{
  "id": 4453,
  "url": "https://arxiv.org/abs/2605.12335v1",
  "title": "EHR-RAGp: Retrieval-Augmented Prototype-Guided Foundation Model for Electronic Health Records",
  "summary": "Electronic Health Records (EHR) contain rich longitudinal patient information and are widely used in predictive modeling applications. However, effectively leveraging historical data remains challenging due to long trajectories, heterogeneous events, temporal irregularity, and the varying relevance of past clinical context. Existing approaches often rely on fixed windows or uniform aggregation, which can obscure clinically important signals. In this work, we introduce EHR-RAGp, a retrieval-augme",
  "authors": "Saeed Shurrab, Mariam Al-Omari, Dana El Samad, Farah E. Shamout",
  "category": "research",
  "topics": "healthcare",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-12T16:17:03.000Z",
  "fetched_at": "2026-07-14T16:30:59.239Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4453",
  "original_url": "https://arxiv.org/abs/2605.12335v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}