{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,2]],"date-time":"2026-11-02T13:59:21Z","timestamp":1793627961582,"version":"4.5.1"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T00:00:00Z","timestamp":1774915200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T00:00:00Z","timestamp":1778544000000},"content-version":"vor","delay-in-days":42,"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>To the best of our knowledge, this is the first study in oral and maxillofacial radiology to comprehensively include all examination questions, to systematically analyse their topic distribution across years and examination periods, and to concurrently compare multiple contemporary large language models within a unified methodological framework. This study aimed to compare the accuracy performance of six different artificial intelligence (AI) systems based on large language models (LLMs) of questions asked in the field of oral and maxillofacial radiology in the Dental Specialization Examination (DSE) over the past 13 years, and to analyze the subject matter in detail.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 200 oral and maxillofacial radiology questions from the DSE held between 2012 and 2025 were included in the analysis. The questions were grouped according to their topics and divided into early-late periods (2012\u20132018 and 2019\u20132025) to observe changes over time. ChatGPT-5.2, ChatGPT-4.0, Gemini-3, Claude 4.5, Microsoft Copilot, and Perplexity AI were tested using the original question formats. The models\u2019 answers were evaluated against the official answer key. In addition, the questions were analyzed according to exam years and periods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In the early and late periods, ChatGPT-5.2 showed accuracy rates of 91.9% and 95.7%, respectively. This was followed by ChatGPT-4.0 (79.8% \u2212\u200982.8%). Differences between the models were statistically significant across periods (\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&lt;\u20090.001). Oral diseases and oral pathology retained their importance in both early and late stages of oral health. Furthermore, while oral diseases and oral pathology were more frequently inquired about in the spring, advanced imaging techniques, radiation physics, and temporomandibular joint disorders were also included in the autumn surveys.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ChatGPT-5.2 demonstrated the highest and most consistent accuracy among the evaluated models in DSE oral and maxillofacial radiology questions. In the field of oral and maxillofacial radiology, these model prototypes have the potential to generate new knowledge. Interest in oral diseases and pathology has remained important, while attention to jaw lesions and advanced imaging techniques has increased in recent years.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12903-026-08236-3","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T12:17:37Z","timestamp":1774959457000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Comparative diagnostic accuracy of multiple large language models in oral and maxillofacial radiology specialty examinations: a 13-year analysis of performance and topic trends"],"prefix":"10.1186","volume":"26","author":[{"given":"Murat","family":"Icen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9947-5679","authenticated-orcid":false,"given":"Katibe Tugce","family":"Temur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,31]]},"reference":[{"key":"8236_CR1","unstructured":"Y\u00fcksek\u00f6\u011fretim Kurulu. Mezuniyet \u00d6ncesi Di\u015f Hekimli\u011fi Ulusal \u00c7ekirdek E\u011fitim Program\u0131 (DU\u00c7EP). Ankara: Y\u00d6K. 2020. Available from: Cited 2026 Jan 22. https:\/\/egitim.yok.gov.tr\/documentFiles\/17594056261.Mezuniyet%20%C3%96ncesi%20Di%C5%9F%20Hekimli%C4%9Fi%20Ulusal%20%C3%87ekirdek%20E%C4%9Fitim%20Program%C4%B1.pdf"},{"key":"8236_CR2","unstructured":"T\u00fcrkiye Cumhuriyeti Cumhurba\u015fkanl\u0131\u011f\u0131. Di\u015f Hekimli\u011finde Uzmanl\u0131k E\u011fitimi Y\u00f6netmeli\u011fi. Resm\u00ee Gazete. 