Limitations of off-the-shelf multimodal foundation models in secondary caries detection on interproximal radiographs
Authors:
- Camila Guimarães da Costa CamposCCCamila Guimarães da Costa Campos
- Cristiano Miranda de AraujoCristiano Miranda de Araujo
- Luana Beatriz das Portas LuizLLLuana Beatriz das Portas Luiz
- Diulia Pereira BubnaDBDiulia Pereira Bubna
- Angela Graciela Deliga SchroderASAngela Graciela Deliga Schroder
- Flares Baratto-FilhoFBFlares Baratto-Filho
- Camila Paiva PerinCPCamila Paiva Perin
- Bianca Marques de Mattos de AraujoBABianca Marques de Mattos de Araujo
- Thalita de Paris MatosTMThalita de Paris Matos
Open Access
- 31 August 2026
- journal article
- research article
- Published by Springer Nature in Odontology
- p. 1-8
Abstract
To evaluate whether off-the-shelf general-purpose multimodal foundation models can achieve clinically meaningful diagnostic performance in detecting secondary caries on interproximal radiographs without domain-specific training, using GPT-5o (OpenAI) and Gemini 2.5 Flash (Google Inc.) as representative publicly accessible models. A comparative exploratory study used 50 interproximal radiographs of posterior teeth obtained from a dental imaging center, yielding 208 teeth. Each tooth was evaluated twice by each model in independent sessions, totaling 416 observations per model. A specialist in restorative dentistry established the reference standard. Models were assessed in a zero-shot setting using a standardized prompt. Diagnostic performance was evaluated at the tooth level using accuracy, sensitivity, specificity, precision, F1-score, and Cohen’s kappa, with 95% confidence intervals estimated via bootstrap resampling (1000 iterations). Both models demonstrated limited diagnostic performance. GPT-5o showed moderate sensitivity (64.7%) but low specificity (32.3%), resulting in an accuracy of 41.3% and negligible agreement with the reference standard (κ = − 0.021). Gemini 2.5 Flash exhibited higher sensitivity (82.8%) but extremely low specificity (13.0%), with lower accuracy (32.5%) and similarly negligible agreement (κ = − 0.026). Both models showed a strong tendency toward false-positive classifications. Tooth localization performance was poor, with low identification rates in both models. GPT-5o and Gemini 2.5 Flash, when used in their off-the-shelf configurations, demonstrated inadequate diagnostic performance for detecting secondary caries on interproximal radiographs. Their limited accuracy, low specificity, and poor localization ability do not support their direct use for secondary caries detection on interproximal radiographs without domain-specific training and rigorous independent validation.Keywords
Funding Information
- Universidade Tuiuti Do Paraná
This publication has 23 references indexed in Scilit:
- Comparative evaluation of ChatGPT and Gemini in detecting external apical root resorption on panoramic radiographs of orthodontic patientsJournal of Orofacial Orthopedics / Fortschritte der Kieferorthopädie, 2025
- Applications and potential of ChatGPT in dentistry: Scoping review of research perspectivesJournal of Dental Sciences, 2025
- Image-Based Diagnostic Performance of LLMs vs CNNs for Oral Lichen Planus: Example-Guided and Differential DiagnosisInternational Dental Journal, 2025
- Deep caries detection using deep learning: from dataset acquisition to detectionClinical Oral Investigations, 2024
- Artificial Intelligence in Dental Caries Diagnosis and Detection: An Umbrella ReviewClinical and Experimental Dental Research, 2024
- GPT-4o and multimodal large language models as companions for mental wellbeingAsian Journal of Psychiatry, 2024
- Large language models illuminate a progressive pathway to artificial intelligent healthcare assistantMedicine Plus, 2024
- AI-Assisted Detection of Interproximal, Occlusal, and Secondary Caries on Bite-Wing Radiographs: A Single-Shot Deep Learning ApproachJournal of Imaging Informatics in Medicine, 2024
- Secondary caries: what is it, and how it can be controlled, detected, and managed?Clinical Oral Investigations, 2020
- Secondary caries: prevalence, characteristics, and approachClinical Oral Investigations, 2019