{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T10:54:16Z","timestamp":1793357656780,"version":"4.5.0"},"reference-count":29,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"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: Artificial intelligence (AI) is increasingly used in clinical dentistry, but its diagnostic accuracy for oral mucosal lesions based on clinical photographs remains insufficiently validated. This prospective observational study compared the Top-1 diagnostic accuracy of ChatGPT-4o and ChatGPT-5 in identifying normal anatomical variants and pathological oral mucosal lesions and evaluated their performance across anatomical sites. Materials and Methods: Seventy adults with either normal anatomical variants (n = 21) or pathological oral mucosal lesions (n = 49) were consecutively recruited at the Department of Dental Medicine, University Hospital of Split, Croatia. One standardized clinical photograph per patient was analyzed by ChatGPT-4o and ChatGPT-5 under image-only and image-plus-text conditions using identical prompts. The reference diagnosis was established by an oral medicine specialist, with histopathological examination (HPE) performed when clinically indicated. Diagnostic performance was assessed using Top-1 accuracy and McNemar\u2019s test. Results: Both models showed low accuracy with image-only input, but performance improved significantly after clinical information was added (p &lt; 0.001). Overall Top-1 accuracy increased from 19.0% to 69.0% for ChatGPT-4o and from 9.0% to 51.0% for ChatGPT-5. For normal anatomical variants, accuracy increased from 14.3% to 81.0% and from 14.3% to 76.2%, respectively. For pathological oral mucosal lesions, accuracy increased from 20.4% to 63.3% and from 6.1% to 40.8%, respectively. ChatGPT-4o showed numerically higher accuracy than ChatGPT-5, particularly for pathological oral mucosal lesions, but no statistically significant difference was found between the models in the corresponding paired comparisons. Conclusions: Diagnostic performance was limited with image-only input but improved substantially when standardized clinical information accompanied the images. The numerical differences between models, particularly for pathological oral mucosal lesions, may be clinically relevant but do not establish superiority or equivalence. Neither model can currently replace conventional clinical diagnosis, and AI should be regarded as a clinical decision-support tool for evaluating oral mucosal lesions.<\/jats:p>","DOI":"10.3390\/medicina62081610","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T09:31:59Z","timestamp":1787304719000},"page":"1610","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial Intelligence for Diagnosing Normal Anatomical Variants and Pathological Oral Mucosal Lesions: A Prospective Observational Study"],"prefix":"10.3390","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2137-9665","authenticated-orcid":false,"given":"Ana","family":"Glavina","sequence":"first","affiliation":[{"name":"Department of Dental Medicine, University Hospital of Split, 21000 Split, Croatia"},{"name":"Department of Oral Medicine, Study of Dental Medicine, School of Medicine, University of Split, 21000 Split, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marija","family":"Gale\u0161i\u0107","sequence":"additional","affiliation":[{"name":"Department of Oral Medicine, Study of Dental Medicine, School of Medicine, University of Split, 21000 Split, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4002-2736","authenticated-orcid":false,"given":"Bojan","family":"Poposki","sequence":"additional","affiliation":[{"name":"Department of Oral and Periodontal Diseases, Faculty of Dentistry\u2014Skopje, Ss. Cyril and Methodius University in Skopje, 1000 Skopje, North Macedonia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5365-9816","authenticated-orcid":false,"given":"Antonija","family":"Tadin","sequence":"additional","affiliation":[{"name":"Department of Dental Medicine, University Hospital of Split, 21000 Split, Croatia"},{"name":"Department of Restorative Dental Medicine and Endodontics, Study of Dental Medicine, School of Medicine, University of Split, 21000 Split, Croatia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"100157","DOI":"10.1016\/j.dentre.2025.100157","article-title":"Artificial intelligence in dentistry: Advancements in periodontology and other specialties, diagnosis, treatment planning, and ethical considerations","volume":"5","author":"Akram","year":"2025","journal-title":"Dent. