Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine

Theresa Blumlein, Joel Persson, Stefan Feuerriegel
Proceedings of the 7th Machine Learning for Healthcare Conference, PMLR 182:146-171, 2022.

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 causal trees (DTR-CT) and DTR causal forest (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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v182-blumlein22a, title = {Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine}, author = {Blumlein, Theresa and Persson, Joel and Feuerriegel, Stefan}, booktitle = {Proceedings of the 7th Machine Learning for Healthcare Conference}, pages = {146--171}, year = {2022}, editor = {Lipton, Zachary and Ranganath, Rajesh and Sendak, Mark and Sjoding, Michael and Yeung, Serena}, volume = {182}, series = {Proceedings of Machine Learning Research}, month = {05--06 Aug}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v182/blumlein22a/blumlein22a.pdf}, url = {https://proceedings.mlr.press/v182/blumlein22a.html}, 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 causal trees (DTR-CT) and DTR causal forest (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.} }
Endnote
%0 Conference Paper %T Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine %A Theresa Blumlein %A Joel Persson %A Stefan Feuerriegel %B Proceedings of the 7th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2022 %E Zachary Lipton %E Rajesh Ranganath %E Mark Sendak %E Michael Sjoding %E Serena Yeung %F pmlr-v182-blumlein22a %I PMLR %P 146--171 %U https://proceedings.mlr.press/v182/blumlein22a.html %V 182 %X 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 causal trees (DTR-CT) and DTR causal forest (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.
APA
Blumlein, T., Persson, J. & Feuerriegel, S.. (2022). Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine. Proceedings of the 7th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 182:146-171 Available from https://proceedings.mlr.press/v182/blumlein22a.html.

Related Material