2022. Available from: https:\/\/www.mevzuat.gov.tr\/mevzuat?MevzuatNo=39700&MevzuatTur=7&MevzuatTertip=5. Cited 2026 Jan 22."},{"key":"8236_CR3","unstructured":"Sa\u011fl\u0131kla \u0130lgili Baz\u0131 Kanun ve Kanun H\u00fckm\u00fcnde Kararnamelerde De\u011fi\u015fiklik Yap\u0131lmas\u0131na Dair Kanun. Madde 7. Resm\u00ee Gazete. 2018;30616. Available from: https:\/\/resmigazete.gov.tr\/eskiler\/2018\/12\/20181205-8.htm."},{"key":"8236_CR4","unstructured":"T.C. Sa\u011fl\u0131k Bakanl\u0131\u011f\u0131 T\u0131pta Uzmanl\u0131k Kurulu (TUK). T\u0131pta ve Di\u015f Hekimli\u011finde uzmanl\u0131k dallar\u0131n\u0131n \u00e7ekirdek m\u00fcfredat ve standartlar\u0131 (Versiyon 2.3 dok\u00fcmanlar\u0131). 2025. https:\/\/tuk.saglik.gov.tr\/TR-82500\/v-23-dokumanlari.html."},{"issue":"3","key":"8236_CR5","first-page":"420","volume":"31","author":"AK Culhaoglu","year":"2021","unstructured":"Culhaoglu AK, K\u0131l\u0131carslan MA, Deniz KZ. Evaluation of dental specialty entrance examination on approach and preferences for different levels of dental education and post graduation. J Dent Fac Ataturk Univ. 2021;31(3):420\u20136.","journal-title":"J Dent Fac Ataturk Univ"},{"issue":"3","key":"8236_CR6","doi-asserted-by":"publisher","first-page":"311","DOI":"10.62411\/jcta.9447","volume":"1","author":"A Iorliam","year":"2024","unstructured":"Iorliam A, Ingio JA. A comparative analysis of generative artificial intelligence tools for natural language processing. J Comput Theor Appl. 2024;1(3):311\u201325.","journal-title":"J Comput Theor Appl"},{"key":"8236_CR7","unstructured":"OpenAI. ChatGPT: optimizing language models for dialogue. San Francisco: OpenAI. 2023. Available from: https:\/\/openai.com\/blog\/chatgpt\/. Cited 2026 Jan 15."},{"issue":"1","key":"8236_CR8","doi-asserted-by":"publisher","first-page":"4694","DOI":"10.1038\/s41598-025-34773-y","volume":"16","author":"KT Temur","year":"2026","unstructured":"Temur KT, Magat G. Comparative diagnostic accuracy of ChatGPT large language models and expert clinicians in complex oral and maxillofacial diseases. Sci Rep. 2026;16(1):4694.","journal-title":"Sci Rep"},{"issue":"2","key":"8236_CR9","first-page":"31","volume":"3","author":"KT Temur","year":"2025","unstructured":"Temur KT. Performance comparison of artificial intelligence-based language models on oral pathology questions in dental education. J Dent Sci Educ. 2025;3(2):31\u20134.","journal-title":"J Dent Sci Educ"},{"issue":"4","key":"8236_CR10","doi-asserted-by":"publisher","first-page":"459","DOI":"10.1002\/jdd.13766","volume":"89","author":"O Uehara","year":"2025","unstructured":"Uehara O, et al. Performance of ChatGPT-3.5 and ChatGPT-4o in the Japanese National Dental Examination. J Dent Educ. 2025;89(4):459\u201366.","journal-title":"J Dent Educ"},{"issue":"1","key":"8236_CR11","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1111\/eje.13056","volume":"29","author":"S Aldukhail","year":"2025","unstructured":"Aldukhail S. Mapping the landscape of generative language models in dental education: a comparison between ChatGPT and Google Bard. Eur J Dent Educ. 2025;29(1):136\u201348.","journal-title":"Eur J Dent Educ"},{"key":"8236_CR12","doi-asserted-by":"publisher","first-page":"1652422","DOI":"10.3389\/froh.2025.1652422","volume":"6","author":"D Kapoor","year":"2025","unstructured":"Kapoor D, Garg D, Tadakamadla SK. Brush, byte, and bot: quality comparison of artificial intelligence-generated pediatric dental advice across ChatGPT, Gemini, and Microsoft Copilot. Front Oral Health. 