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Ding, H., Wu, J., Zhao, W., Matinlinna, J.P., Burrow, M.F., and Tsoi, J.K.H. (2023). Artificial intelligence in dentistry\u2014A review. Front. Dent. Med., 4.","DOI":"10.3389\/fdmed.2023.1085251"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"70","DOI":"10.15644\/asc57\/1\/8","article-title":"Artificial Intelligence in Medicine and Dentistry","volume":"57","year":"2023","journal-title":"Acta Stomatol. Croat."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e946676","DOI":"10.12659\/MSM.946676","article-title":"Artificial Intelligence in Dentistry: A Narrative Review of Diagnostic and Therapeutic Applications","volume":"31","author":"Gao","year":"2025","journal-title":"Med. Sci. Monit."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Schneider, H., Ahrens, M., Strumpski, M., R\u00fcger, C., H\u00e4fer, M., H\u00fcttmann, G., Theisen-Kunde, D., Schulz-Hildebrandt, H., and Haak, R. (2020). An Intraoral OCT Probe to Enhanced Detection of Approximal Carious Lesions and Assessment of Restorations. J. Clin. Med., 9.","DOI":"10.3390\/jcm9103257"},{"key":"ref_6","unstructured":"(2025, August 05). Periodontal Disease, Available online: https:\/\/www.ncbi.nlm.nih.gov\/books\/NBK554590\/."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Olawade, D.B., Leena, N., Egbon, E., Rai, J., Mohammed, A.P.E.K., Oladapo, B.I., and Boussios, S. (2025). AI-Driven Advancements in Orthodontics for Precision and Patient Outcomes. Dent. J., 13.","DOI":"10.3390\/dj13050198"},{"key":"ref_8","first-page":"e47941","article-title":"The Impact of Artificial Intelligence on Dental Implantology: A Narrative Review","volume":"15","author":"Altalhi","year":"2023","journal-title":"Cureus"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"5711","DOI":"10.1038\/s41598-020-62586-8","article-title":"Automatic mandibular canal detection using a deep convolutional neural network","volume":"10","author":"Kwak","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_10","unstructured":"(2025, August 15). What Implant Is That?. Available online: https:\/\/www.whatimplantisthat.com."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1111\/j.1875-595X.2006.tb00095.x","article-title":"Identification of dental implants through the use of Implant Recognition Software (IRS)","volume":"56","author":"Michelinakis","year":"2006","journal-title":"Int. Dent. J."},{"key":"ref_12","first-page":"e70090","article-title":"Global cancer statistics 2024: GLOBOCAN estimates of incidence and mortality worldwide for 34 cancers in 186 countries","volume":"76","author":"Sung","year":"2026","journal-title":"CA Cancer J. Clin."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Vinay, V., Jodalli, P., Chavan, M.S., Buddhikot, C.S., Luke, A.M., Ingafou, M.S.H., Reda, R., Pawar, A.M., and Testarelli, L. (2025). Artificial Intelligence in Oral Cancer: A Comprehensive Scoping Review of Diagnostic and Prognostic Applications. Diagnostics, 15.","DOI":"10.3390\/diagnostics15030280"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Adeoye, J., Koohi-Moghadam, M., Lo, A.W.I., Tsang, R.K., Chow, V.L.Y., Zheng, L.W., Choi, S.W., Thomson, P., and Su, Y.X. (2021). Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders. Cancers, 13.","DOI":"10.3390\/cancers13236054"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"20210515","DOI":"10.1259\/dmfr.20210515","article-title":"Segmentation of metastatic cervical lymph nodes from CT images of oral cancers using deep-learning technology","volume":"51","author":"Ariji","year":"2022","journal-title":"Dentomaxillofac. