{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T22:39:50Z","timestamp":1792449590453,"version":"4.5.0"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002322","name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de N\u00edvel Superior","doi-asserted-by":"publisher","award":["0001"],"award-info":[{"award-number":["0001"]}],"id":[{"id":"10.13039\/501100002322","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Clin Oral Invest"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To explore the performance and limitations of three vision-language models (VLMs) in estimating chronological age from panoramic radiographs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>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\u2019 chronological ages. Statistical analysis included agreement within \u00b1\u20091 year percentage calculation, and one-way analysis of variance to compare estimated and chronological ages (\u03b1\u2009=\u20090.05).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>All three VLMs demonstrated low agreement in age estimation, with overall performance below 35%. Slightly better agreement was observed in individuals aged 9\u201310 years. The models showed greater deviations from chronological age at the extremes of the age range (7\u20138 and 17\u201320 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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical Relevance<\/jats:title>\n                    <jats:p>Understanding the potential applications and limitations of VLMs as an auxiliary tool in image interpretation is imperative to its use in clinical scenarios.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00784-026-07183-1","type":"journal-article","created":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T07:31:29Z","timestamp":1790407889000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Can vision-language models estimate patient age? evidence from panoramic radiographs"],"prefix":"10.1007","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-0206","authenticated-orcid":false,"given":"Tha\u00edsa Pinheiro","family":"Silva","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-4197","authenticated-orcid":false,"given":"Fernanda Bulh\u00f5es","family":"Fagundes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2300-3143","authenticated-orcid":false,"given":"Maria Fernanda","family":"Andrade-Bortoletto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9936-7547","authenticated-orcid":false,"given":"Christiano","family":"Oliveira-Santos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1425-5966","authenticated-orcid":false,"given":"Deborah Queiroz","family":"Freitas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matheus L.","family":"Oliveira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,26]]},"reference":[{"key":"7183_CR1","first-page":"211","volume":"45","author":"A Demirjian","year":"1973","unstructured":"Demirjian A, Goldstein H, Tanner JM (1973) A new system of dental age assessment. Hum Biol 45:211\u2013227","journal-title":"Hum Biol"},{"key":"7183_CR2","doi-asserted-by":"publisher","first-page":"526","DOI":"10.1111\/j.1440-1673.2006.01651","volume":"50","author":"R Boeddinghaus","year":"2006","unstructured":"Boeddinghaus R, Whyte A (2006) Dental panoramic tomography: an approach for the general radiologist. Australas Radiol 50:526\u2013533. https:\/\/doi.org\/10.1111\/j.1440-1673.2006.01651","journal-title":"Australas Radiol"},{"key":"7183_CR3","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/s00194-012-0845-6","volume":"22","author":"A Olze","year":"2012","unstructured":"Olze A, Peschke C, Schulz R, Ribbecke S, Schmeling A (2012) Beurteilung der Weisheitszahneruption: Vergleich von zwei Stadieneinteilungen. Rechtsmedizin 22:451\u2013455. https:\/\/doi.org\/10.1007\/s00194-012-0845-6","journal-title":"Rechtsmedizin"},{"key":"7183_CR4","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.1111\/1556-4029.15629","volume":"69","author":"\u017d Bizjak","year":"2024","unstructured":"Bizjak \u017d, Robi\u010d T (2024) DentAge: Deep learning for automated age prediction using panoramic dental X-ray images. J Forensic Sci 69:2069\u20132074. https:\/\/doi.org\/10.1111\/1556-4029.15629","journal-title":"J Forensic Sci"},{"key":"7183_CR5","first-page":"30","volume":"41","author":"M Vodanovi\u0107","year":"2023","unstructured":"Vodanovi\u0107 M, Suba\u0161i\u0107 M, Milo\u0161evi\u0107 DP, Gali\u0107 I, Brki\u0107 H (2023) Artificial intelligence in forensic medicine and forensic dentistry. J Forensic Odontostomatol 41:30\u201341","journal-title":"J Forensic Odontostomatol"},{"key":"7183_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/app14167014","volume":"14","author":"T \u015eahin","year":"2024","unstructured":"\u015eahin T, K\u00f6l\u00fc\u015f T (2024) Age and sex estimation in children and young adults using panoramic radiographs with convolutional neural networks. Appl Sci 14:1\u201310. https:\/\/doi.org\/10.3390\/app14167014","journal-title":"Appl Sci"},{"key":"7183_CR7","doi-asserted-by":"publisher","first-page":"2817","DOI":"10.1007\/s00330-023-10213-1","volume":"34","author":"K Jeblick","year":"2024","unstructured":"Jeblick K, Schachtner B, Dexl J, Mittermeier A, St\u00fcber AT, Topalis J, Weber T, Wesp P, Sabel BO, Ricke J, Ingrisch M (2024) ChatGPT makes medicine easy to swallow: an exploratory case study on simplified radiology reports. Eur Radiol 34:2817\u20132825. https:\/\/doi.org\/10.1007\/s00330-023-10213-1","journal-title":"Eur Radiol"},{"key":"7183_CR8","doi-asserted-by":"publisher","first-page":"80","DOI":"10.4274\/dir.2023.232417","volume":"30","author":"D