Model-Based Reinforcement Learning for Sepsis Treatment
This work addresses the challenge of personalized sepsis treatment for patients, but it is incremental as it builds on existing RL methods without introducing a new paradigm.
The paper tackled the problem of sepsis treatment by using continuous state-space model-based reinforcement learning to discover high-quality treatment policies, resulting in improved policies when blended with clinician strategies, potentially enabling better medical treatment.
Sepsis is a dangerous condition that is a leading cause of patient mortality. Treating sepsis 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 explore the use of continuous state-space model-based reinforcement learning (RL) to discover high-quality treatment policies for sepsis patients. Our quantitative evaluation reveals that by blending the treatment strategy discovered with RL with what clinicians follow, we can obtain improved policies, potentially allowing for better medical treatment for sepsis.