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"3753","DOI":"10.1007\/s11263-024-02032-8","article-title":"Multimodal Machine Learning in Image-Based and Clinical Biomedicine: Survey and Prospects","volume":"132","author":"Warner","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Vaira, L.A., Lechien, J.R., Maniaci, A., De Vito, A., Mayo-Y\u00e1\u00f1ez, M., Troise, S., Consorti, G., Chiesa-Estomba, C.M., Cammaroto, G., and Radulesco, T. (2025). Diagnostic Performance of ChatGPT-4o in Analyzing Oral Mucosal Lesions: A Comparative Study with Experts. Medicina, 61.","DOI":"10.3390\/medicina61081379"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"World Medical Association (2025). World Medical Association Declaration of Helsinki: Ethical principles for medical research involving human participants. JAMA, 333, 71\u201374.","DOI":"10.1001\/jama.2024.21972"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"807","DOI":"10.1038\/s41591-020-0941-1","article-title":"Developing specific reporting guidelines for diagnostic accuracy studies assessing AI interventions: The STARD-AI Steering Group","volume":"26","author":"Sounderajah","year":"2020","journal-title":"Nat. Med."},{"key":"ref_20","unstructured":"OpenAI (2025, August 30). Hello GPT-4o. Available online: https:\/\/openai.com\/index\/hello-gpt-4o\/."},{"key":"ref_21","unstructured":"OpenAI (2025, August 30). Introducing GPT-5. Available online: https:\/\/openai.com\/index\/introducing-gpt-5\/."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s42492-024-00171-w","article-title":"IQAGPT: Computed tomography image quality assessment with vision-language and ChatGPT models","volume":"7","author":"Chen","year":"2024","journal-title":"Vis. Comput. Ind. Biomed. Art"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Furriel, B.C.R.S., Oliveira, B.D., Pr\u00f4a, R., Paiva, J.Q., Loureiro, R.M., Calixto, W.P., Reis, M.R.C., and Giavina-Bianchi, M. (2024). Artificial intelligence for skin cancer detection and classification for clinical environment: A systematic review. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1305954"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106873","DOI":"10.1016\/j.oraloncology.2024.106873","article-title":"Utilizing deep learning for automated detection of oral lesions: A multicenter study","volume":"155","author":"Ye","year":"2024","journal-title":"Oral Oncol."},{"key":"ref_25","unstructured":"OpenAI (2025, September 10). GPT-5 System Card. Available online: https:\/\/cdn.openai.com\/gpt-5-system-card.pdf."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1492","DOI":"10.1002\/ohn.489","article-title":"Accuracy of ChatGPT-Generated Information on Head and Neck and Oromaxillofacial Surgery: A Multicenter Collaborative Analysis","volume":"170","author":"Vaira","year":"2024","journal-title":"Otolaryngol. Head Neck Surg."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"6123","DOI":"10.1007\/s00405-024-08710-0","article-title":"Validation of the Quality Analysis of Medical Artificial Intelligence (QAMAI) tool: A new tool to assess the quality of health information provided by AI platforms","volume":"281","author":"Vaira","year":"2024","journal-title":"Eur. Arch. Otorhinolaryngol."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Chiesa-Estomba, C.M., Andueza-Guembe, M., Maniaci, A., Mayo-Yanez, M., Betances-Reinoso, F., Vaira, L.A., Saibene, A.M., and Lechien, J.R. (2025). Accuracy of ChatGPT-4o in Text and Video Analysis of Laryngeal Malignant and Premalignant Diseases. J. Voice, in press.","DOI":"10.1016\/j.jvoice.2025.03.006"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yu, S., Sun, W., Mi, D., Jin, S., Wu, X., Xin, B., Zhang, H., Wang, Y., Sun, X., and He, X. (2024). Artificial Intelligence Diagnosing of Oral Lichen Planus: A Comparative Study. Bioengineering, 11.","DOI":"10.3390\/bioengineering11111159"}],"container-title":["Medicina"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/8\/1610\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T10:02:56Z","timestamp":1787306576000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1648-9144\/62\/8\/1610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":29,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["medicina62081610"],"URL":"https:\/\/doi.org\/10.3390\/medicina62081610","relation":{},"ISSN":["1648-9144"],"issn-type":[{"value":"1648-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]}}}