Paper Detail

DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening

Yung Wei Shueh, Zhi-Jie Chen, Chia-Hsuan Hsu, Hsin-Ling Hsu, Donghua Zhang, Chenwei Wu, Jun-En Ding, Tongze Zhang, Shihao Yang, Pengfei Hu, Fang-Ming Hung, Feng Liu

arxiv Score 9.3

Published 2026-08-31 · First seen 2026-09-01

General AI

Abstract

Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We 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, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Diabetes Association (ADA) guidelines, and a hybrid verification layer combining rule-based checks with LLM entailment. The demonstration provides a real-time batch-screening dashboard and an interactive patient report interface with cited recommendations, verification results, and raw EHR comparison. DIASENTINEL demonstrates a practical framework for reliable, auditable, and privacy-preserving LLM-based clinical decision support.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{shueh2026diasentinel,
  title = {DIASENTINEL: An Auditable Multi-Agent System for Guideline-Grounded Diabetes Risk Screening},
  author = {Yung Wei Shueh and Zhi-Jie Chen and Chia-Hsuan Hsu and Hsin-Ling Hsu and Donghua Zhang and Chenwei Wu and Jun-En Ding and Tongze Zhang and Shihao Yang and Pengfei Hu and Fang-Ming Hung and Feng Liu},
  year = {2026},
  abstract = {Large language models (LLMs) offer promising clinical decision support but remain vulnerable to hallucinated facts, unsupported recommendations, and citation errors. We 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, deterministic clinical signal extraction, Reciprocal Rank Fusion over American Dia},
  url = {https://arxiv.org/abs/2608.31128},
  keywords = {cs.CL},
  eprint = {2608.31128},
  archiveprefix = {arXiv},
}

Metadata

{}