Academic Journal
Assessing the performance of large language models when used to determine ASA status of cats and dogs and generate anaesthetic protocols.
| Τίτλος: | Assessing the performance of large language models when used to determine ASA status of cats and dogs and generate anaesthetic protocols. |
|---|---|
| Συγγραφείς: | Okur S; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Akçora Y; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Okur DT; Department of Obstetrics and Gynecology, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Şenocak MG; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Bedir AG; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Ersöz U; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Kartal T; Department of Surgery, Faculty of Veterinary Medicine, Atatürk University, Erzurum, Turkey., Kurt BK; Department of Surgery, Faculty of Veterinary Medicine, Aydın Adnan Menderes University, Aydın, Turkey. |
| Πηγή: | The Veterinary record [Vet Rec] 2026 Oct 03; Vol. 199 (7), pp. e304-e311. Date of Electronic Publication: 2026 May 12. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: Wiley Country of Publication: England NLM ID: 0031164 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2042-7670 (Electronic) Linking ISSN: 00424900 NLM ISO Abbreviation: Vet Rec Subsets: MEDLINE |
| Imprint Name(s): | Publication: 2021- : [Oxford] : Wiley Original Publication: -June 2009 : London : British Veterinary Medicine |
| Ιατρικοί όροι (MeSH): | Anesthesia*/veterinary , Large Language Models*, Animals ; Dogs ; Cats ; Retrospective Studies ; Reproducibility of Results ; Clinical Protocols |
| Περίληψη: | Background: Large language models (LLMs) are emerging as decision-support tools in human medicine; however, their evaluation in veterinary anaesthesiology remains limited. Methods: We retrospectively analysed 225 anonymised feline and canine cases (American Society of Anaesthesiologists [ASA] classifications 1‒5) from Atatürk University Veterinary Hospital. ChatGPT-4o, ChatGPT-5 and Gemini 2.5 Pro independently assigned ASA classifications and generated anaesthetic protocols using standardised prompts. Protocol adequacy was evaluated for all cases, regardless of ASA classification agreement, by two experienced veterinary anaesthesiologists using a four-point scale. Statistical analyses included Friedman and Bonferroni-adjusted Wilcoxon tests, effect sizes and inter-panelist reliability (assessed by quadratic-weighted Cohen's kappa and intraclass correlation coefficient). Results: ChatGPT-5 achieved the highest ASA classification accuracy (53.3%), followed by ChatGPT-4o (46.7%) and Gemini 2.5 Pro (30.7%). The performance was strongest for ASA 3‒5, whereas ASA 1 cases were frequently misclassified, mainly due to ASA overestimation. ChatGPT-5 generated the most clinically sufficient anaesthetic protocols, outperforming the other models. Limitations: The retrospective, single-centre design and inclusion of only feline and canine cases may limit generalisability. Conclusions: LLMs can generate clinically relevant ASA classifications and anaesthetic protocols in veterinary anaesthesiology, although performance varies across models. However, expert oversight remains essential. (© 2026 The Author(s). Veterinary Record published by John Wiley & Sons Ltd on behalf of British Veterinary Association.) |
| References: | Nat Rev Cancer. 2018 Aug;18(8):500-510. (PMID: 29777175) J Clin Anesth. 2024 Sep;96:111475. (PMID: 38657530) BMC Med Inform Decis Mak. 2020 Nov 30;20(1):310. (PMID: 33256715) Vet Med Sci. 2025 May;11(3):e70315. (PMID: 40173266) Vet Anaesth Analg. 2013 May;40(3):229-36. (PMID: 23402568) Front Vet Sci. 2024 Jun 07;11:1395934. (PMID: 38911678) Anesth Analg. 2024 Aug 1;139(2):349-356. (PMID: 38640076) Domest Anim Endocrinol. 2020 Jul;72:106396. (PMID: 32006871) Am J Emerg Med. 2025 Mar;89:27-29. (PMID: 39675178) Anesthesiology. 2020 Feb;132(2):379-394. (PMID: 31939856) Vet Med Sci. 2025 May;11(3):e70258. (PMID: 40145983) Rev Cardiovasc Med. 2021 Dec 22;22(4):1095-1113. (PMID: 34957756) BMC Med Inform Decis Mak. 2025 Mar 07;25(1):117. (PMID: 40055694) J Am Vet Med Assoc. 2022 Mar 30;260(8):819-824. (PMID: 35358065) J Equine Vet Sci. 2020 Jul;90:102973. (PMID: 32534764) J Orthop Surg Res. 2024 Sep 18;19(1):574. (PMID: 39289734) Histopathology. 2019 Feb;74(3):372-376. (PMID: 30270453) JMIR Med Inform. 2024 May 10;12:e53787. (PMID: 38728687) Biometrics. 1977 Mar;33(1):159-74. (PMID: 843571) Nat Med. 2023 Aug;29(8):1930-1940. (PMID: 37460753) Curr Anesthesiol Rep. 2023 Jun;13(2):31-40. (PMID: 38106626) |
| Contributed Indexing: | Keywords: ASA classification; decision support; large language models; veterinary anaesthesiology |
| Entry Date(s): | Date Created: 20260512 Date Completed: 20261002 Latest Revision: 20261004 |
| Update Code: | 20261004 |
| PubMed Central ID: | PMC13631851 |
| DOI: | 10.1002/vetr.70741 |
| PMID: | 42117364 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 2042-7670 |
|---|---|
| DOI: | 10.1002/vetr.70741 |