Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach

TL;DR

This paper introduces a deep reinforcement learning approach using continuous state-space models to optimize sepsis treatment, capturing detailed physiological data to improve patient outcomes in ICUs.

Contribution

It presents a novel method for deriving interpretable, continuous-space treatment policies for sepsis using deep reinforcement learning, outperforming observed clinical policies.

Findings

Potential to reduce hospital mortality by up to 3.6%.

Learned policies are clinically interpretable and similar to physician decisions.

Model retains detailed physiological information for better decision-making.

Abstract

Sepsis is a leading cause of mortality in intensive care units (ICUs) and costs hospitals billions annually. Treating a septic patient is highly challenging, because individual patients respond very differently to medical interventions and there is no universally agreed-upon treatment for sepsis. Understanding more about a patient's physiological state at a given time could hold the key to effective treatment policies. In this work, we propose a new approach to deduce optimal treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Learning treatment policies over continuous spaces is important, because we retain more of the patient's physiological information. Our model is able to learn clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. Evaluating our algorithm on past ICU patient data, we find that our model could reduce patient mortality in the hospital by up to 3.6% over observed clinical policies, from a baseline mortality of 13.7%. The learned treatment policies could be used to aid intensive care clinicians in medical decision making and improve the likelihood of patient survival.