Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning

Abstract

Sepsis is the leading cause of mortality in the ICU. It is challenging to manage because individual patients respond differently to treatment. Thus, tailoring treatment to the individual patient is essential for the best outcomes. In this paper, we take steps toward this goal by applying a mixture-of-experts framework to personalize sepsis treatment. The mixture model selectively alternates between neighbor-based (kernel) and deep reinforcement learning (DRL) experts depending on patient's current history. On a large retrospective cohort, this mixture-based approach outperforms physician, kernel only, and DRL-only experts.

arXiv commentAMIA 2018 Annual Symposium

References in corpus (3)

• Prioritized Experience Replay
• Continuous State-Space Models for Optimal Sepsis Treatment - a Deep Reinforcement Learning Approach
• Malaria Likelihood Prediction By Effectively Surveying Households Using Deep Reinforcement Learning

Cited by in corpus (7)

• Reinforcement Learning in Healthcare: A Survey
• Unifying Cardiovascular Modelling with Deep Reinforcement Learning for Uncertainty Aware Control of Sepsis Treatment
• Is Deep Reinforcement Learning Ready for Practical Applications in Healthcare? A Sensitivity Analysis of Duel-DDQN for Hemodynamic Management in Sepsis Patients
• Medical Dead-ends and Learning to Identify High-risk States and Treatments
• Understanding the Artificial Intelligence Clinician and optimal treatment strategies for sepsis in intensive care
• Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes
• Nonparametric Additive Value Functions: Interpretable Reinforcement Learning with an Application to Surgical Recovery