2025;6:1652422.","journal-title":"Front Oral Health"},{"key":"8236_CR13","doi-asserted-by":"publisher","first-page":"1657","DOI":"10.1186\/s12909-025-08263-8","volume":"25","author":"\u00d6 Kurt","year":"2025","unstructured":"Kurt \u00d6, \u015eim\u015fek E. Knowledge-level comparison in pulpal and periapical diseases: dental students versus artificial intelligence models (Gemini, Microsoft Copilot, ChatGPT-3.5, ChatGPT-4o): a cross-sectional study. BMC Med Educ. 2025;25:1657.","journal-title":"BMC Med Educ"},{"key":"8236_CR14","doi-asserted-by":"crossref","unstructured":"Ba\u015fkan HK, Baskan B. Performance comparison of large language models on pediatric dentistry questions in the Turkish dentistry specialization examination. BMC Med Educ. 2025;25:1734.","DOI":"10.1186\/s12909-025-08315-z"},{"key":"8236_CR15","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1186\/s12903-025-05554-w","volume":"25","author":"M Tassoker","year":"2025","unstructured":"Tassoker M. ChatGPT-4 Omni\u2019s superiority in answering multiple-choice oral radiology questions. BMC Oral Health. 2025;25(1):173.","journal-title":"BMC Oral Health"},{"issue":"3","key":"8236_CR16","doi-asserted-by":"publisher","first-page":"130","DOI":"10.5505\/yeditepe.2025.93265","volume":"21","author":"RB Peker","year":"2025","unstructured":"Peker RB, ChatGPT CGPT, Plus. Gemini ve Microsoft Copilot b\u00fcy\u00fck dil modellerinin T\u00fcrkiye\u2019deki di\u015f hekimli\u011fi uzmanl\u0131k e\u011fitimi giri\u015f s\u0131nav\u0131nda sorulan a\u011f\u0131z, di\u015f ve \u00e7ene radyolojisi sorular\u0131n\u0131 cevaplama performanslar\u0131n\u0131n de\u011ferlendirilmesi. Yeditepe J Dent. 2025;21(3):130\u20135.","journal-title":"Yeditepe J Dent"},{"issue":"6","key":"8236_CR17","doi-asserted-by":"publisher","first-page":"e0326351","DOI":"10.1371\/journal.pone.0326351","volume":"20","author":"M Kara","year":"2025","unstructured":"Kara M, Ozduran E, Kara MM, \u00d6zbek \u0130C, Hanc\u0131 V. Evaluating the readability, quality, and reliability of responses generated by ChatGPT, Gemini, and Perplexity on the most commonly asked questions about ankylosing spondylitis. PLoS ONE. 2025;20(6):e0326351.","journal-title":"PLoS ONE"},{"key":"8236_CR18","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1186\/s12909-025-07896-z","volume":"25","author":"EC \u00c7eki\u00e7","year":"2025","unstructured":"\u00c7eki\u00e7 EC, Tav\u015fan O. Evaluating large language models using national endodontic specialty examination questions: are they ready for real-world dentistry? BMC Med Educ. 2025;25:1308.","journal-title":"BMC Med Educ"},{"key":"8236_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1186\/s12903-025-07612-9","volume":"26","author":"M Haberal","year":"2026","unstructured":"Haberal M, Han\u00e7erlio\u011fullar\u0131 D. Can artificial intelligence chatbots think like dentists? A comparative analysis based on dental specialty examination questions in restorative dentistry. BMC Oral Health. 2026;26(1):231.","journal-title":"BMC Oral Health"},{"issue":"3","key":"8236_CR20","doi-asserted-by":"publisher","first-page":"401","DOI":"10.5336\/dentalsci.2024-107488","volume":"31","author":"A A\u015f\u0131k","year":"2025","unstructured":"A\u015f\u0131k A, Kuru E. Di\u015f hekimli\u011finde uzmanl\u0131k e\u011fitim giri\u015f s\u0131nav\u0131nda sorulan \u00e7ocuk di\u015f hekimli\u011fi sorular\u0131na ChatGPT\u2019nin verdi\u011fi cevaplar\u0131n analizi: kesitsel ara\u015ft\u0131rma. Turkiye Klinikleri J Dent Sci. 2025;31(3):401\u20136.","journal-title":"Turkiye Klinikleri J Dent Sci"},{"issue":"4","key":"8236_CR21","doi-asserted-by":"publisher","first-page":"668","DOI":"10.5336\/dentalsci.2024-104610","volume":"30","author":"D