{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T20:53:15Z","timestamp":1792615995077,"version":"4.5.0"},"reference-count":13,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Eur J Dental Education"],"published-print":{"date-parts":[[2026,11]]},"abstract":"ABSTRACT<\/jats:title>\n \n Background<\/jats:title>\n Large language models (LLMs), including ChatGPT, Gemini and DeepSeek, are increasingly explored as supportive tools in health professions education. However, their educational utility across different knowledge domains and question formats, particularly those involving visual content, remains insufficiently understood.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to evaluate the educational potential of three advanced LLMs in dental training by analysing their performance on a national specialty examination over a 10\u2010year period, with particular emphasis on domain\u2010specific accuracy and differences between text\u2010based and visual questions.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n A total of 1560 multiple\u2010choice questions from 13 administrations of the Turkish Dental Specialty Examination (DUS) between 2012 and 2021 were included. All questions were translated into English and categorized into nine dental specialties. Each question was individually entered into ChatGPT\u20104.0, Gemini Advanced and DeepSeek in isolated sessions. Model responses were compared with official answer keys, and accuracy rates were analysed across years, specialties and question types. Statistical analyses included chi\u2010square tests, one\u2010way ANOVA and Kruskal\u2013Wallis tests.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n ChatGPT\u20104.0 achieved the highest overall accuracy (86.93%), followed by Gemini (82.86%) and DeepSeek (82.34%). Performance varied across specialties, with higher accuracy observed in Basic Sciences and Oral Surgery, and lower performance in Orthodontics and Endodontics. A substantial decrease in accuracy was observed for visual questions (ChatGPT: 52.38%; Gemini: 45.24%; DeepSeek: 2.38%) compared to text\u2010based items (all models >\u200983%). ChatGPT demonstrated more stable performance across years, whereas Gemini and DeepSeek showed greater variability.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n LLMs demonstrate strong potential as supportive tools in dental education, particularly for text\u2010based knowledge assessment. However, their limited performance in visual question contexts highlights an important constraint for their integration into image\u2010dependent domains such as dental diagnostics. These findings underscore the need for cautious and context\u2010aware implementation of AI tools in dental curricula and assessment practices.<\/jats:p>\n <\/jats:sec>","DOI":"10.1111\/eje.70268","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T15:58:52Z","timestamp":1786377532000},"page":"2165-2171","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing the Educational Role of Large Language Models in Dental Training: A Decade\u2010Long Analysis of Text\u2010Based and Visual Questions in a National Examination"],"prefix":"10.1111","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1880-9276","authenticated-orcid":false,"given":"Sedef Ayse","family":"Tasyapan","sequence":"first","affiliation":[{"name":"Department of Oral and Maxillofacial Radiology, Faculty of Dentistry Istanbul University Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-2156-8776","authenticated-orcid":false,"given":"Didem","family":"\u00d6zer","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Radiology, Faculty of Dentistry Istanbul University Istanbul Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198"},{"key":"e_1_2_12_3_1","unstructured":"OpenAI \u201cChatGPT: Optimizing Language Models for Dialogue \u201dhttps:\/\/openai.com\/research\/chatgpt."},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.2196\/48291"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-07009-w"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.3390\/info16080653"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-06389-9"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0317423"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02709-7"},{"key":"e_1_2_12_10_1","unstructured":"https:\/\/www.osym.gov.tr\/TR 15070\/dus\u2010cikmis\u2010sorular.html."},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000416"},{"issue":"1","key":"e_1_2_12_12_1","article-title":"Evaluating ChatGPT and Google Gemini Performance and Implications in Turkish Dental Education","volume":"17","author":"Kinikoglu I.","year":"2025","journal-title":"Cureus"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.2196\/57594"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240528"}],"container-title":["European Journal of Dental Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eje.70268","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/eje.70268","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eje.70268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T20:17:04Z","timestamp":1792613824000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/eje.70268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":13,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["10.1111\/eje.70268"],"URL":"https:\/\/doi.org\/10.1111\/eje.70268","archive":["Portico"],"relation":{},"ISSN":["1396-5883","1600-0579"],"issn-type":[{"value":"1396-5883","type":"print"},{"value":"1600-0579","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]},"assertion":[{"value":"2026-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}