Can vision-language models estimate patient age? evidence from panoramic radiographs
Authors:
- Thaísa Pinheiro SilvaTSThaísa Pinheiro Silva
- Fernanda Bulhões FagundesFFFernanda Bulhões Fagundes
- Maria Fernanda Andrade-BortolettoMAMaria Fernanda Andrade-Bortoletto
- Christiano Oliveira-SantosCOChristiano Oliveira-Santos
- Deborah Queiroz FreitasDFDeborah Queiroz Freitas
- Matheus L. OliveiraMOMatheus L. Oliveira
Open Access
- 26 September 2026
- journal article
- research article
- Published by Springer Nature in Clinical Oral Investigations
- Vol. 30 (10) , 476
Abstract
Objective: To explore the performance and limitations of three vision-language models (VLMs) in estimating chronological age from panoramic radiographs. Materials and Methods: A sample of 140 panoramic radiographs from individuals aged 7 to 20 years was uploaded to three VLMs: ChatGPT-4o, Microsoft Copilot Fast, and Microsoft Copilot Deep. Each VLM was independently prompted to estimate chronological age based on dental eruption patterns. The results were compared with the individuals’ chronological ages. Statistical analysis included agreement within ± 1 year percentage calculation, and one-way analysis of variance to compare estimated and chronological ages (α = 0.05). Results: All three VLMs demonstrated low agreement in age estimation, with overall performance below 35%. Slightly better agreement was observed in individuals aged 9–10 years. The models showed greater deviations from chronological age at the extremes of the age range (7–8 and 17–20 years). No correct estimations were recorded for individuals aged 7, 17, 18, 19, and 20 years for ChatGPT-4o, 15 and 20 years for Microsoft Copilot Fast, and 20 years for Microsoft Copilot Deep. Conclusions: The evaluated VLMs showed limited agreement in estimating chronological age from panoramic radiographs. Therefore, their application in clinical and forensic contexts cannot currently be recommended. Clinical Relevance: Understanding the potential applications and limitations of VLMs as an auxiliary tool in image interpretation is imperative to its use in clinical scenarios.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (0001)
This publication has 15 references indexed in Scilit:
- The performance of large language models in dentomaxillofacial radiology: a systematic reviewDentomaxillofacial Radiology, 2025
- Customized GPT-4V(ision) for radiographic diagnosis: can large language model detect supernumerary teeth?BMC Oral Health, 2025
- Accuracy of LLMs in medical education: evidence from a concordance test with medical teacherBMC Medical Education, 2025
- ChatGPT-4 Omni’s superiority in answering multiple-choice oral radiology questionsBMC Oral Health, 2025
- Performance of a Generative Pre‐Trained Transformer in Generating Scientific Abstracts in Dentistry: A Comparative Observational StudyEuropean Journal of Dental Education, 2024
- DentAge: Deep learning for automated age prediction using panoramic dental X‐ray imagesJournal of Forensic Sciences, 2024
- ChatGPT is bullshitEthics and Information Technology, 2024
- Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnosesClinical Oral Investigations, 2024
- ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reportsEuropean Radiology, 2023
- Beurteilung der WeisheitszahneruptionRechtsmedizin, 2012