TAMER: A Test-Time Adaptive MoE-Driven Framework for EHR Representation Learning
On the map: Mixture-of-experts → Medical and biomedical MoE
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Medical and biomedical MoE, one of 12 directions in Mixture-of-experts. Builds on 18 of its 42 references that are in the map. First posted on arXiv 10 Jan 2025.
Builds on
18 of 42 references.
References · 18
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
- 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 834
- 2022Mixture-of-Experts with Expert Choice Routingcited by 611
- 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
- 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 344
- 2024Learning to (Learn at Test Time): RNNs with Expressive Hidden Statescited by 329
- 2024MoE-LLaVA: Mixture of Experts for Large Vision-Language Modelscited by 298
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
- 2023From Sparse to Soft Mixtures of Expertscited by 245
- 2022On the Representation Collapse of Sparse Mixture of Expertscited by 156
6 more
- 2022M3Care: Learning with Missing Modalities in Multimodal Healthcare Datacited by 71
- 2024FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusioncited by 67
- 2019ConCare: Personalized Clinical Feature Embedding via Capturing the Healthcare Contextcited by 56
- 2019AdaCare: Explainable Clinical Health Status Representation Learning via Scale-Adaptive Feature Extraction and Recalibrationcited by 50
- 2022Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensingcited by 37
- 2023PRISM: Mitigating EHR Data Sparsity via Learning from Missing Feature Calibrated Prototype Patient Representationscited by 9
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025MoE-Health: A Mixture of Experts Framework for Robust Multimodal Healthcare Prediction
- 2025CEHR-XGPT: A Scalable Multi-Task Foundation Model for Electronic Health Records
- 2022Learning to Adapt Clinical Sequences with Residual Mixture of Experts
- 2024EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation
- 2026EHR-RAG: Bridging Long-Horizon Structured Electronic Health Records and Large Language Models via Enhanced Retrieval-Augmented Generation
- 2026CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records
- 2026Reinforcement Learning over Patient Trajectories for Clinical Reasoning in EHR Foundation Models
- 2026EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records