Deep Reinforcement Learning for Sepsis Treatment
arXiv:1711.09602
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.
arXiv commentExtensions on earlier work (arXiv:1705.08422). Accepted at workshop on Machine Learning For Health at the conference on Neural Information Processing Systems, 2017
References in corpus (1)
Cited by in corpus (24)
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- Reinforcement Learning in Healthcare: A Survey
- Evaluating Reinforcement Learning Algorithms in Observational Health Settings
- Deconfounding Reinforcement Learning in Observational Settings
- Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
- Model-Based Reinforcement Learning for Sepsis Treatment
- Model Selection for Offline Reinforcement Learning: Practical Considerations for Healthcare Settings
- DeepHealth: Review and challenges of artificial intelligence in health informatics
- Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation
- An Empirical Study of Representation Learning for Reinforcement Learning in Healthcare
- Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning
- 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
- Sepsis World Model: A MIMIC-based OpenAI Gym "World Model" Simulator for Sepsis Treatment
- Challenges for Reinforcement Learning in Healthcare
- Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey
- Privacy Preserving Off-Policy Evaluation
- Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score
- Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes
- Discovering an Aid Policy to Minimize Student Evasion Using Offline Reinforcement Learning
- InferNet for Delayed Reinforcement Tasks: Addressing the Temporal Credit Assignment Problem
- DeepFoldit -- A Deep Reinforcement Learning Neural Network Folding Proteins
- Time-Aware Q-Networks: Resolving Temporal Irregularity for Deep Reinforcement Learning