{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T09:12:28Z","timestamp":1788772348224,"version":"build-2803163510"},"reference-count":25,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,6]],"date-time":"2026-09-06T00:00:00Z","timestamp":1788652800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medicina"],"abstract":"<jats:p>Background and Objectives: General-purpose multimodal large language models (MLLMs) can interpret radiographic images, but their classification performance across orthodontic tasks remains uncertain. This study compared the classification performance of ChatGPT, Gemini, and Claude on lateral cephalometric, hand\u2013wrist, and panoramic radiographs. Materials and Methods: This retrospective diagnostic accuracy study included 250 individuals, each contributing one lateral cephalometric, hand\u2013wrist, and panoramic pretreatment radiograph (750 total). Reference classifications were established by two experienced orthodontists, with disagreements resolved by consensus. Lateral cephalometric radiographs were classified as skeletal Class I, II, or III based on the ANB angle according to Steiner analysis; hand\u2013wrist radiographs as prepubertal, pubertal, or postpubertal; and panoramic radiographs as early mixed, late mixed, or permanent dentition. Each image was evaluated once by each AI platform using identical Turkish prompts in separate chat sessions. Classification accuracy, balanced accuracy, macro-F1, class-specific metrics, and reference agreement were assessed. Generalized estimating equations (GEE) assessed platform, radiograph type, and interaction effects on correct classification. Results: ChatGPT had the highest hand\u2013wrist accuracy (81.6%; 95% CI, 76.3\u201385.9), whereas Gemini had the highest panoramic accuracy (92.8%; 95% CI, 88.9\u201395.4). Lateral cephalometric accuracies were 70.0%, 64.4%, and 64.8% for ChatGPT, Gemini, and Claude, respectively, with no significant interplatform difference (p = 0.336). The platform \u00d7 radiograph type interaction was significant (Wald \u03c72 = 42.52; df = 4; p &lt; 0.001). Agreement with the reference standard was highest for ChatGPT on hand\u2013wrist radiographs (\u03baw = 0.758) and Gemini on panoramic radiographs (\u03baw = 0.883). Conclusions: Classification performance was task- and platform-dependent, with no model consistently achieving the highest performance. For the predefined classification tasks, these models should not be used as standalone tools for these classification tasks. Their potential as decision-support tools requires prospective evaluation of AI-assisted clinician performance and external validation.<\/jats:p>","DOI":"10.3390\/medicina62091714","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T08:07:06Z","timestamp":1788768426000},"page":"1714","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classification Performance of General-Purpose Multimodal Large Language Models Across Orthodontic Radiographic Tasks: A Comparative Study of ChatGPT, Gemini, and Claude"],"prefix":"10.3390","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8698-4361","authenticated-orcid":false,"given":"Nuri Can","family":"Tanr\u0131sever","sequence":"first","affiliation":[{"name":"Department of Orthodontics, School of Dentistry, Ankara University, 06560 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6743-679X","authenticated-orcid":false,"given":"Kutluhan","family":"Y\u0131lmaz","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, School of Dentistry, Ankara University, 06560 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"given":"Ay\u015feg\u00fcl Dilara","family":"G\u00fcven\u00e7 Tokur","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, School of Dentistry, Ankara University, 06560 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7005-6179","authenticated-orcid":false,"given":"Merve Berika","family":"Kad\u0131o\u011flu","sequence":"additional","affiliation":[{"name":"Department of Orthodontics, School of Dentistry, Ankara University, 06560 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]},{"given":"Mahmut","family":"Kad\u0131o\u011flu","sequence":"additional","affiliation":[{"name":"Independent Researcher, 06560 Ankara, T\u00fcrkiye"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,6]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Tanr\u0131sever, N.C., Kartal, \u00d6.N., G\u00fcven\u00e7 Tokur, A.D., and Ak\u00e7am, M.O. (2026). Maxillary Arch Morphology in Unilateral Buccally and Palatally Impacted Maxillary Canines: A Three-Dimensional Digital Model Study. Diagnostics, 16.","DOI":"10.3390\/diagnostics16131971"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1016\/0002-9416(76)90143-3","article-title":"Skeletal ossification and the adolescent growth spurt","volume":"69","author":"Grave","year":"1976","journal-title":"Am. J. Orthod."},{"key":"ref_3","unstructured":"Proffit, W.R., Fields, H.W., Larson, B.E., and Sarver, D.M. (2019). Contemporary Orthodontics, Elsevier. [6th ed.]."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"729","DOI":"10.1016\/0002-9416(53)90082-7","article-title":"Cephalometrics for you and me","volume":"39","author":"Steiner","year":"1953","journal-title":"Am. J. Orthod."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Ertem Arslan, H., Tanr\u0131sever, N.C., and Ak\u00e7am, M.O. (2026). Craniocervical posture and skeletal malocclusion in adolescents: A cross-sectional study. J. Clin. Med., 15.","DOI":"10.3390\/jcm15051974"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1177\/00220345241235606","article-title":"Artificial intelligence in orthodontics: Critical review","volume":"103","author":"Nordblom","year":"2024","journal-title":"J. Dent. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105442","DOI":"10.1016\/j.jdent.2024.105442","article-title":"Artificial intelligence for orthodontic diagnosis and treatment planning: A scoping review","volume":"152","author":"Gracea","year":"2025","journal-title":"J. Dent."