Guardian-regularized Safe Offline Reinforcement Learning for Smart Weaning of Mechanical Circulatory Devices

Aysin Tumay, Sophia Huiwen Sun, Sonia Fereidooni, Aaron Dumas, Elise Jortberg, Rose Yu

Keywords: safe offline reinforcement learning, mechanical circulatory support devices, digital twin, smart weaning, medical decision-making

TL;DR: Clinically-aware OOD-regularized Model-based Policy Optimization for learning smart weaning of Mechanical Circulatory Devices, digital twin hemodynamics model for evaluation.

Track: Proceedings

Abstract: We study the sequential decision-making problem for automated weaning of mechanical circulatory support (MCS) devices in cardiogenic shock patients. MCS devices are percutaneous micro-axial flow pumps that provide left ventricular unloading and forward blood flow, but current weaning strategies vary significantly across care teams and lack data-driven approaches. Offline reinforcement learning (RL) has proven to be successful in sequential decision-making tasks, but our setting presents challenges for training and evaluating traditional offline RL methods: prohibition of online patient interaction, highly uncertain circulatory dynamics due to concurrent treatments, and limited data availability. We developed an end-to-end machine learning framework with two key contributions (1) Clinically-aware OOD-regularized Model-based Policy Optimization (CORMPO), a density-regularized offline RL algorithm for out-of-distribution suppression that also incorporates clinically-informed reward shaping and (2) a Transformer-based probabilistic digital twin that models MCS circulatory dynamics for policy evaluation with rich physiological and clinical metrics. We prove that CORMPO achieves theoretical performance guarantees under mild assumptions. CORMPO attains a higher reward than the offline RL baselines by 28% and higher scores in clinical metrics by 82.6% on real and synthetic datasets. Our approach offers a principled framework for safe offline policy learning in high-stakes medical applications where domain expertise and safety constraints are essential.

General Area: Models and Methods

Specific Subject Areas: Reinforcement Learning, Uncertainty & Distribution Shift

Data And Code Availability: No

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Code URL: https://github.com/Rose-STL-Lab/CORMPO

Submission Number: 214