Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study
JMIR Medical Informatics · 26.01.2026 · 14 · e82026
DOI: 10.2196/82026 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Medical Informatics, online erschienen am 26.01.2026. Verfasst von Hang Sheung Wong und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Accident & Emergency, Princess Margaret Hospital, Hong Kong (SAR), China (Hong Kong). Hauptthemen laut MEDLINE: Triage, Clinical Reasoning. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
Emergency triage accuracy is critical but varies with clinician experience, cognitive load, and case complexity. Mis-triage can delay care for high-risk patients and exacerbate crowding through unnecessary prioritization. Large language models (LLMs) show promise as triage decision-support tools but are vulnerable to hallucinations. Retrieval-augmented generation (RAG) may improve reliability by grounding LLM reasoning in authoritative guidelines and real clinical cases.
Objective
This study aimed to evaluate whether a dual-source RAG system that integrates guideline- and case-based evidence improves emergency triage performance versus a baseline LLM and to assess how closely its urgency assignments align with expert consensus and outcome-defined clinical severity.
Methods
We developed a dual-source RAG system—Multi-Evidence Clinical Reasoning RAG (MECR-RAG)—that retrieves sections from the Hong Kong Accident and Emergency Triage Guidelines (HKAETG) and cases from a database of 3000 emergency department triage encounters. In a retrospective single‑center evaluation, MECR‑RAG and a prompt‑only baseline LLM (both DeepSeek‑V3) were tested on 236 routine triage encounters to predict 5‑level triage categories. Expert consensus reference labels were assigned by blinded senior triage nurses. Primary outcomes were quadratic weighted kappa (QWK) and accuracy versus consensus labels. Secondary analyses examined performance within 3 operationally and clinically relevant triage bands—immediate (categories 1 and 2), urgent (category 3), and nonurgent (categories 4 and 5). In 226 encounters with follow‑up, we also assigned outcome‑based severity tiers (R1-R3) using a published 3‑level urgency reference standard and defined a disposition‑safety composite.
Results
MECR‑RAG achieved a mean QWK of 0.902 (SD 0.0021; 95% CI 0.901-0.904) and accuracy of 0.802 (SD 0.0082; 95% CI 0.795-0.808), outperforming the baseline LLM (QWK 0.801, SD 0.004; accuracy 0.542, SD 0.0073; both P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Accident & Emergency, Princess Margaret Hospital, Hong Kong (SAR), China (Hong Kong).
- Department of Accident & Emergency, North Lantau Hospital, Hong Kong (SAR), China (Hong Kong).
ORCID-Profile: Hang Sheung Wong, Tsz Kwan Wong
Zitieren
APA
Wong, H. S., & Wong, T. K. (2026). Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study. JMIR Medical Informatics, 14, e82026. https://doi.org/10.2196/82026
Vancouver
Wong HS, Wong TK. Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study. JMIR Medical Informatics. 2026;14:e82026. doi:10.2196/82026
BibTeX
@article{Wong2026,
author = {Wong, Hang Sheung and Wong, Tsz Kwan},
title = {Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study},
journal = {JMIR Medical Informatics},
year = {2026},
volume = {14},
pages = {e82026},
doi = {10.2196/82026}
}
EUVIMED