cs.LGNov 12, 2026

Support-Constrained Offline Policy Improvement for Pediatric ECMO from Limited Clinical Data

Authors: Fateme Golivand Darvishvand, Saurabh Mathur, Nikhilesh Prabhakar, Michael A. Skinner, Ameet Soni, Neel Shah, Ethan L Sanford, Lakshmi Raman, 

Organizations: University of Texas at Dallas · Technische Universität Darmstadt · Swarthmore College · Washington University in St. Louis · 

Abstract

Managing children on ECMO (Extracorporeal Membrane Oxygenation) requires balancing short-term physiological stability with the long-term goal of preventing neurological injury. Standard reinforcement learning can propose risky, out-of-distribution actions, while imitation learning is limited to reproducing clinician behavior. We introduce Support-Constrained Fitted Q-Iteration (FQI-SC), an offline reinforcement learning framework that cautiously improves upon expert behavior by restricting optimization to empirically supported state-action pairs and defaulting to the clinician baseline in low-data regions. On 78 pediatric trajectories totaling over 6,000 hours of clinical data, we evaluate our framework using Fitted Q-Evaluation (FQE) and a behavioral disagreement. Additionally, we formalize the performance-safety trade-off by introducing a unified Balance Score (S(π)S(π)). Our empirical evaluation shows that support-constrained policy improves the Balance Score by 38% relative to FQI, improves estimated value by 1.28 FQE units over imitation learning, and reduces disagreement with clinician actions by 71% relative to FQI.

Figures & tables

Explore similar work

CardsList
  1. Imitation learning for clinical decision support in pediatric ECMO

    May 15, 2026Fateme Golivand, Michael Skinner, Saurabh Mathur +5Latent Action LearningClinical Decision Support

  2. Finite-Sample Theory for Fitted Q-Iteration When Actions Are Functions

    Sep 28, 2026Gefei Lin, Rui Miao, Xiaoke Zhangfitted q-iterationReinforcement Learning

  3. ISEP: Implicit Support Expansion for Offline Reinforcement Learning via Stochastic Policy Optimization

    May 18, 2026Yifei Chen, Shaoqin Zhu, Xiaoqiang JiPolicy OptimizationOffline RL