Diagnostic Performance of Multimodal Large Language Models in the Analysis of Oral Pathology
Oral Diseases · 2025-12 · 31 (12) · 3344-3354
DOI: 10.1111/odi.70009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Oral Diseases, online erschienen am 22.06.2025. Verfasst von Ana Suárez und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pre-Clinic Dentistry II, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Madrid, Spain. Hauptthemen laut MEDLINE: Mouth Diseases, Pathology, Oral. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Objective
This study evaluated the accuracy and repeatability of ChatGPT‐4o, a multimodal AI model, in interpreting photographs of oral mucosal lesions, and explored its potential as a diagnostic support tool for specialists and non‐specialists.
Methods
Thirty clinical photographs of oral and labial mucosal lesions were analysed using ChatGPT‐4o. For each image, 30 responses were generated across 20 days. The model was asked to identify the anatomical location, suggest a diagnosis, and recommend diagnostic tests and treatments. Two oral pathology experts assessed 3600 responses using a three‐point scale (0 = incorrect, 1 = partially correct, 2 = correct). Accuracy and repeatability were analysed using accuracy rates, Gwet's AC and percent agreement.
Results
ChatGPT‐4o achieved 71.4% accuracy in identifying lesion location and 58.2% in diagnosis. In cases with correct diagnoses, the model reached 90.7% and 95.8% accuracy in suggesting diagnostic tests and treatments, respectively. Repeated responses showed substantial to almost perfect agreement across all evaluated aspects.
Conclusions
ChatGPT‐4o showed potential as a reliable and accessible tool to support the initial assessment of oral lesions. Although not a substitute for clinical judgment, it may enhance diagnostic efficiency, particularly in resource‐limited settings. Further validation is needed before clinical use.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Pre-Clinic Dentistry II, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Madrid, Spain.
- Department of pre-Clinic Dentistry I, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Madrid, Spain.
- Department of Veterinary Medicine, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Madrid, Spain.
- School for Doctoral Studies and Research, Universidad Europea de Madrid, Madrid, Spain.
- Department of Medicine, Faculty of Medicine, Health and Sports, Universidad Europea de Madrid, Madrid, Spain.
ORCID-Profile: Víctor Díaz-Flores García, Carmen Martín
Zitieren
APA
Suárez, A., Freire, Y., Suárez, M., Díaz-Flores García, V., Andreu-Vázquez, C., Thuissard Vasallo, I. J., Castillo Varón, A. I., & Martín, C. (2025). Diagnostic Performance of Multimodal Large Language Models in the Analysis of Oral Pathology. Oral Diseases, 31(12), 3344-3354. https://doi.org/10.1111/odi.70009
Vancouver
Suárez A, Freire Y, Suárez M, Díaz-Flores García V, Andreu-Vázquez C, Thuissard Vasallo IJ, et al. Diagnostic Performance of Multimodal Large Language Models in the Analysis of Oral Pathology. Oral Diseases. 2025;31(12):3344-3354. doi:10.1111/odi.70009
BibTeX
@article{Surez2025,
author = {Suárez, Ana and Freire, Yolanda and Suárez, María and Díaz-Flores García, Víctor and Andreu-Vázquez, Cristina and Thuissard Vasallo, Israel John and Castillo Varón, Ana Isabel and Martín, Carmen},
title = {Diagnostic Performance of Multimodal Large Language Models in the Analysis of Oral Pathology},
journal = {Oral Diseases},
year = {2025},
volume = {31},
number = {12},
pages = {3344--3354},
doi = {10.1111/odi.70009}
}
EUVIMED