AI-driven sepsis care: early detection and personalized treatment

Abstract: Sepsis is a life-threatening organ dysfunction caused by a dysregulated host response to infection, and remains a leading cause of death in intensive care units worldwide. An optimal treatment strategy is still unknown, leading to a significant variability in sepsis treatment with poorer outcomes.

Recently, deep reinforcement learning has shown promise as a decision-aiding tool for the administration of intravenous fluids and vasopressors to septic patients. However, these models are limited in their ability to accommodate the entire range from high-risk to low-risk patients, and thus fail to provide personalized treatment recommendations.

To address this limitation, in particular in the presence of heterogeneous patient groups or heterogeneous treatment responses, we propose a Multi-Head Dueling Double Deep Q-Network (MH-DQN) model that incorporates patient characteristics to enable more personalized treatment recommendations. The MH-DQN model has multiple output layers, each of which is optimized for a specific patient profile. The model is trained using the Medical Information Mart for Intensive Care (MIMIC-III) database.

machine learningprobabilitystatistics theory

Audience: researchers in the discipline

Gothenburg statistics seminar

Series comments: Gothenburg statistics seminar is open to the interested public, everybody is welcome. It usually takes place in MVL14 (http://maps.chalmers.se/#05137ad7-4d34-45e2-9d14-7f970517e2b60, see specific talk). Speakers are asked to prepare material for 35 minutes excluding questions from the audience.