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). Addressing the vulnerability of large language models to hallucinated facts, unsupported recommendations, and citation errors, the system integrates calibrated risk prediction, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer that combines rule-based checks with LLM-based entailment. The demonstration includes a real-time batch-screening dashboard and an interactive patient report interface showing cited recommendations, verification results, and raw EHR comparisons. By keeping all processing local, DIASENTINEL offers a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support.
Paper Overview
Field: NLP
Authors: Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu
Published: 2025-09-01
arXiv: 2509.00147
Abstract
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).
The system integrates:
- Calibrated risk prediction for one-year T2DM risk
- Deterministic clinical signal extraction from EHR data
- Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines to ground recommendations
- Hybrid verification layer combining rule-based checks with LLM-based entailment
The demonstration provides a real-time batch-screening dashboard and an interactive patient report interface featuring cited recommendations, verification results, and side-by-side comparison with raw EHR data.
DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support, with all deployment kept fully on-premise to protect patient privacy.
---
*Auto-collected on 2026-09-02 from zhichai.net.*
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