Deep Reinforcement Learning for Sepsis Treatment

Abstract

Sepsis is a leading cause of mortality in intensive care units 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. In this work, we propose an approach to deduce treatment policies for septic patients by using continuous state-space models and deep reinforcement learning. Our model learns clinically interpretable treatment policies, similar in important aspects to the treatment policies of physicians. The learned policies could be used to aid intensive care clinicians in medical decision making and improve the likelihood of patient survival.

Extensions on earlier work (arXiv:1705.08422). Accepted at workshop on Machine Learning For Health at the conference on Neural Information Processing Systems, 2017

Cited by in corpus (12)

• Deconfounding Reinforcement Learning in Observational Settings
• Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
• Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
• An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
• Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients
• Time-series Imputation and Prediction with Bi-Directional Generative Adversarial Networks
• RL4health: Crowdsourcing Reinforcement Learning for Knee Replacement Pathway Optimization
• Challenges for Reinforcement Learning in Healthcare
• Sepsis World Model: A MIMIC-based OpenAI Gym "World Model" Simulator for Sepsis Treatment
• Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey
• Privacy Preserving Off-Policy Evaluation
• DeepFoldit -- A Deep Reinforcement Learning Neural Network Folding Proteins