The Utility of Large Language Models to Assist With Emergency Triage Decisions Within Otolaryngology
Otolaryngology–Head and Neck Surgery · 2026
DOI: 10.1002/ohn.70313 ↗Kurz gefasst
Fachartikel in der Zeitschrift Otolaryngology–Head and Neck Surgery, 2026. Verfasst von Sholem Hack und 14 weiteren Autor:innen. Beteiligte Einrichtung: City St. George's University London School of Medicine, Program Delivered by University of Nicosia at the Chaim Sheba Medical Center, Ramat Gan, Isra…. Hauptthemen laut MEDLINE: Large Language Models, Triage, Otolaryngology, Clinical Decision-Making. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Objective
To determine whether contemporary large language models can match clinician performance in evaluating the urgency of emergency otolaryngology referrals. Study Design Blinded cross‐sectional diagnostic reasoning study.
Setting
Simulated emergency referral environment modeled on tertiary care otolaryngology practice.
Methods
Thirty emergency referral scenarios spanning the spectrum of otolaryngologic urgency were independently evaluated by 4 large language models (GPT‐5, GPT‐4, DeepSeek, and Grok) and 4 clinicians (otolaryngology attending and resident, emergency attending and resident). Outputs were anonymized and scored by 10 blinded otolaryngologists for appropriateness of urgency and quality of explanation using a three‐point scale. Statistical analyses included nonparametric group comparisons, adjusted ordinary least squares modeling with case‐level control, and correlation of each entity's case profile with that of the otolaryngology attending.
Results
Inter‐rater reliability was excellent. The otolaryngology attending achieved the highest overall performance. GPT‐5 demonstrated comparable mean performance, with no statistically significant difference in either domain. GPT‐4 scored modestly lower but received higher mean ratings than both emergency clinicians. DeepSeek and the otolaryngology resident demonstrated intermediate performance, while Grok and the emergency clinicians performed lowest. Group‐level analyses showed no significant difference between the large language model and otolaryngology cohorts; both were rated higher than emergency clinicians in this sample.
Conclusion
GPT‐5 demonstrated triage performance comparable to the otolaryngology attending in this controlled sample. Large language models may support emergency decision‐making and education when specialist consultation is limited, but require supervision, transparency, and local calibration.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- City St. George's University London School of Medicine, Program Delivered by University of Nicosia at the Chaim Sheba Medical Center, Ramat Gan, Israel.
- Department of Emergency Medicine, Penn State Hershey Medical Center, Hershey, Pennsylvania, USA.
- Department of Otolaryngology-Head and Neck Surgery, Meir Medical Center, Kfar Saba, Israel, Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.
- Department of Otolaryngology-Head and Neck Surgery, University of California, San Francisco, California, USA.
- Department of Otolaryngology-Head and Neck Surgery Stanford University, Lucile Packard Children's Hospital, Palo Alto, California, USA.
- Department of Otolaryngology-Head and Neck Surgery, University of California, Davis, USA.
ORCID-Profile: Sholem Hack
Zitieren
APA
Hack, S., Attal, R., Steckbeck, R. J., Boldes, T., Ayeni, T., Smith, A. J., Sagiv, D., Kellermeyer, B., Garcia-Lliberos, A., Rodriguez-Prado, C., Biadsee, A., Sebelik, M., Roxbury, C. R., Purnell, P., & Zalzal, H. G. (2026). The Utility of Large Language Models to Assist With Emergency Triage Decisions Within Otolaryngology. Otolaryngology–Head and Neck Surgery. https://doi.org/10.1002/ohn.70313
Vancouver
Hack S, Attal R, Steckbeck RJ, Boldes T, Ayeni T, Smith AJ, et al. The Utility of Large Language Models to Assist With Emergency Triage Decisions Within Otolaryngology. Otolaryngology–Head and Neck Surgery. 2026. doi:10.1002/ohn.70313
BibTeX
@article{Hack2026,
author = {Hack, Sholem and Attal, Rebecca and Steckbeck, Rachel J and Boldes, Tomer and Ayeni, Tokunbo and Smith, Alyssa J and Sagiv, Doron and Kellermeyer, Brian and Garcia-Lliberos, Ainhoa and Rodriguez-Prado, Cristina and Biadsee, Ameen and Sebelik, Merry and Roxbury, Christopher R and Purnell, Phillip and Zalzal, Habib G},
title = {The Utility of Large Language Models to Assist With Emergency Triage Decisions Within Otolaryngology},
journal = {Otolaryngology–Head and Neck Surgery},
year = {2026},
doi = {10.1002/ohn.70313}
}
EUVIMED