TAMER: A Test-Time Adaptive MoE-Driven Framework for EHR Representation Learning
This work addresses dynamic and personalized predictions in clinical settings, offering a promising approach for EHR-based applications, though it appears incremental as it builds on existing MoE and TTA techniques.
The paper tackled the challenges of patient heterogeneity and distribution shifts in Electronic Health Record (EHR) modeling by proposing TAMER, a framework combining Mixture-of-Experts with Test-Time Adaptation, which consistently improved predictive performance for mortality and readmission risk tasks across four real-world EHR datasets.
We propose TAMER, a Test-time Adaptive MoE-driven framework for Electronic Health Record (EHR) Representation learning. TAMER introduces a framework where a Mixture-of-Experts (MoE) architecture is co-designed with Test-Time Adaptation (TTA) to jointly mitigate the intertwined challenges of patient heterogeneity and distribution shifts in EHR modeling. The MoE focuses on latent patient subgroups through domain-aware expert specialization, while TTA enables real-time adaptation to evolving health status distributions when new patient samples are introduced. Extensive experiments across four real-world EHR datasets demonstrate that TAMER consistently improves predictive performance for both mortality and readmission risk tasks when combined with diverse EHR modeling backbones. TAMER offers a promising approach for dynamic and personalized EHR-based predictions in practical clinical settings.