{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,18]],"date-time":"2026-10-18T09:24:58Z","timestamp":1792315498620,"version":"4.4.0"},"reference-count":24,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":32,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Oral Health"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>This study evaluated the performance of ChatGPT, a multimodal large language model (LLM), in estimating dental age from panoramic radiographs (PRs) and compared its accuracy and reproducibility with those of the London Atlas (LA) method.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      PRs of 620 healthy children aged 6 through 13 years were retrospectively analyzed. An experienced dentomaxillofacial radiologist estimated dental age using the LA, and the ChatGPT-4o model analyzed the same anonymized images to generate automated age predictions. Both methods were repeated after two weeks to assess intra-observer reliability. Predictive accuracy and agreement with chronological age (CA) were evaluated using mean absolute error (MAE), root mean squared error (RMSE), intraclass correlation coefficients (ICC), and Bland\u2013Altman analyses. Statistical significance was set at\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u2009.05.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>ChatGPT\u2019s predictions differed significantly from chronological age (CA), tending to overestimate age in younger children and underestimate age in older children. Compared with the LA, ChatGPT exhibited higher MAE and RMSE values, indicating lower predictive accuracy and greater variability. Error magnitudes were greatest in the 6-, 12-, and 13-year-old groups and lowest in the 8-year-old group, whereas the LA showed lower and more stable errors across ages. The LA demonstrated fewer discrepancies and excellent reproducibility (ICC\u2009=\u20090.960) as compared with the moderate agreement of ChatGPT (ICC\u2009=\u20090.703). Overall, the LA provided estimates closer to CA, whereas ChatGPT exhibited greater variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ChatGPT shows promise for complex decision-making tasks such as dental age estimation; however, its current accuracy, reproducibility, and output stability remain inferior to established methods such as the LA. The inconsistent predictions observed across repeated evaluations highlight a critical limitation regarding its reliability for clinical and forensic applications. Therefore, ChatGPT-based estimations should be interpreted with caution until future versions achieve more consistent and reproducible performance through population-specific training, model optimization, and multicenter validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12903-025-07360-w","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T02:05:18Z","timestamp":1764295518000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Artificial intelligence versus human expertise: reliability of ChatGPT and the London atlas for dental age estimation using panoramic radiographs"],"prefix":"10.1186","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3162-6236","authenticated-orcid":false,"given":"Ramazan Berkay","family":"Peker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"issue":"2","key":"7360_CR1","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/s00414-018-1924-3","volume":"133","author":"Z Yang","year":"2019","unstructured":"Yang Z, Geng K, Liu Y, Sun S, Wen D, Xiao J, et al. Accuracy of the Demirjian and Willems methods of dental age estimation for children from central Southern China. Int J Legal Med. 2019;133(2):593\u2013601.","journal-title":"Int J Legal Med"},{"issue":"4","key":"7360_CR2","volume":"47","author":"MV Bittencourt","year":"2018","unstructured":"Bittencourt MV, Cericato G, Franco A, Gir\u00e3o R, Lima APB, Paranhos L. Accuracy of dental development for estimating the pubertal growth spurt in comparison to skeletal development: a systematic review and meta-analysis. Dentomaxillofac Radiol. 2018;47(4):20170362.","journal-title":"Dentomaxillofac Radiol"},{"issue":"1","key":"7360_CR3","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.forsciint.2007.03.013","volume":"174","author":"R Cameriere","year":"2008","unstructured":"Cameriere R, Ferrante L. Age estimation in children by measurement of carpals and epiphyses of radius and ulna and open apices in teeth: a pilot study. Forensic Sci Int. 2008;174(1):60\u20133.","journal-title":"Forensic Sci Int"},{"issue":"Suppl","key":"7360_CR4","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1177\/00220345650440011901","volume":"44","author":"SM Garn","year":"1965","unstructured":"Garn SM, Lewis AB, Kerewsky RS. Genetic, nutritional, and maturational correlates of dental development. J Dent Res. 