{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:09:49Z","timestamp":1788948589574,"version":"build-2803163510"},"reference-count":15,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Cone-beam computed tomography (CBCT) provides three-dimensional anatomical detail that is used when classifying impacted mandibular third molars, yet the classification performance of general-purpose multimodal artificial intelligence (AI) chatbot services in this task remains unexplored. This study compared the Winter classification performance of five general-purpose multimodal AI chatbot services with that of expert oral and maxillofacial radiologists using identical standardized CBCT-derived image composites. Methods: A total of 114 impacted mandibular third molars were retrospectively evaluated. For each tooth, a standardized composite of axial, coronal and sagittal multiplanar reconstructions together with one three-dimensional surface rendering was exported as a single JPEG image and submitted to five multimodal AI chatbot services (ChatGPT, Gemini, Copilot, Perplexity and Grok) through their web interfaces using an identical structured prompt that named the target tooth by its FDI number (38 or 48). Each impacted tooth was submitted as a separate case in a separate cleared session; a composite was never used to query two teeth simultaneously. Two board-certified oral and maxillofacial radiologists independently classified the same JPEG composites to establish an adjudicated reference standard. Accuracy, balanced accuracy, macro-averaged recall, precision and F1 score, category-level sensitivity and specificity with exact 95% confidence intervals (CIs) and Cohen\u2019s kappa were calculated, and the accuracy of each service was compared with the majority-class (no-information) baseline. Results: The adjudicated reference standard comprised mesioangular (n = 28), distoangular (n = 9), vertical (n = 25), horizontal (n = 46) and inverted (n = 6) impactions; no transverse case occurred, so the six-category spectrum was incomplete. Inter-observer agreement between the two radiologists was 80.7% (92\/114) with Cohen\u2019s kappa 0.688 (95% CI 0.571\u20130.805). Accuracy was 41.2% (95% CI 32.6\u201350.4) for ChatGPT, 30.7% (23.0\u201339.7) for Copilot and 24.6% (17.6\u201333.2) for Gemini, Perplexity and Grok. No service exceeded the 40.4% majority-class baseline (ChatGPT versus baseline, p = 0.85). Balanced accuracy was 23.8% or lower for every service, and agreement with the reference standard was slight to none (kappa \u22120.003 to 0.097; all 95% CIs included zero). No service produced a correct distoangular (0\/9; 95% CI 0.0\u201333.6) or inverted (0\/6; 95% CI 0.0\u201345.9) classification, although these categories were represented by very few cases and the corresponding estimates are therefore highly imprecise. Conclusions: Within the specific web interfaces, prompt, image composites and testing period evaluated, general-purpose multimodal AI chatbot services did not classify impacted mandibular third molars according to the Winter system more accurately than a trivial majority-class classifier, and their agreement with an expert-adjudicated reference standard was negligible. These findings apply to the tested consumer chatbot services and to static CBCT-derived composites and should not be generalized to all multimodal AI models or to task-specific dental AI systems.<\/jats:p>","DOI":"10.3390\/diagnostics16182904","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:24:02Z","timestamp":1788945842000},"page":"2904","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classification Performance of General-Purpose Multimodal AI Chatbots Versus Expert Radiologists in the Winter Classification of Impacted Mandibular Third Molars on CBCT-Derived Images"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4404-1547","authenticated-orcid":false,"given":"Ahmet Faruk","family":"Erturk","sequence":"first","affiliation":[{"name":"Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Biruni University, Istanbul 34010, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7894-3752","authenticated-orcid":false,"given":"Merve","family":"Yelken Kendirci","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Biruni University, Istanbul 34010, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"validation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1552-2819","authenticated-orcid":false,"given":"Oyun Erdene","family":"Batgerel","sequence":"additional","affiliation":[{"name":"Department of Restorative Dentistry, Faculty of Dentistry, Biruni University, Istanbul 34010, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"resources","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9006-5630","authenticated-orcid":false,"given":"Ilknur","family":"Ozcan","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Radiology, Faculty of Dentistry, Biruni University, Istanbul 34010, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"627","DOI":"10.1007\/s12663-020-01473-1","article-title":"Prevalence of mandibular third molars according to the Pell & Gregory and Winter classifications","volume":"21","author":"Santos","year":"2022","journal-title":"J. Maxillofac. Oral Surg."