Research
Understanding Structured Health Data through Interaction-Aware Mixture-of-Experts
arXiv:2607.12255v1 Announce Type: new Abstract: We study interaction-aware mixture-of-experts for post-stroke rigidity prediction using multi-level views of structured health records. Despite minimal
arXiv:2607.12255v1 Announce Type: new Abstract: We study interaction-aware mixture-of-experts for post-stroke rigidity prediction using multi-level views of structured health records. Despite minimal performance gains, routing attribution reveals systematic importance differences across views, underscoring view construction as key to interpretability.
Related
- Validating a Deep Learning Algorithm to Identify Patients with Glaucoma using Systemic Electronic Health Records
- One Loss to Rule Them All: Marked Time-to-Event for Structured EHR Foundation Models
- Dialysis Risk Prediction and Treatment Effect Estimation for AKI patients using Longitudinal Electronic Health Records
- Predicting Post-Traumatic Epilepsy from Clinical Records using Large Language Model Embeddings
- Enhancing Clinician Decision-Making via Uncertainty-Aware Multi-Expert Fusion for Stroke Rehabilitation
Source: arXiv cs.LG | 2026-07-15