Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment

TL;DR

This paper presents a novel approach combining deep reinforcement learning with physiological models to develop personalized, uncertainty-aware sepsis treatment strategies that are explainable and aligned with clinical knowledge.

Contribution

It introduces a physiologically driven recurrent autoencoder and a framework for uncertainty-aware decision support in sepsis treatment using deep reinforcement learning.

Findings

Learned physiologically explainable treatment policies

Identified high-risk states associated with mortality

Demonstrated robustness and clinical consistency of the approach

Abstract

Sepsis is a potentially life threatening inflammatory response to infection or severe tissue damage. It has a highly variable clinical course, requiring constant monitoring of the patient's state to guide the management of intravenous fluids and vasopressors, among other interventions. Despite decades of research, there's still debate among experts on optimal treatment. Here, we combine for the first time, distributional deep reinforcement learning with mechanistic physiological models to find personalized sepsis treatment strategies. Our method handles partial observability by leveraging known cardiovascular physiology, introducing a novel physiology-driven recurrent autoencoder, and quantifies the uncertainty of its own results. Moreover, we introduce a framework for uncertainty aware decision support with humans in the loop. We show that our method learns physiologically explainable, robust policies that are consistent with clinical knowledge. Further our method consistently identifies high risk states that lead to death, which could potentially benefit from more frequent vasopressor administration, providing valuable guidance for future research