},{"key":"ref_2","first-page":"58","article-title":"Prevalence of second molar external root resorption caused by mandibular third molars: A CBCT study","volume":"71","author":"Granja","year":"2023","journal-title":"Gen. Dent."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.tripleo.2006.06.060","article-title":"A comparative study of cone-beam computed tomography and conventional panoramic radiography in assessing the topographic relationship between the mandibular canal and impacted third molars","volume":"103","author":"Tantanapornkul","year":"2007","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol. Endodontology"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"20200172","DOI":"10.1259\/dmfr.20200172","article-title":"Artificial intelligence system for automatic deciduous tooth detection and numbering in panoramic radiographs","volume":"50","author":"Bayrakdar","year":"2021","journal-title":"Dentomaxillofacial Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"6562","DOI":"10.1109\/TPAMI.2021.3086072","article-title":"A fully automated method for 3D individual tooth identification and segmentation in dental CBCT","volume":"44","author":"Jang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Batgerel, O.E., Kendirci, M.Y., Ert\u00fcrk, A.F., and Sasany, R. (Eur. J. Dent. Educ., 2026). Diagnostic Performance and Agreement Between Dental Students and an Artificial Intelligence System in Panoramic Radiographs, Eur. J. Dent. Educ., in press.","DOI":"10.1111\/eje.70195"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1007\/s11282-019-00420-2","article-title":"Is there a relationship between third-molar impaction types and the dimensional\/angular measurement values of posterior mandible according to Pell & Gregory\/Winter classification?","volume":"37","author":"Balaban","year":"2021","journal-title":"Oral Radiol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.ajoms.2025.06.014","article-title":"Is it possible to predict the postoperative sequelae following third molar surgery using hematological biomarkers?","volume":"38","author":"Yilmaz","year":"2026","journal-title":"J. Oral Maxillofac. Surg. Med. Pathol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"h5527","DOI":"10.1136\/bmj.h5527","article-title":"STARD 2015: An updated list of essential items for reporting diagnostic accuracy studies","volume":"351","author":"Bossuyt","year":"2015","journal-title":"BMJ"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A guide for authors and reviewers","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol. Artif. Intell."},{"key":"ref_11","unstructured":"StatCounter GlobalStats (2026, January 01). AI Chatbot Market Share. Available online: https:\/\/gs.statcounter.com\/ai-chatbot-market-share."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Assiri, H.A., Hameed, M.S., Alqarni, A., Dawasaz, A.A., Arem, S.A., and Assiri, K.I. (2024). Artificial intelligence application in a case of mandibular third molar impaction: A systematic review of the literature. J. Clin. Med., 13.","DOI":"10.37766\/inplasy2024.6.0081"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.jormas.2020.12.006","article-title":"Evaluation of artificial intelligence for detecting impacted third molars on cone-beam computed tomography scans","volume":"122","author":"Orhan","year":"2021","journal-title":"J. Stomatol. Oral Maxillofac. Surg."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"cjaf085","DOI":"10.1093\/ejo\/cjaf085","article-title":"Assessment of AI software\u2019s diagnostic accuracy in identifying impacted teeth in panoramic radiographs","volume":"47","author":"Makrygiannakis","year":"2025","journal-title":"Eur. J. Orthod."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"994","DOI":"10.1038\/s41598-024-51393-0","article-title":"A retrospective longitudinal assessment of artificial intelligence-assisted radiographic prediction of lower third molar eruption","volume":"14","author":"Chopra","year":"2024","journal-title":"Sci. Rep."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/2904\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T09:45:41Z","timestamp":1788947141000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/18\/2904"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":15,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["diagnostics16182904"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16182904","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]}}}