Compositional Q-learning for electrolyte repletion with imbalanced patient sub-populations

TL;DR

The paper introduces CFQI, a compositional reinforcement learning method that effectively handles heterogeneous patient responses in medical treatment planning, demonstrated through electrolyte repletion scenarios.

Contribution

CFQI is a novel compositional Q-learning approach that models and learns from heterogeneous treatment responses, improving decision-making in personalized medical care.

Findings

CFQI performs robustly with class imbalance in patient sub-populations.

CFQI effectively leverages shared knowledge across task variants.

CFQI shows promise for clinical applications with compositional structures.

Abstract

Reinforcement learning (RL) is an effective framework for solving sequential decision-making tasks. However, applying RL methods in medical care settings is challenging in part due to heterogeneity in treatment response among patients. Some patients can be treated with standard protocols whereas others, such as those with chronic diseases, need personalized treatment planning. Traditional RL methods often fail to account for this heterogeneity, because they assume that all patients respond to the treatment in the same way (i.e., transition dynamics are shared). We introduce Compositional Fitted $Q$-iteration (CFQI), which uses a compositional task structure to represent heterogeneous treatment responses in medical care settings. A compositional task consists of several variations of the same task, each progressing in difficulty; solving simpler variants of the task can enable efficient solving of harder variants. CFQI uses a compositional $Q$-value function with separate modules for each task variant, allowing it to take advantage of shared knowledge while learning distinct policies for each variant. We validate CFQI's performance using a Cartpole environment and use CFQI to recommend electrolyte repletion for patients with and without renal disease. Our results demonstrate that CFQI is robust even in the presence of class imbalance, enabling effective information usage across patient sub-populations. CFQI exhibits great promise for clinical applications in scenarios characterized by known compositional structures.