Dynamic Treatment Regime

Dynamic treatment regimes (DTRs) aim to personalize sequential treatment decisions by tailoring interventions to individual patient characteristics and responses over time. Current research heavily utilizes reinforcement learning (RL) algorithms, including Q-learning and actor-critic methods, often enhanced with techniques like Bayesian learning or distributed computing to handle large, complex datasets and address challenges like confounding and missing data. This field is crucial for advancing personalized medicine, enabling more effective and efficient treatment strategies across various healthcare settings, particularly for chronic diseases where treatment decisions are made over extended periods. A key focus is on robust methods that account for real-world complexities such as non-compliance and heterogeneous treatment effects.

Papers

May 28, 2024

May 2, 2024

Dynamic Local Average Treatment Effects
Ravi B. Sojitra, Vasilis Syrgkanis
Treatment Effect Unobserved Confounders Dynamic Treatment Regime Time Varying Treatment Dynamic Treatment Effect

October 30, 2023

Stage-Aware Learning for Dynamic Treatments
Hanwen Ye, Wenzhuo Zhou, Ruoqing Zhu, Annie Qu
Multi Stage Dynamic Treatment Regime Optimal Treatment Optimal Regime

September 12, 2023

Optimal and Fair Encouragement Policy Evaluation and Learning
Angela Zhou
LeArning Abstract Optimal Policy Fairness Constraint Proportional Fairness Dynamic Treatment Regime Preference Distribution Eligibility Criterion

July 22, 2023

A Flexible Framework for Incorporating Patient Preferences Into Q-Learning
Joshua P. Zitovsky, Leslie Wilson, Michael R. Kosorok
Q Learning Preference Feedback Multiple Outcome Dynamic Treatment Regime Utility Learning

March 8, 2023

Inference on Optimal Dynamic Policies via Softmax Approximation
Qizhao Chen, Morgane Austern, Vasilis Syrgkanis
Scientific Inference Optimal Policy Softmax Function Dynamic Treatment Regime Optimal Treatment Optimal Regime

February 21, 2023

Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes
Di Wang, Yao Wang, Shaojie Tang, Shao-Bo Lin
Reinforcement Learning Q Learning Clean Distribution Dynamic Treatment Regime

January 3, 2023

Deep Spectral Q-learning with Application to Mobile Health
Yuhe Gao, Chengchun Shi, Rui Song
Application Proficiency Principal Component Analysis Deep Q Learning Mobile Health Dynamic Treatment Regime Time Varying Covariates

October 26, 2022

Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach
Yunzhe Zhou, Zhengling Qi, Chengchun Shi, Lexin Li
Dynamic Treatment Regime Optimistic Learning

October 20, 2022

Synthetic Blip Effects: Generalizing Synthetic Controls for the Dynamic Treatment Regime
Anish Agarwal, Vasilis Syrgkanis
Impulse Response Individual Treatment Effect Dynamic Treatment Regime Synthetic Control Synthetic Intervention

June 22, 2022

Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space
Zeyu Wang, Huiying Zhao, Peng Ren, Yuxi Zhou, Ming Sheng
Deep Reinforcement Learning Offline Reinforcement Learning Real Time Continuous Space Standard Sepsis Dynamic Treatment Regime Optimal Treatment Medical Decision

June 11, 2022

Federated Offline Reinforcement Learning
Doudou Zhou, Yufeng Zhang, Aaron Sonabend-W, Zhaoran Wang, Junwei Lu, Tianxi Cai
Markov Decision Process Offline Reinforcement Learning Policy Optimization Offline Reinforcement Learning Algorithm Dynamic Treatment Regime Federated Offline Reinforcement Learning

May 19, 2022

Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes
Changchang Yin, Ruoqi Liu, Jeffrey Caterino, Ping Zhang
Reinforcement Learning Actor Critic Policy Adaptation Dynamic Treatment Regime

April 14, 2022

Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine
Theresa Blümlein, Joel Persson, Stefan Feuerriegel
Time Varying Dynamic Treatment Regime Causal Forest Sequential Treatment Causality Method

March 4, 2022

Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions
Nina Deliu, Joseph Jay Williams, Bibhas Chakraborty
Reinforcement Learning Mobile Health Adaptive Intervention Dynamic Treatment Regime

December 8, 2021

Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach
Soroush Saghafian
Unobserved Confounders Underlying Causal Dynamic Treatment Regime Optimal Treatment

Dynamic Treatment Regime

Papers

DTR-Bench: An in silico Environment and Benchmark Platform for Reinforcement Learning Based Dynamic Treatment Regime

Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination

Dynamic Local Average Treatment Effects

Stage-Aware Learning for Dynamic Treatments

Optimal and Fair Encouragement Policy Evaluation and Learning

A Flexible Framework for Incorporating Patient Preferences Into Q-Learning

Inference on Optimal Dynamic Policies via Softmax Approximation

Kernel-Based Distributed Q-Learning: A Scalable Reinforcement Learning Approach for Dynamic Treatment Regimes

Deep Spectral Q-learning with Application to Mobile Health

Optimizing Pessimism in Dynamic Treatment Regimes: A Bayesian Learning Approach

Synthetic Blip Effects: Generalizing Synthetic Controls for the Dynamic Treatment Regime

Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space

Federated Offline Reinforcement Learning

Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes

Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine

Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions

Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach