EUVIMEDEUVIMED entdecken
Open Access

The Utility of Large Language Models to Assist With Emergency Triage Decisions Within Otolaryngology

Sholem Hack iD, Rebecca Attal, Rachel J Steckbeck, Tomer Boldes, Tokunbo Ayeni, Alyssa J Smith, Doron Sagiv, Brian Kellermeyer, Ainhoa Garcia-Lliberos, Cristina Rodriguez-Prado, Ameen Biadsee, Merry Sebelik und 3 weitere

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Large Language ModelsTriageOtolaryngologyClinical Decision-MakingHumansCross-Sectional StudiesReferral and Consultation

Stichwörter der Autor:innen

Artificial IntelligenceLarge Language ModelsTriageclinical decision‐makingemergency departmentotolaryngology

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}
}
Kostenlos starten →