Accessibility settings

Published on in Vol 14 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/82026, first published .
Infographic: MECR-RAG improves ED triage accuracy compared to LLMs, achieving expert agreement.

Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study

Multi-Evidence Clinical Reasoning With Retrieval-Augmented Generation for Emergency Triage: Retrospective Evaluation Study

Authors of this article:

Hang Sheung Wong1 Author Orcid Image ;   Tsz Kwan Wong2 Author Orcid Image

Journals

  1. Song M, Kim J, Jang E, Kwon S. Interpretable Machine Learning for Emergency Department Triage: Clinical Insights from 133,198 Patients Using the Korean Triage and Acuity Scale (KTAS). Diagnostics 2026;16(6):954 View
  2. Šoša I. A Two-Stage In Silico-Guided Workflow for Forensic Toxicology: Empirical Validation via Capillary Zone Electrophoresis Prior to Mass-Spectrometric Confirmation. Toxics 2026;14(5):451 View
  3. Zheng J, Liu Y, Chen W, Chen M, Yin Y. Risk factors for mis-triage between medical and surgical causes in emergency patients with non-traumatic abdominal pain: a retrospective study. Frontiers in Public Health 2026;14 View
  4. Karpov O, Kuc A, Smirnov N, Zamyatin M, Osipov A, Kilnik A, Kurkin S, Maksachuk A, Hramov A. Self-organizing search on hierarchical normative hypergraphs for decision support in disaster medicine. The European Physical Journal Special Topics 2026 View
  5. Zhang Y, Li L, Tan C, Ji M, Tian X, Mu X, Li J, Gu Y, Liu H. Large Language Model–Based Clinical Decision Support for Antibiotic Selection and Dose Recommendation in Hospitalized Patients With Pneumonia: Multicenter Retrospective Study. JMIR Medical Informatics 2026;14:e98207 View
  6. Zhao Y, Miao Y, Guo R, Luo Y, Wang H, Wu Y. Evaluation Methods for Inference-Time Retrieval-Augmented and Graph Retrieval-Augmented Large Language Models in Health Care: Scoping Review. Journal of Medical Internet Research 2026;28:e90046 View