Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study

Banu Çiçek Tez Yaşar; Meltem Karahan; Arif Yiğit Güler; Başak Eliaçık

Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study

Abstract

Aims: To comparatively evaluate adherence to the 2020 International Association of Dental Traumatology (IADT) guidelines and short-term temporal consistency across three large language models (LLMs)-ChatGPT (GPT-5.5), Gemini 2.5 Flash, and Microsoft Copilot-when answering open-ended questions on tooth avulsion management. Methods: Fourteen open-ended questions were categorized into four domains: Emergency and first aid, clinical management, prognosis and critical factors, and advanced decision-making. Each question was submitted to each LLM three times daily for three consecutive days. Two pediatric dentists classified responses as correct or incorrect by consensus using a guideline-based answer key. Cochran’s Q and post hoc McNemar tests were used for comparisons. Results: Among 378 responses, ChatGPT generated the highest number of correct responses (94/126; 74.6%), followed by Gemini (87/126; 69.0%) and Copilot (79/126; 62.7%). The overall intermodel difference was significant (p=0.021), with a significant pairwise difference only between ChatGPT and Copilot (p=0.015). No significant differences were observed in emergency and first aid, clinical management, or prognosis and critical factors (p>0.05). Advanced decision-making differed significantly among models (p=0.008), particularly between ChatGPT and Gemini (p=0.016). No significant within-day or across-day variation was detected (p>0.05). Conclusion: The evaluated LLMs showed no statistically significant short-term temporal variation, but their adherence to IADT recommendations varied across models and clinical domains. ChatGPT achieved the highest performance, while the greatest divergence occurred in the predefined Advanced Decision-Making domain, specifically in questions concerning extra-alveolar dry time and delayed replantation. These models should be used only as adjunctive tools, with recommendations verified against guidelines under professional supervision.

Keywords

Supporting Institution

This research received no funding.

Ethical Statement

No ethical approval was needed because this is not a human study, but only online information was used.

References

Glendor U, Halling A, Andersson L, Eilert-Petersson E. Incidence of traumatic tooth injuries in children and adolescents in the county of Västmanland, Sweden. Swed Dent J. 1996;20(1-2):15-28
Andreasen JO, Andreasen FM, Tsilingaridis G. Avulsions. In: Andreasen JO, Andreasen FM, Andersson L, eds. Textbook and Color Atlas of Traumatic Injuries to the Teeth. 5th ed. Wiley-Blackwell; 2019:486-528
Fouad AF, Abbott PV, Tsilingaridis G, et al. International Association of Dental Traumatology guidelines for the management of traumatic dental injuries: 2. Avulsion of permanent teeth. Dent Traumatol. 2020; 36(4):331-342. doi:10.1111/edt.12573
Mustuloğlu Ş, Deniz BP. Evaluation of chatbots in the emergency management of avulsion injuries. Dent Traumatol. 2025;41(4):437-444. doi:10.1111/edt.13041
Guven Y, Ozdemir OT, Kavan MY. Performance of Artificial Intelligence chatbots in responding to patient queries related to traumatic dental injuries: a comparative study. Dent Traumatol. 2025;41(3):338-347. doi:10.1111/edt.13020
Tokgöz Kaplan T, Cankar M. Evidence-based potential of generative Artificial Intelligence large language models on dental avulsion: ChatGPT versus Gemini. Dent Traumatol. 2025;41(2):178-186. doi:10.1111/edt.12999
Wang L, Wan Z, Ni C, et al. Applications and concerns of ChatGPT and other conversational large language models in health care: systematic review. J Med Internet Res. 2024;26:e22769. doi:10.2196/22769
Ghanem YK, Rouhi AD, Al-Houssan A, et al. Dr. Google to Dr. ChatGPT: assessing the content and quality of Artificial Intelligence-generated medical information on appendicitis. Surg Endosc. 2024;38(5):2887-2893. doi:10.1007/s00464-024-10739-5

