Based on the condition of alcohol dependant patients (S1), the physician may prescribe a medication or behavioral therapy (X1).

Treatment individualization and adaptation over time are crucial for managing chronic diseases.

A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments and covariates' history. These regimes are particularly effective for managing chronic disorders and is arguably one of the key aspects towards more personalized decision-making. In this paper, we investigate the online reinforcement learning (RL) problem for selecting optimal DTRs provided that observational data is available. We develop the first adaptive algorithm that achieves near-optimal regret in DTRs in online settings, without any access to historical data. We further derive informative bounds on the system dynamics of the underlying DTR from confounded, observational data. Finally, we combine these results and develop a novel RL algorithm that efficiently learns the optimal DTR while leveraging the abundant, yet imperfect confounded observations.

An alternative is to randomize patients' treatments at each stage based on the previous decisions and observed outcomes; for instance, one popular strategy is known as the sequential multiple assignment randomized trail (SMART) [

We thank the reviewers for their thoughtful feedback. The applications of online RL in health care are motivated by the increasing "use For experimental studies (e.g., RCTs) in DTRs, issues of sample Our analysis reveals that this is not the case. We really appreciate the reviewers for the helpful suggestions and references.

A dynamic treatment regime (DTR) consists of a sequence of decision rules, one per stage of intervention, that dictates how to determine the treatment assignment to patients based on evolving treatments and covariates' history. These regimes are particularly effective for managing chronic disorders and is arguably one of the key aspects towards more personalized decision-making. In this paper, we investigate the online reinforcement learning (RL) problem for selecting optimal DTRs provided that observational data is available. We develop the first adaptive algorithm that achieves near-optimal regret in DTRs in online settings, without any access to historical data. We further derive informative bounds on the system dynamics of the underlying DTR from confounded, observational data.

Precision health, increasingly supported by digital technologies, is a domain of research that broadens the paradigm of precision medicine, advancing everyday healthcare. This vision goes hand in hand with the groundbreaking advent of artificial intelligence (AI), which is reshaping the way we diagnose, treat, and monitor both clinical subjects and the general population. AI tools powered by machine learning have shown considerable improvements in a variety of healthcare domains. In particular, reinforcement learning (RL) holds great promise for sequential and dynamic problems such as dynamic treatment regimes and just-in-time adaptive interventions in digital health. In this work, we discuss the opportunity offered by AI, more specifically RL, to current trends in healthcare, providing a methodological survey of RL methods in the context of precision and digital health. Focusing on the area of adaptive interventions, we expand the methodological survey with illustrative case studies that used RL in real practice. This invited article has undergone anonymous review and is intended as a book chapter for the volume "Frontiers of Statistics and Data Science" edited by Subhashis Ghoshal and Anindya Roy for the International Indian Statistical Association Series on Statistics and Data Science, published by Springer. It covers the material from a short course titled "Artificial Intelligence in Precision and Digital Health" taught by the author Bibhas Chakraborty at the IISA 2022 Conference, December 26-30 2022, at the Indian Institute of Science, Bengaluru.

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.