EUVIMEDEUVIMED entdecken
Crossref

When used for veterinary triage, artificial intelligence models recognise emergencies but are more likely than veterinary staff to flag non‐urgent cases as urgent

Arlene Wong, Madeleine Roberts, Marie Jean Angela Patricia Victoria Pantangco, Ashleigh Arnold, Alexander Philp, Jan Šlapeta iD, Samantha Livingstone

Veterinary Record · 17.01.2026 · 198 (2)

DOI: 10.1002/vetr.6126 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Veterinary Record, online erschienen am 04.12.2025. Verfasst von Arlene Wong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Sydney School of Veterinary Science, University of Sydney, Sydney, New South Wales, Australia. Hauptthemen laut MEDLINE: Artificial Intelligence, Dog Diseases, Emergencies, Triage. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 31 Literaturangaben. Gefördert von: Sydney School of Veterinary Science Research & Enquiry Unit of Study 2024 Fund.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

This study assesses the capability of ChatGPT and nurses in accurately triaging emergency patients compared to veterinarians.

Methods

Retrospective observational study of canine patients that presented at a private veterinary specialist and emergency hospital. Given clinical signs and history, patients were assigned to a triage category (waiting times of 0, 15, 30‒60, 120 and 240 minutes). Triages were performed by three veterinarians, two nurses, ChatGPT‐3.5 and ChatGPT‐4.0. Statistical analysis was used to assess how often triage by ChatGPT and nurses agreed with veterinarians.

Results

ChatGPT has high sensitivity in identifying severe emergencies, correctly prioritising 80%‒90% of critical cases, but over‐triaged around 60% of non‐urgent cases as requiring immediate attention. ChatGPT's triage performance was comparable to that of nurses. When ChatGPT was used as a tool to flag severe cases (‘0 minutes’) in concert with nurses, triage sensitivity rose to 95%.

Limitations

The small sample of nurses limits the ability to assess how performance relative to artificial intelligence (AI) may vary with nurses’ triage experience.

Conclusions

AI models can be an effective tool for flagging severe cases and complementing nurse triages. However, the tendency to flag non‐urgent cases as requiring immediate attention may lead to increased pressure on emergency clinics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceDog DiseasesEmergenciesTriageVeterinariansAnimalsDogsFemaleHumansMaleRetrospective Studies

Autor:innen und Institutionen

  • Sydney School of Veterinary Science, University of Sydney, Sydney, New South Wales, Australia.
  • Sydney Infectious Diseases Institute, University of Sydney, Sydney, New South Wales, Australia.

ORCID-Profile: Jan Šlapeta

Förderung

  • Sydney School of Veterinary Science Research & Enquiry Unit of Study 2024 Fund

Zitieren

APA

Wong, A., Roberts, M., Pantangco, M. J. A. P. V., Arnold, A., Philp, A., Šlapeta, J., & Livingstone, S. (2026). When used for veterinary triage, artificial intelligence models recognise emergencies but are more likely than veterinary staff to flag non‐urgent cases as urgent. Veterinary Record, 198(2). https://doi.org/10.1002/vetr.6126

Vancouver

Wong A, Roberts M, Pantangco MJAPV, Arnold A, Philp A, Šlapeta J, et al. When used for veterinary triage, artificial intelligence models recognise emergencies but are more likely than veterinary staff to flag non‐urgent cases as urgent. Veterinary Record. 2026;198(2). doi:10.1002/vetr.6126

BibTeX
@article{Wong2026,
  author = {Wong, Arlene and Roberts, Madeleine and Pantangco, Marie Jean Angela Patricia Victoria and Arnold, Ashleigh and Philp, Alexander and Šlapeta, Jan and Livingstone, Samantha},
  title = {When used for veterinary triage, artificial intelligence models recognise emergencies but are more likely than veterinary staff to flag non‐urgent cases as urgent},
  journal = {Veterinary Record},
  year = {2026},
  volume = {198},
  number = {2},
  doi = {10.1002/vetr.6126}
}
Kostenlos starten →