Performance of generative artificial intelligence in oral and maxillofacial radiology based on the board-certification examination of Japan.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	Performance of generative artificial intelligence in oral and maxillofacial radiology based on the board-certification examination of Japan.
Συγγραφείς:	Takeshita Y; Department of Oral and Maxillofacial Radiology, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan. takeshita@okayama-u.ac.jp., Kawazu T; Department of Oral and Maxillofacial Radiology, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Hisatomi M; Department of Oral and Maxillofacial Radiology, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Fujikura M; Department of Oral and Maxillofacial Radiology, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Okada S; Department of Oral and Maxillofacial Radiology, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Shibanuma A; Department of Community and Global Health, Graduate School of Medicine, The University of Tokyo, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-0033, Japan., Namba Y; Department of Oral and Maxillofacial Radiology, Division of Dentistry, Okayama University Hospital, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Yoshida S; Department of Oral and Maxillofacial Radiology, Division of Dentistry, Okayama University Hospital, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Yoshida S; Preliminary Examination Room, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Nakamura Y; Department of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan., Yanagi Y; Department of Oral and Maxillofacial Radiology, Faculty of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan.; Department of Oral and Maxillofacial Radiology, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan.; Department of Oral and Maxillofacial Radiology, Division of Dentistry, Okayama University Hospital, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan.; Preliminary Examination Room, Medical Development Field, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan.; Department of Oral and Maxillofacial Radiology, Graduate School of Medicine, Dentistry and Pharmaceutical Sciences, Okayama University, 2-5-1 Shikata-Cho, Kita-Ku, Okayama, 700-8558, Japan.
Πηγή:	Oral radiology [Oral Radiol] 2026 Oct; Vol. 42 (4), pp. 1184-1191. Date of Electronic Publication: 2026 Aug 20.
Τύπος έκδοσης:	Journal Article
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Springer-Verlag Tokyo Country of Publication: Japan NLM ID: 8806621 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1613-9674 (Electronic) Linking ISSN: 09116028 NLM ISO Abbreviation: Oral Radiol Subsets: MEDLINE
Imprint Name(s):	Publication: 2004- : Tokyo : Springer-Verlag Tokyo Original Publication: Gifu, Japan : Japanese Society of Dental Radiology
Ιατρικοί όροι (MeSH):	Radiology/education , Generative Artificial Intelligence , Certification*, Japan ; Humans
Περίληψη:	Objective: To evaluate the performance and potential utility of generative artificial intelligence (AI) in oral and maxillofacial radiology using the board-certification examination administered by the Japanese Society for Oral and Maxillofacial Radiology (JSOMR). Methods: The responses generated by ChatGPT for multiple-choice questions from the board-certification examination of the JSOMR over the three-year period from 2020 to 2022 were assessed. The questions were manually entered individually as prompts for GPT-3.5, GPT-4, and GPT-5, which are the models available from ChatGPT. The accuracy was calculated according to examination year, question format, and level of taxonomy. Results: GPT-3.5 achieved an accuracy of 40.3% for the three years (42.9%, 42.0%, and 36.0% for 2020, 2021, and 2022, respectively), that of GPT-4 was 67.8% (67.3%, 74.0%, and 62.0%, respectively), and that of GPT-5 was 76.5% (79.6%, 78.0%, and 72.0%, respectively). GPT-5's results exceeded the passing score for each year with the accuracy significantly outperformed that of GPT-3.5 and GPT-4. Regarding performance according to the question format, GPT-5 performed significantly superior to the earlier models, especially on two-answer questions. Conclusions: On the board-certification examination of the JSOMR, the performance of GPT-5 was significantly superior to that of GPT-3.5 and GPT-4. This suggests that, given the rapid development of generative AI, GPT-5 has reached a level of text-based knowledge equivalent to that assessed in the board-certification examination of the JSOMR. (© 2026. The Author(s).)
Competing Interests:	Declarations. Conflicts of interest: Takeshita Y, Kawazu T, Hisatomi M, Fujikura M, Okada S, Shibanuma A, Namba Y, Yoshida S, Yoshida S, Nakamura Y, Yanagi Y declare that they have no conflict of interest. Ethics approval: This article does not contain any studies with human or animal subjects performed by the any of the authors.
References:	Nat Rev Cancer. 2018 Aug;18(8):500-510. (PMID: 29777175) Radiology. 2023 Jul;308(1):e231040. (PMID: 37462501) Dentomaxillofac Radiol. 2024 Sep 1;53(6):390-395. (PMID: 38848473) Radiology. 2023 Jun;307(5):e230987. (PMID: 37191491) Radiology. 2023 Nov;309(2):e232561. (PMID: 37987662) Radiology. 2023 Apr;307(2):e230163. (PMID: 36700838) Radiology. 2023 Jun;307(5):e231259. (PMID: 37367439) BMC Med Educ. 2025 Oct 2;25(1):1319. (PMID: 41039365) BMC Med Educ. 2025 Oct 10;25(1):1403. (PMID: 41074130) J Dent Sci. 2024 Jul;19(3):1595-1600. (PMID: 39035269) Healthcare (Basel). 2023 Mar 19;11(6):. (PMID: 36981544) Radiology. 2023 Jun;307(5):e230582. (PMID: 37191485) Radiology. 2024 Jan;310(1):e232411. (PMID: 38226874) Radiology. 2023 May;307(4):e230424. (PMID: 37014239) Multimed Tools Appl. 2023;82(3):3713-3744. (PMID: 35855771) Jpn J Radiol. 2024 Feb;42(2):201-207. (PMID: 37792149) BMC Oral Health. 2025 Jul 21;25(1):1229. (PMID: 40691556) Dentomaxillofac Radiol. 2025 Nov 1;54(8):613-631. (PMID: 40796316) Nat Med. 2023 Aug;29(8):1930-1940. (PMID: 37460753) Yearb Med Inform. 2022 Aug;31(1):243-253. (PMID: 35654422)
Contributed Indexing:	Keywords: Artificial intelligence; ChatGPT; Education; Generative artificial intelligence; Large language model; Radiology
Entry Date(s):	Date Created: 20260820 Date Completed: 20260928 Latest Revision: 20261001
Update Code:	20261001
PubMed Central ID:	PMC13619696
DOI:	10.1007/s11282-026-00965-z
PMID:	42622945
Βάση Δεδομένων:	MEDLINE

Περιγραφή
ISSN:	1613-9674
DOI:	10.1007/s11282-026-00965-z