1965;44(Suppl):228\u201342.","journal-title":"J Dent Res"},{"issue":"5","key":"7360_CR5","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/s004149900102","volume":"113","author":"A Schmeling","year":"2000","unstructured":"Schmeling A, Reisinger W, Loreck D, Vendura K, Markus W, Geserick G. Effects of ethnicity on skeletal maturation: consequences for forensic age estimations. Int J Legal Med. 2000;113(5):253\u201358.","journal-title":"Int J Legal Med"},{"issue":"8","key":"7360_CR6","doi-asserted-by":"publisher","first-page":"4833","DOI":"10.1007\/s00784-021-03788-w","volume":"25","author":"A Ko\u00e7","year":"2021","unstructured":"Ko\u00e7 A, \u00d6zlek E, \u00d6ner Talma\u00e7 AG. Accuracy of the London atlas, Willems, and Nolla methods for dental age estimation: a cross-sectional study on Eastern Turkish children. Clin Oral Investig. 2021;25(8):4833\u201340.","journal-title":"Clin Oral Investig"},{"issue":"3","key":"7360_CR7","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1002\/ajpa.21258","volume":"142","author":"SJ AlQahtani","year":"2010","unstructured":"AlQahtani SJ, Hector MP, Liversidge HM. Brief communication: the London atlas of human tooth development and eruption. Am J Phys Anthropol. 2010;142(3):481\u201390.","journal-title":"Am J Phys Anthropol"},{"key":"7360_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.legalmed.2021.101991","volume":"54","author":"B Sezer","year":"2022","unstructured":"Sezer B, \u00c7ar\u0131k\u00e7\u0131o\u011flu B. Accuracy of the London Atlas, Haavikko\u2019s method and Cameriere\u2019s European formula of dental age estimation in Turkish children. Leg Med (Tokyo). 2022;54:101991.","journal-title":"Leg Med (Tokyo)"},{"key":"7360_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.forsciint.2019.109912","volume":"302","author":"N Ozveren","year":"2019","unstructured":"Ozveren N, Serindere G, Meric P, Cameriere R. A comparison of the accuracy of Willems\u2019 and Cameriere\u2019s methods based on panoramic radiography. Forensic Sci Int. 2019;302:109912.","journal-title":"Forensic Sci Int"},{"issue":"2","key":"7360_CR10","first-page":"42","volume":"35","author":"J De Tobel","year":"2017","unstructured":"De Tobel J, Radesh P, Vandermeulen D, Thevissen PW. An automated technique to stage lower third molar development on panoramic radiographs for age estimation: a pilot study. J Forensic Odontostomatol. 2017;35(2):42\u201354.","journal-title":"J Forensic Odontostomatol"},{"issue":"4","key":"7360_CR11","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1259\/dmfr.25.4.9084269","volume":"25","author":"L Kullman","year":"1996","unstructured":"Kullman L, Tronje G, Teivens A, Lundholm A. Methods of reducing observer variation in age estimation from panoramic radiographs. Dentomaxillofac Radiol. 1996;25(4):173\u20138.","journal-title":"Dentomaxillofac Radiol"},{"issue":"1","key":"7360_CR12","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/s00414-013-0932-6","volume":"128","author":"D Wittschieber","year":"2014","unstructured":"Wittschieber D, Schulz R, Vieth V, K\u00fcppers M, Bajanowski T, Ramsthaler F, P\u00fcschel K, Pfeiffer H, Schmidt S, Schmeling A. Influence of the examiner\u2019s qualification and sources of error during stage determination of the medial clavicular epiphysis by means of computed tomography. Int J Legal Med. 2014;128(1):183\u201391.","journal-title":"Int J Legal Med"},{"issue":"2\u20133","key":"7360_CR13","first-page":"242.e241","volume":"179","author":"N Lynnerup","year":"2008","unstructured":"Lynnerup N, Belard E, Buch-Olsen K, Sejrsen B, Damgaard-Pedersen K. Intra- and interobserver error of the Greulich\u2013Pyle method as used on a Danish forensic sample. Forensic Sci Int. 2008;179(2\u20133):242.e241-6.","journal-title":"Forensic Sci Int"},{"issue":"Suppl 1","key":"7360_CR14","doi-asserted-by":"publisher","first-page":"S74","DOI":"10.1016\/j.forsciint.2006.02.020","volume":"159","author":"KS Dhanjal","year":"2006","unstructured":"Dhanjal KS, Bhardwaj MK, Liversidge HM. Reproducibility of radiographic stage assessment of third molars. Forensic Sci Int. 2006;159(Suppl 1):S74\u20137.","journal-title":"Forensic Sci Int"},{"issue":"1","key":"7360_CR15","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1186\/s12903-024-03928-0","volume":"24","author":"K Kokomoto","year":"2024","unstructured":"Kokomoto K, Kariya R, Muranaka A, Okawa R, Nakano K, Nozaki K. Automatic dental age calculation from panoramic radiographs using deep learning: a two-stage approach with object detection and image classification. BMC Oral Health. 2024;24(1):143.","journal-title":"BMC Oral Health"},{"issue":"1","key":"7360_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. Customized GPT-4V(ision) for radiographic diagnosis: can large language model detect supernumerary teeth? BMC Oral Health. 