Summary
DIASENTINEL is a fully on-premise multi-agent system presented in arXiv paper 2509.00147 (September 2025) for one-year type 2 diabetes mellitus (T2DM) risk screening and guideline-grounded report generation from electronic health records (EHRs). Large language models promise strong clinical decision support but remain prone to hallucinated facts, unsupported recommendations, and citation errors. DIASENTINEL addresses these weaknesses by combining calibrated risk prediction, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer that pairs rule-based checks with LLM entailment. The system ships with a real-time batch-screening dashboard and an interactive patient report interface showing cited recommendations, verification results, and side-by-side raw EHR comparisons. By keeping all components local, it offers a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support.
Paper Overview
Research area: NLP
Authors: Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu
Published: 2025-09-01
arXiv: 2509.00147
Summary
Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. The authors present DIASENTINEL, a fully on-premise multi-agent system for one-year type 2 diabetes mellitus (T2DM) risk screening and guideline-grounded report generation from electronic health records (EHRs).
Key components
- Calibrated risk prediction for one-year T2DM risk
- Deterministic clinical signal extraction from EHR data
- Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines for grounded recommendations
- Hybrid verification layer combining rule-based checks with LLM entailment to validate outputs
Demonstration
The system provides a real-time batch-screening dashboard and an interactive patient report interface that includes:
- Cited recommendations
- Verification results
- Side-by-side raw EHR comparisons
DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support, keeping all processing on-premise.
---
*Auto-collected on 2026-09-02*
This page is an English static mirror generated for search and AI citation.
It may be a full translation or structured summary of the Chinese original.
Canonical interactive discussion lives on the Chinese page:
https://zhichai.net/topic/178634403