Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space

06/22/2022
by   Zeyu Wang, et al.
0

Sepsis is a leading cause of death in the ICU. It is a disease requiring complex interventions in a short period of time, but its optimal treatment strategy remains uncertain. Evidence suggests that the practices of currently used treatment strategies are problematic and may cause harm to patients. To address this decision problem, we propose a new medical decision model based on historical data to help clinicians recommend the best reference option for real-time treatment. Our model combines offline reinforcement learning with deep reinforcement learning to address the problem that traditional reinforcement learning in healthcare cannot interact with the environment, enabling our model to make decisions in a continuous state-action space. We demonstrate that, on average, the treatments recommended by the model are more valuable and reliable than those recommended by clinicians. In a large validation dataset, we found that patients whose actual doses from clinicians matched the AI's decisions had the lowest mortality rates. Our model provides personalized, clinically interpretable treatment decisions for sepsis that can improve patient care.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/27/2017

Deep Reinforcement Learning for Sepsis Treatment

Sepsis is a leading cause of mortality in intensive care units and costs...
research
11/23/2018

Model-Based Reinforcement Learning for Sepsis Treatment

Sepsis is a dangerous condition that is a leading cause of patient morta...
research
06/13/2023

Pruning the Way to Reliable Policies: A Multi-Objective Deep Q-Learning Approach to Critical Care

Most medical treatment decisions are sequential in nature. Hence, there ...
research
08/27/2022

SupervisorBot: NLP-Annotated Real-Time Recommendations of Psychotherapy Treatment Strategies with Deep Reinforcement Learning

We propose a recommendation system that suggests treatment strategies to...
research
03/25/2022

A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies

Sepsis is a leading cause of mortality and its treatment is very expensi...
research
10/08/2021

Medical Dead-ends and Learning to Identify High-risk States and Treatments

Machine learning has successfully framed many sequential decision making...
research
07/09/2021

Offline reinforcement learning with uncertainty for treatment strategies in sepsis

Guideline-based treatment for sepsis and septic shock is difficult becau...

Please sign up or login with your details

Forgot password? Click here to reset