Guzman AL, Lewis SC. Artificial Intelligence and communication: a human-machine communication research agenda. New Media Soc. 2020;22(1):70-86. doi:10.1177/1461444819858691
Kuru HE, Aşık A, Demir DM. Can Artificial Intelligence language models effectively address dental trauma questions? Dent Traumatol. 2025;41(5):567-580. doi:10.1111/edt.13063
Walker HL, Ghani S, Kuemmerli C, et al. Reliability of medical information provided by ChatGPT: assessment against clinical guidelines and patient information quality instrument. J Med Internet Res. 2023;25: e47479. doi:10.2196/47479
İlter Er Ö, Adıgüzel Ö, Taşyürek M, Ortaç H. Comparison of ChatGPT-5, Gemini 2.5 Pro, and DeepSeek-V3.1 chatbot responses to dental avulsion injuries. H Sci Mon. 2025;3(1):e251201. doi:10.5577/hsm.e251201
Abat VH, Veznikli M. Accuracy of Artificial Intelligence responses on antibiotic use in endodontics. Int Dent Res. 2026;16(S1):e260681. doi:10.5577/intdentres.681
Day PF, Flores MT, O'Connell AC, et al. International Association of Dental Traumatology guidelines for the management of traumatic dental injuries: 3. Injuries in the primary dentition. Dent Traumatol. 2020;36(4):343-359. doi:10.1111/edt.12576
Karagöz Doğan G, Polat Yavuz Y, Yavuz İ. Artificial Intelligence applications in tooth avulsion: comparative accuracy of ChatGPT and DeepSeek. J Clin Pediatr Dent. 2026;50(2):199-208. doi:10.22514/jocpd.2026.049
Grinberg N, Arbel S, Boyadjiev YY, Ianculovici C, Kleinman S, Peleg O. The performance of Artificial Intelligence in providing real-time aid in emergency dental trauma: a clinical validation study. Dent Traumatol. 2026;42(3):356-362. doi:10.1111/edt.70022
Sarıoğlu D, Yücetürk B, Güner Z, Uçar Gündoğar Z. Chatbots in clinical decision-making for dental trauma: from diagnosis to references. J Clin Pediatr Dent. 2026;50(3):274-281. doi:10.22514/jocpd.2026.082
Sözen E, Akpınar H, Yaman S. Comparative performance of large language models for patient-oriented support in dental trauma emergencies. BMC Oral Health. 2026;26(1):665. doi:10.1186/s12903-026-08037-8

Details

Primary Language

English

Subjects

Oral and Maxillofacial Surgery, Paedodontics, Endodontics, Dental Public Health

Journal Section

Research Article

Authors

Banu Çiçek Tez Yaşar ^*
0000-0002-6053-5547
Türkiye

Meltem Karahan
0000-0001-5178-6849
Türkiye

Arif Yiğit Güler
0000-0002-9962-4926
Türkiye

Başak Eliaçık
0000-0003-1848-3007
Türkiye

Publication Date

October 25, 2026

Submission Date

July 23, 2026

Acceptance Date

August 29, 2026

Published in Issue

Year 2026 Volume: 8 Number: 6

IZ

https://izlik.org/JA22BS28SD

Cite

RIS / Bibtex

APA

Tez Yaşar, B. Ç., Karahan, M., Güler, A. Y., & Eliaçık, B. (2026). Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study. Anatolian Current Medical Journal, 8(6), 1199-1207. https://izlik.org/JA22BS28SD

AMA

1.Tez Yaşar BÇ, Karahan M, Güler AY, Eliaçık B. Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study. Anatolian Curr Med J / ACMJ / acmj. 2026;8(6):1199-1207. https://izlik.org/JA22BS28SD

Chicago

Tez Yaşar, Banu Çiçek, Meltem Karahan, Arif Yiğit Güler, and Başak Eliaçık. 2026. “Can Large Language Models Adhere to Clinical Guidelines in Tooth Avulsion Management? A Repeated-Measures Comparative Study”. Anatolian Current Medical Journal 8 (6): 1199-1207. https://izlik.org/JA22BS28SD.

EndNote

Tez Yaşar BÇ, Karahan M, Güler AY, Eliaçık B (October 1, 2026) Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study. Anatolian Current Medical Journal 8 6 1199–1207.

IEEE

[1]B. Ç. Tez Yaşar, M. Karahan, A. Y. Güler, and B. Eliaçık, “Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study”, Anatolian Curr Med J / ACMJ / acmj, vol. 8, no. 6, pp. 1199–1207, Oct. 2026, [Online]. Available: https://izlik.org/JA22BS28SD

ISNAD

Tez Yaşar, Banu Çiçek - Karahan, Meltem - Güler, Arif Yiğit - Eliaçık, Başak. “Can Large Language Models Adhere to Clinical Guidelines in Tooth Avulsion Management? A Repeated-Measures Comparative Study”. Anatolian Current Medical Journal 8/6 (October 1, 2026): 1199-1207. https://izlik.org/JA22BS28SD.

JAMA

1.Tez Yaşar BÇ, Karahan M, Güler AY, Eliaçık B. Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study. Anatolian Curr Med J / ACMJ / acmj. 2026;8:1199–1207.

MLA

Tez Yaşar, Banu Çiçek, et al. “Can Large Language Models Adhere to Clinical Guidelines in Tooth Avulsion Management? A Repeated-Measures Comparative Study”. Anatolian Current Medical Journal, vol. 8, no. 6, Oct. 2026, pp. 1199-07, https://izlik.org/JA22BS28SD.

Vancouver

1.Banu Çiçek Tez Yaşar, Meltem Karahan, Arif Yiğit Güler, Başak Eliaçık. Can large language models adhere to clinical guidelines in tooth avulsion management? A repeated-measures comparative study. Anatolian Curr Med J / ACMJ / acmj [Internet]. 2026 Oct. 1;8(6):1199-207. Available from: https://izlik.org/JA22BS28SD