Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine

TL;DR

This paper introduces two novel causal tree-based methods, DTR-CT and DTR-CF, for learning optimal dynamic treatment regimes in medicine, effectively handling complex patient data and improving treatment personalization.

Contribution

It is the first to adapt causal tree methods for learning optimal DTRs, addressing limitations of previous outcome prediction and linear models.

Findings

Outperform state-of-the-art baselines in synthetic data

Achieve higher percentage of optimal decisions in ICU data

Reduce cumulative regret significantly

Abstract

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.