IntelliLung: Advancing Safe Mechanical Ventilation using Offline RL with Hybrid Actions and Clinically Aligned Rewards
This work addresses the problem of safe and personalized mechanical ventilation for critically ill patients, representing an incremental improvement over existing offline RL methods.
The paper tackled the challenge of optimizing mechanical ventilation settings for ICU patients by addressing the hybrid action space issue in offline RL, resulting in a method that avoids discretization pitfalls and uses a clinically aligned reward function to potentially enhance patient safety and individualized care.
Invasive mechanical ventilation (MV) is a life-sustaining therapy for critically ill patients in the intensive care unit (ICU). However, optimizing its settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for MV control, current stateof-the-art (SOTA) methods struggle with the hybrid (continuous and discrete) nature of MV actions. Discretizing the action space limits available actions due to exponential growth in combinations and introduces distribution shifts that can compromise safety. In this paper, we propose optimizations that build upon prior work in action space reduction to address the challenges of discrete action spaces. We also adapt SOTA offline RL algorithms (IQL and EDAC) to operate directly on hybrid action spaces, thereby avoiding the pitfalls of discretization. Additionally, we introduce a clinically grounded reward function based on ventilator-free days and physiological targets, which provides a more meaningful optimization objective compared to traditional sparse mortality-based rewards. Our findings demonstrate that AI-assisted MV optimization may enhance patient safety and enable individualized lung support, representing a significant advancement toward intelligent, data-driven critical care solutions.