2025;25(1):756.","journal-title":"BMC Oral Health"},{"key":"7360_CR17","unstructured":"Queen Mary University of London. London Atlas software. Available from: https:\/\/www.qmul.ac.uk\/dentistry\/atlas\/software-app-full-width-\/. Accessed 12 Jun 2025."},{"key":"7360_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.fsir.2020.100105","volume":"2","author":"HC K\u0131\u015f","year":"2020","unstructured":"K\u0131\u015f HC, G\u00f6r\u00fcrg\u00f6z C, Ba\u015fol M, Canger EM, \u00d6zta\u015f B. Evaluation of the Willems and Cameriere\u2019s dental age estimation methods in Turkish children\u2014a modified version of Cameriere\u2019s method. Forensic Sci Int Rep. 2020;2:100105.","journal-title":"Forensic Sci Int Rep"},{"issue":"6","key":"7360_CR19","doi-asserted-by":"publisher","first-page":"2469","DOI":"10.1007\/s00414-024-03298-w","volume":"138","author":"L Matthijs","year":"2024","unstructured":"Matthijs L, Delande L, De Tobel J, B\u00fcy\u00fck\u00e7akir B, Claes P, Vandermeulen D, Thevissen P. Artificial intelligence and dental age estimation: development and validation of an automated stage allocation technique on all mandibular tooth types in panoramic radiographs. Int J Legal Med. 2024;138(6):2469\u201379.","journal-title":"Int J Legal Med"},{"issue":"1","key":"7360_CR20","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1186\/s12903-024-04160-6","volume":"24","author":"SH Ong","year":"2024","unstructured":"Ong SH, Kim H, Song JS, Shin TJ, Hyun HK, Jang KT, Kim YJ. Fully automated deep learning approach to dental development assessment in panoramic radiographs. BMC Oral Health. 2024;24(1):426.","journal-title":"BMC Oral Health"},{"issue":"2","key":"7360_CR21","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/s12024-025-00962-4","volume":"21","author":"E Yilmaz","year":"2025","unstructured":"Yilmaz E, G\u00f6r\u00fcrg\u00f6z C, K\u0131\u015f HC, Canger EM, \u00d6zta\u015f B. Forensic dental age estimation with deep learning: a modified Xception model for panoramic X-ray images. Forensic Sci Med Pathol. 2025;21(2):565\u201379.","journal-title":"Forensic Sci Med Pathol"},{"key":"7360_CR22","doi-asserted-by":"publisher","first-page":"518.e511","DOI":"10.1016\/j.forsciint.2015.09.007","volume":"257","author":"SR Vidisdottir","year":"2015","unstructured":"Vidisdottir SR, Richter S. Age estimation by dental developmental stages in children and adolescents in Iceland. Forensic Sci Int. 2015;257:518.e511-17.","journal-title":"Forensic Sci Int"},{"issue":"3","key":"7360_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/s00784-024-05587-5","volume":"28","author":"TP Silva","year":"2024","unstructured":"Silva TP, Andrade-Bortoletto MFS, Ocampo TSC, Alencar-Palha C, Bornstein MM, Oliveira-Santos C, et al. Performance of a commercially available Generative Pre-trained Transformer (GPT) in describing radiolucent lesions in panoramic radiographs and establishing differential diagnoses. Clin Oral Investig. 2024;28(3):204.","journal-title":"Clin Oral Investig"},{"key":"7360_CR24","doi-asserted-by":"publisher","first-page":"1224682","DOI":"10.3389\/fradi.2023.1224682","volume":"3","author":"Z Liu","year":"2024","unstructured":"Liu Z, Zhang L, Wu Z, Yu X, Cao C, Dai H, Liu N, Liu J, Liu W, Li Q, Shen D, Li X, Zhu D, Liu T. Surviving ChatGPT in healthcare. Front Radiol. 2024;3:1224682.","journal-title":"Front Radiol"}],"container-title":["BMC Oral Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-07360-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12903-025-07360-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-07360-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T14:01:58Z","timestamp":1781618518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12903-025-07360-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":24,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["7360"],"URL":"https:\/\/doi.org\/10.1186\/s12903-025-07360-w","relation":{},"ISSN":["1472-6831"],"issn-type":[{"value":"1472-6831","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"14 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The Non\u2011Interventional Scientific Research Ethics Committee of Trakya University Faculty of Medicine, Turkey, approved this retrospective observational study (No. T\u00dcTF-GOBEAK 2025\/376). All panoramic radiographs were anonymized prior to analysis, and no identifiable personal information was used. All procedures performed in this study involving human data were conducted in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Declaration of Helsinki and its later amendments or comparable ethical standards. As this study involved only retrospective analysis of existing, anonymized clinical data, the ethics committee waived the requirement for informed consent.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2002"}}