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1038\/s41405-024-00277-6","article-title":"Innovation and application of Large Language Models (LLMs) in dentistry\u2014A scoping review","volume":"10","author":"Umer","year":"2024","journal-title":"BDJ Open"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"cjae017","DOI":"10.1093\/ejo\/cjae017","article-title":"Evidence-based potential of generative artificial intelligence large language models in orthodontics: A comparative study of ChatGPT, Google Bard, and Microsoft Bing","volume":"48","author":"Makrygiannakis","year":"2026","journal-title":"Eur. J. Orthod."},{"key":"ref_10","first-page":"e89149","article-title":"Evaluation of the reliability of AI-based large language models in developing orthodontic treatment plans","volume":"17","author":"Sorel","year":"2025","journal-title":"Cureus"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/j.ajodo.2025.08.010","article-title":"Chat Generative Pretrained Transformer-4.0\u2019s accuracy in assessing cervical vertebrae and hand-wrist maturation stages: A retrospective study","volume":"168","author":"Salmanpour","year":"2025","journal-title":"Am. J. Orthod. Dentofac. Orthop."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Abuabara, A., Baratto-Filho, F., Gallego, G.R., Luiz, L.B., Meger, M.N., Scariot, R., Beisel-Memmert, S., de Araujo, C.M., K\u00fcchler, E.C., and de Araujo, B.M. (2025). Comparative evaluation of ChatGPT and Gemini in detecting external apical root resorption on panoramic radiographs of orthodontic patients. J. Orofac. Orthop.","DOI":"10.1007\/s00056-025-00624-8"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131r\u0131m, A., Cicek, O., Gen\u00e7, Y.S., and Erdem, R. (2026). Comparative analysis of generative pre-trained transformers for text- and image-based cephalometric prompts using a novel Artificial Intelligence Based Diagnosis and Treatment Planning Index (AIDTI). BMC Med. Inform. Decis. Mak.","DOI":"10.1186\/s12911-026-03587-x"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"101216","DOI":"10.1016\/j.ortho.2026.101216","article-title":"Performance of multimodal large language models in interpreting lateral cephalometric superimpositions: A comparative observer-performance study","volume":"24","author":"Nguyen","year":"2026","journal-title":"Int. Orthod."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"5870","DOI":"10.1038\/s41598-023-33058-6","article-title":"Prediction of Fishman\u2019s skeletal maturity indicators using artificial intelligence","volume":"13","author":"Kim","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Y\u0131ld\u0131r\u0131m, A., Cicek, O., and Gen\u00e7, Y.S. (2025). Can AI-based ChatGPT models accurately analyze hand\u2013wrist radiographs? A comparative study. Diagnostics, 15.","DOI":"10.3390\/diagnostics15121513"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1111\/ocr.70008","article-title":"Deep learning based evaluation of skeletal maturation: A comparative analysis of five hand-wrist methods","volume":"28","year":"2025","journal-title":"Orthod. Craniofac. Res."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ai, Q.Y.H., Yeung, A.W.K., Tanaka, R., Nalley, A., and Hung, K.F. (2025). Performance of a vision-language model in detecting common dental conditions on panoramic radiographs using different tooth numbering systems. Diagnostics, 15.","DOI":"10.3390\/diagnostics15182315"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Camlet, A., Kusiak, A., Ossowska, A., and \u015awietlik, D. (2025). Advances in periodontal diagnostics: Application of multimodal language models in visual interpretation of panoramic radiographs. Diagnostics, 15.","DOI":"10.3390\/diagnostics15151851"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Tanr\u0131sever, N.C., and Ak\u00e7am, M.O. (2026). Sagittal, vertical, and transverse skeletal characteristics in individuals with impacted maxillary canines: A retrospective study. J. Clin. Med., 15.","DOI":"10.3390\/jcm15041466"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jeong, S.H., Yun, J.P., Yeom, H.G., Lim, H.J., Lee, J., and Kim, B.C. (2021). Deep-learning-based detection of cranio-spinal differences between skeletal classification using cephalometric radiography. Diagnostics, 11.","DOI":"10.3390\/diagnostics11040591"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"cjae029","DOI":"10.1093\/ejo\/cjae029","article-title":"Can artificial intelligence-driven cephalometric analysis replace manual tracing? A systematic review and meta-analysis","volume":"46","author":"Hendrickx","year":"2024","journal-title":"Eur. J. Orthod."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"11659","DOI":"10.1038\/s41598-022-15856-6","article-title":"Deep convolutional neural network-based skeletal classification of cephalometric image compared with automated-tracing software","volume":"12","author":"Kim","year":"2022","journal-title":"Sci. Rep."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Acerra, A., Aliberti, A., Amato, A., Eccellente, A., Santurro, A., and Giordano, F. (2026). Artificial Intelligence in Implant Dentistry: Clinical Validity, Diagnostic Performance, Surgical Planning, and Medico-Legal Implications\u2014A Narrative Review. Dent. J., 14.","DOI":"10.3390\/dj14070389"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Neji, G., Gasparro, R., Tlili, M., Dhahri, A., Khanfir, F., Sammartino, G., Aliberti, A., Campana, M.D., and Ben Amor, F. (2026). AI-Powered Predictive Models in Implant Dentistry: Planning, Risk Assessment, and Outcomes. J. Clin. Med., 15.","DOI":"10.3390\/jcm15010228"}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/9\/1714\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T09:01:14Z","timestamp":1788771674000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/9\/1714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,6]]},"references-count":25,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["medicina62091714"],"URL":"https:\/\/doi.org\/10.3390\/medicina62091714","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,6]]}}}