it appears incremental as it adapts existing causal tree methods to a new application.
The authors tackled the problem of learning optimal dynamic treatment regimes (DTRs) in medicine by developing two novel methods, DTR-CT and DTR-CF, based on causal tree methods to handle complex patient data and estimate heterogeneous treatment effects. Their methods outperformed state-of-the-art baselines in synthetic and real-world ICU data, achieving significant improvements in cumulative regret and percentage of optimal decisions.
Dynamic treatment regimes (DTRs) are used in medicine to tailor sequential treatment decisions to patients by considering patient heterogeneity. Common methods for learning optimal DTRs, however, have shortcomings: they are typically based on outcome prediction and not treatment effect estimation, or they use linear models that are restrictive for patient data from modern electronic health records. To address these shortcomings, we develop two novel methods for learning optimal DTRs that effectively handle complex patient data. We call our methods DTR-CT and DTR-CF. Our methods are based on a data-driven estimation of heterogeneous treatment effects using causal tree methods, specifically causal trees and causal forests, that learn non-linear relationships, control for time-varying confounding, are doubly robust, and explainable. To the best of our knowledge, our paper is the first that adapts causal tree methods for learning optimal DTRs. We evaluate our proposed methods using synthetic data and then apply them to real-world data from intensive care units. Our methods outperform state-of-the-art baselines in terms of cumulative regret and percentage of optimal decisions by a considerable margin. Our work improves treatment recommendations from electronic health record and is thus of direct relevance for personalized medicine.