Akinci","year":"2024","unstructured":"Akinci D, Stanzione A, Bluethgen C, Vernuccio F, Ugga L, Klontzas ME, Cuocolo R, Cannella R, Ko\u00e7ak B (2024) Large language models in radiology: fundamentals, applications, ethical considerations, risks, and future directions. Diagn Interv Radiol 30:80\u201390. https:\/\/doi.org\/10.4274\/dir.2023.232417","journal-title":"Diagn Interv Radiol"},{"key":"7183_CR9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1111\/eje.13057","volume":"29","author":"C Alencar-Palha","year":"2025","unstructured":"Alencar-Palha C, Ocampo T, Silva TP, Neves FS, Oliveira ML (2025) Performance of a generative pre-trained transformer in generating scientific abstracts in dentistry: a comparative observational study. Eur J Dent Educ 29:149\u2013154. https:\/\/doi.org\/10.1111\/eje.13057","journal-title":"Eur J Dent Educ"},{"key":"7183_CR10","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s10676-024-09775-5","volume":"26","author":"MT Hicks","year":"2024","unstructured":"Hicks MT, Humphries J, Slater J (2024) ChatGPT is bullshit. Ethics Inf Technol 26:38. https:\/\/doi.org\/10.1007\/s10676-024-09775-5","journal-title":"Ethics Inf Technol"},{"key":"7183_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00784-024-05587-5","volume":"28","author":"T Silva","year":"2024","unstructured":"Silva T, Bortoletto MF, Ocampo T, Alencar-Palha C, Bornstein MM, Oliveira-Santos C, Oliveira M (2024) Performance of a commercially available generative pre-trained transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses. Clin Oral Investig 28:1\u20139. https:\/\/doi.org\/10.1007\/s00784-024-05587-5","journal-title":"Clin Oral Investig"},{"key":"7183_CR12","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1186\/s12903-025-05554-w","volume":"25","author":"M Tassoker","year":"2025","unstructured":"Tassoker M (2025) ChatGPT-4 Omni\u2019s superiority in answering multiple-choice oral radiology questions. BMC Oral Health 25:173. https:\/\/doi.org\/10.1186\/s12903-025-05554-w","journal-title":"BMC Oral Health"},{"key":"7183_CR13","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1186\/s12909-025-07875-4","volume":"25","author":"BN Gokkurt Yilmaz","year":"2025","unstructured":"Gokkurt Yilmaz BN, Ozbey F, Yilmaz BE (2025) Effect of artificial intelligence-assisted personalized feedback on radiographic diagnostic performance of dental students: a controlled study. BMC Med Educ 25:1403. https:\/\/doi.org\/10.1186\/s12909-025-07875-4","journal-title":"BMC Med Educ"},{"key":"7183_CR14","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.3390\/diagnostics15151851","volume":"15","author":"A Camlet","year":"2025","unstructured":"Camlet A, Kusiak A, Ossowska A, \u015awietlik D (2025) Advances in periodontal diagnostics: application of multimodal language models in visual interpretation of panoramic radiographs. Diagnostics 15:1851. https:\/\/doi.org\/10.3390\/diagnostics15151851","journal-title":"Diagnostics"},{"key":"7183_CR15","doi-asserted-by":"publisher","DOI":"10.1093\/dmfr\/twaf060","author":"Z Liu","year":"2025","unstructured":"Liu Z, Nalley A, Hao J, Ai Q, Yeung AWK, Tanaka R, Hung KF (2025) The performance of large language models in dentomaxillofacial radiology: a systematic review. Dentomaxillofac Radiol. https:\/\/doi.org\/10.1093\/dmfr\/twaf060","journal-title":"Dentomaxillofac Radiol"},{"key":"7183_CR16","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1186\/s12903-025-06163-3","volume":"25","author":"EM A\u015far","year":"2025","unstructured":"A\u015far EM, \u0130pek \u0130, Bilge K (2025) Customized GPT-4V(ision) for radiographic diagnosis: can large language model detect supernumerary teeth? BMC Oral Health 25:756. https:\/\/doi.org\/10.1186\/s12903-025-06163-3","journal-title":"BMC Oral Health"},{"key":"7183_CR17","doi-asserted-by":"publisher","first-page":"2389","DOI":"10.3390\/diagnostics15182389","volume":"15","author":"D Dursun","year":"2025","unstructured":"Dursun D, Bilici Ge\u00e7er R (2025) Dental age estimation from panoramic radiographs: a comparison of orthodontist and ChatGPT-4 evaluations using the London Atlas, Nolla, and Haavikko methods. Diagnostics 15:2389. https:\/\/doi.org\/10.3390\/diagnostics15182389","journal-title":"Diagnostics"},{"key":"7183_CR18","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1186\/s12909-025-07009-w","volume":"25","author":"V Mishra","year":"2025","unstructured":"Mishra V, Lurie Y, Mark S (2025) Accuracy of LLMs in medical education: evidence from a concordance test with medical teacher. BMC Med Educ 25:443. https:\/\/doi.org\/10.1186\/s12909-025-07009-w","journal-title":"BMC Med Educ"}],"container-title":["Clinical Oral Investigations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00784-026-07183-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00784-026-07183-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00784-026-07183-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T22:01:55Z","timestamp":1792447315000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00784-026-07183-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,26]]},"references-count":18,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["7183"],"URL":"https:\/\/doi.org\/10.1007\/s00784-026-07183-1","relation":{},"ISSN":["1436-3771"],"issn-type":[{"value":"1436-3771","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,26]]},"assertion":[{"value":"11 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was approved by the local institutional review board (Protocol #79179124.5.0000.5418). Consent to participate was not applicable.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"476"}}