Bilgin Av\u015far","year":"2024","unstructured":"Bilgin Av\u015far D, Ertan AA. Di\u015f hekimli\u011finde uzmanl\u0131k s\u0131nav\u0131nda sorulan protetik di\u015f tedavisi sorular\u0131n\u0131n ChatGPT-3.5 ve Gemini taraf\u0131ndan cevaplanma performanslar\u0131n\u0131n kar\u015f\u0131la\u015ft\u0131rmal\u0131 olarak incelenmesi: kesitsel ara\u015ft\u0131rma. Turkiye Klinikleri J Dent Sci. 2024;30(4):668\u201373.","journal-title":"Turkiye Klinikleri J Dent Sci"},{"issue":"1","key":"8236_CR22","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1186\/s12909-024-06389-9","volume":"25","author":"S Sismanoglu","year":"2025","unstructured":"Sismanoglu S, Capan BS. Performance of artificial intelligence on Turkish dental specialization exam: can ChatGPT-4.0 and Gemini Advanced achieve comparable results to humans? BMC Med Educ. 2025;25(1):214.","journal-title":"BMC Med Educ"},{"issue":"3","key":"8236_CR23","first-page":"59","volume":"4","author":"E Y\u00fcceer \u00c7etiner","year":"2025","unstructured":"Y\u00fcceer \u00c7etiner E. Comparative evaluation of ChatGPT-5 and Gemini 2.5 Pro in answering oral and maxillofacial surgery questions from dentistry specialization exams: a cross-sectional study. Eur J Oral Maxillofac Surg. 2025;4(3):59\u201365.","journal-title":"Eur J Oral Maxillofac Surg"},{"issue":"3","key":"8236_CR24","doi-asserted-by":"publisher","first-page":"193","DOI":"10.21306\/dishekimligi.1776983","volume":"11","author":"O Yal\u00e7\u0131n","year":"2025","unstructured":"Yal\u00e7\u0131n O, Topal CG. Di\u015f hekimli\u011fi uzmanl\u0131k e\u011fitimi giri\u015f s\u0131nav\u0131nda sorulan a\u011f\u0131z, di\u015f ve \u00e7ene radyolojisi sorular\u0131n\u0131n retrospektif analizi. J Int Dent Sci. 2025;11(3):193\u2013201.","journal-title":"J Int Dent Sci"},{"issue":"1","key":"8236_CR25","doi-asserted-by":"crossref","first-page":"85","DOI":"10.5336\/dentalsci.2025-112452","volume":"32","author":"EA Gerzeli","year":"2026","unstructured":"Gerzeli EA. Di\u015f hekimli\u011finde uzmanl\u0131k s\u0131nav\u0131nda sorulmu\u015f a\u011f\u0131z, di\u015f ve \u00e7ene radyolojisi sorular\u0131n\u0131n retrospektif analizi. Turkiye Klinikleri J Dent Sci. 2026;32(1):85\u201392.","journal-title":"Turkiye Klinikleri J Dent Sci"},{"issue":"4","key":"8236_CR26","doi-asserted-by":"publisher","first-page":"564","DOI":"10.5336\/dentalsci.2024-104564","volume":"30","author":"\u00d6 Ekici","year":"2024","unstructured":"Ekici \u00d6, \u00c7al\u0131\u015fkan \u0130. Retrospective analysis of oral and maxillofacial surgery questions asked in the dentistry specialization training entrance exam. Turkiye Klinikleri J Dent Sci. 2024;30(4):564\u201371.","journal-title":"Turkiye Klinikleri J Dent Sci"}],"container-title":["BMC Oral Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12903-026-08236-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-026-08236-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-026-08236-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T23:22:02Z","timestamp":1778541722000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12903-026-08236-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,31]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["8236"],"URL":"https:\/\/doi.org\/10.1186\/s12903-026-08236-3","relation":{},"ISSN":["1472-6831"],"issn-type":[{"value":"1472-6831","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,31]]},"assertion":[{"value":"13 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This research was carried out solely using publicly accessible online materials and did not include any human subjects or animal data. Accordingly, ethics committee approval and informed consent were not necessary.","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":"822"}}