Imitation learning for clinical decision support in pediatric ECMO
This work addresses the need for decision support in a high-stakes pediatric critical care setting with limited data, but the results are incremental as they apply existing methods to a new domain.
The paper frames clinical decision-making in pediatric ECMO as an imitation learning problem where actions are not directly observed, and shows that a TabPFN-based approach outperforms XGBoost and MLPs on real-world data, providing a strong clinician-behavior baseline.
Pediatric critical care is a dynamic, high-stakes process involving constant monitoring and adjustments in life-saving treatments. Modeling these interventions is crucial for effective decision support. To address the challenges of high complexity and data scarcity in pediatric Extracorporeal Membrane Oxygenation (ECMO), we frame clinical decision-making as learning to act from trajectories, i.e., imitation learning that learns action models from observational data, with a key feature that actions are not directly observed. We consider TabPFN, a recent transformer-based approach for tabular data, and traditional baselines including XGBoost and Multi-Layer Perceptrons(MLPs) on real-world pediatric ECMO data to learn the action models. We find that the TabPFN-based approach consistently outperforms these classical baselines, supporting its use as a strong clinician-behavior baseline for pediatric ECMO decision support.