Diagnostic accuracy and repeatability of ChatGPT using textual and radiographic data in reversible pulpitis: a retrospective diagnostic study
Frontiers in Bioinformatics · 21.07.2026 · 6
DOI: 10.3389/fbinf.2026.1877345 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Bioinformatics, online erschienen am 21.07.2026. Verfasst von María Llorente de Pedro und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Dentistry, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, Spain. Die Arbeit nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Objectives
Large language models have recently evolved into multimodal systems capable of interpreting images alongside text. The aim of this study was to assess the diagnostic accuracy and repeatability of ChatGPT-5 for reversible pulpitis, based on structured clinical information and periapical radiographs (PRs).
Methods
Thirty expert-validated cases of reversible pulpitis were retrospectively selected. For each case, clinical data and PRs were compiled to create a reference dataset, with expert consensus serving as the reference standard. A structured prompt incorporating clinical information and PR was designed and included six predefined questions: four addressing diagnostic reasoning, one assessing whether PR information was used to establish the diagnosis, and one requiring radiographic findings description. Each case was entered thirty times into ChatGPT-5, generating a total of 900 answers. Answers were assessed by two independent experts, with disagreements resolved by a third. Radiographic descriptions were graded using a three-point Likert scale. Diagnostic accuracy and repeatability were analysed using binomial and agreement methods.
Results
Diagnostic questions related to tooth identification, pulpal diagnosis, periapical diagnosis and treatment indication showed accuracies above 96%. Overall accuracy for radiographic description was low (4.67%). Coronal radiographic interpretation showed poor performance (5.15%), whereas accuracy for pulpal and periapical structures exceeded 96%. Repeatability was almost perfect for diagnostic questions and pulpal/periapical interpretation, but moderate for coronal descriptions.
Discussion
ChatGPT-5 demonstrated high accuracy and repeatability in text-based diagnostic reasoning for reversible pulpitis. However, limitations in radiographic interpretation, particularly of coronal structures, indicate that its use should be limited to a supervised decision-support role.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Dentistry, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, Spain.
- Department of Veterinary Medicine, Faculty of Biomedical and Health Sciences, Universidad Europea de Madrid, Villaviciosa de Odón, Spain.
- Universidad Europea de Madrid, Faculty of Biomedical and Health Sciences, University Dental Clinics, Villaviciosa de Odón, Spain.
Zitieren
APA
Llorente de Pedro, M., Freire, Y., Moneo, N., Andreu-Vázquez, C., Estévez, R., Díaz-Flores García, V., & Suárez, A. (2026). Diagnostic accuracy and repeatability of ChatGPT using textual and radiographic data in reversible pulpitis: a retrospective diagnostic study. Frontiers in Bioinformatics, 6. https://doi.org/10.3389/fbinf.2026.1877345
Vancouver
Llorente de Pedro M, Freire Y, Moneo N, Andreu-Vázquez C, Estévez R, Díaz-Flores García V, et al. Diagnostic accuracy and repeatability of ChatGPT using textual and radiographic data in reversible pulpitis: a retrospective diagnostic study. Frontiers in Bioinformatics. 2026;6. doi:10.3389/fbinf.2026.1877345
BibTeX
@article{LlorentedePedro2026,
author = {Llorente de Pedro, María and Freire, Yolanda and Moneo, Natalia and Andreu-Vázquez, Cristina and Estévez, Roberto and Díaz-Flores García, Víctor and Suárez, Ana},
title = {Diagnostic accuracy and repeatability of ChatGPT using textual and radiographic data in reversible pulpitis: a retrospective diagnostic study},
journal = {Frontiers in Bioinformatics},
year = {2026},
volume = {6},
doi = {10.3389/fbinf.2026.1877345}
}
EUVIMED