EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Accuracy of AI Tools in the Diagnosis of Benign, Potentially Malignant and Malignant Oral Lesions: A Pilot Study

Luis Monteiro iD, Juliana Lima, Luís Silva iD, Caren Kaur Jauhal, Aaya Shamekh, Vlaho Brailo iD, Danica Vidović Juras iD, Ali Alqarni iD, Khalid Al-Johani, Sara Ferreira iD, Filomena Salazar iD, Molly Harte iD und 1 weitere

Journal of Clinical Medicine · 30.03.2026 · 15 (7) · 2638

DOI: 10.3390/jcm15072638 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Clinical Medicine, online erschienen am 30.03.2026. Verfasst von Luis Monteiro und 12 weiteren Autor:innen. Beteiligte Einrichtung: UNIPRO-Oral Pathology and Rehabilitation Research Unit, University Institute of Health Sciences (IUCS-CESPU), 4585-116 Gandra, Portugal. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Artificial intelligence (AI) is expected to play an increasingly important role in medicine and dentistry. While its diagnostic potential has been tested in various medical fields, limited research exists on its applications within oral medicine diagnoses using clinical images.

Objective

This pilot study aimed to evaluate the diagnostic accuracy of ChatGPT, Gemini, and Copilot in identifying benign, potentially malignant, and malignant oral lesions.

Methods

A cross-sectional study was conducted using clinical images from three categories: benign oromucosal conditions, oral potentially malignant disorders, and malignant oral lesions.

Results

ChatGPT evaluated all images and consistently outperformed Copilot—and in some cases Gemini—across multiple diagnostic questions, with statistically significant advantages particularly in the cancer subgroup. Copilot showed the weakest performance, with high rates of missing evaluations and significantly lower proportions of correct responses in several analyses. Across both full-dataset and adjusted analyses, ChatGPT demonstrated the highest diagnostic performance overall. Diagnostic accuracy metrics for malignancy suspicion was similar for ChatGPT and Gemini. Several limitations such as sample size, lack of reproducibility testing and inability of some AI models to process images must be taken into account when interpreting the results.

Conclusions

AI tools show promise but cannot yet replace clinical expertise. Further research and development are needed to improve the accuracy and applicability of AI diagnostic tools.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligenceclinical decision-makingcomputer-assisted diagnosisdiagnosismouth mucosaoral canceroral potentially malignant disorders

Autor:innen und Institutionen

  • UNIPRO-Oral Pathology and Rehabilitation Research Unit, University Institute of Health Sciences (IUCS-CESPU), 4585-116 Gandra, Portugal.
  • Department of Oral Medicine, Guy's and St Thomas NHS Foundation Trust, London SE1 9RT, UK.
  • Clinic for Dentistry, School of Dental Medicine, University Clinical Hospital Centre, University of Zagreb, 10000 Zagreb, Croatia.
  • Department of Oral & Maxillofacial Surgery and Diagnostic Sciences, Faculty of Dentistry, Taif University, Taif 21944, Saudi Arabia.
  • Diagnostic Sciences Department, Faculty of Dentistry, King Abdulaziz University, Jeddah 21589, Saudi Arabia.
  • Faculty of Dentistry, Oral and Craniofacial Sciences, King's College London, London SE1 9RT, UK.

ORCID-Profile: Luis Monteiro, Luís Silva, Vlaho Brailo, Danica Vidović Juras, Ali Alqarni, Sara Ferreira, Filomena Salazar, Molly Harte, Rui Albuquerque

Zitieren

APA

Monteiro, L., Lima, J., Silva, L., Jauhal, C. K., Shamekh, A., Brailo, V., Vidović Juras, D., Alqarni, A., Al-Johani, K., Ferreira, S., Salazar, F., Harte, M., & Albuquerque, R. (2026). Accuracy of AI Tools in the Diagnosis of Benign, Potentially Malignant and Malignant Oral Lesions: A Pilot Study. Journal of Clinical Medicine, 15(7), 2638. https://doi.org/10.3390/jcm15072638

Vancouver

Monteiro L, Lima J, Silva L, Jauhal CK, Shamekh A, Brailo V, et al. Accuracy of AI Tools in the Diagnosis of Benign, Potentially Malignant and Malignant Oral Lesions: A Pilot Study. Journal of Clinical Medicine. 2026;15(7):2638. doi:10.3390/jcm15072638

BibTeX
@article{Monteiro2026,
  author = {Monteiro, Luis and Lima, Juliana and Silva, Luís and Jauhal, Caren Kaur and Shamekh, Aaya and Brailo, Vlaho and Vidović Juras, Danica and Alqarni, Ali and Al-Johani, Khalid and Ferreira, Sara and Salazar, Filomena and Harte, Molly and Albuquerque, Rui},
  title = {Accuracy of AI Tools in the Diagnosis of Benign, Potentially Malignant and Malignant Oral Lesions: A Pilot Study},
  journal = {Journal of Clinical Medicine},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {2638},
  doi = {10.3390/jcm15072638}
}
Kostenlos starten →