{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T01:32:09Z","timestamp":1788226329568,"version":"build-2803163510"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T00:00:00Z","timestamp":1759968000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Educ"],"DOI":"10.1186\/s12909-025-07938-6","type":"journal-article","created":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:16:16Z","timestamp":1760012176000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Performance of multimodal large language models in the Japanese surgical specialist examination"],"prefix":"10.1186","volume":"25","author":[{"given":"Yuji","family":"Miyamoto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takeshi","family":"Nakaura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiro","family":"Nakamura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshinori","family":"Hirai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Masaaki","family":"Iwatsuki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,9]]},"reference":[{"key":"7938_CR1","doi-asserted-by":"publisher","DOI":"10.1111\/medu.15402","author":"HC Lucas","year":"2024","unstructured":"Lucas HC, Upperman JS, Robinson JR. A systematic review of large language models and their implications in medical education. Med Educ. 2024. https:\/\/doi.org\/10.1111\/medu.15402.","journal-title":"Med Educ"},{"issue":"2","key":"7938_CR2","doi-asserted-by":"publisher","first-page":"210","DOI":"10.7326\/M23-2772","volume":"177","author":"JA Omiye","year":"2024","unstructured":"Omiye JA, Gui H, Rezaei SJ, Zou J, Daneshjou R. Large language models in medicine: the potentials and pitfalls\u202f: a narrative review. Ann Intern Med. 2024;177(2):210\u201320. https:\/\/doi.org\/10.7326\/M23-2772.","journal-title":"Ann Intern Med"},{"issue":"5","key":"7938_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2024.109713","volume":"27","author":"X Meng","year":"2024","unstructured":"Meng X, Yan X, Zhang K, et al. The application of large language models in medicine: a scoping review. iScience. 2024;27(5):109713. https:\/\/doi.org\/10.1016\/j.isci.2024.109713.","journal-title":"iScience"},{"issue":"1","key":"7938_CR4","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232756","volume":"310","author":"R Bhayana","year":"2024","unstructured":"Bhayana R. Chatbots and large language models in radiology: a practical primer for clinical and research applications. Radiology. 2024;310(1):e232756. https:\/\/doi.org\/10.1148\/radiol.232756.","journal-title":"Radiology"},{"issue":"7","key":"7938_CR5","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1007\/s11604-024-01552-0","volume":"42","author":"T Nakaura","year":"2024","unstructured":"Nakaura T, Ito R, Ueda D, et al. The impact of large language models on radiology: a guide for radiologists on the latest innovations in AI. Jpn J Radiol. 2024;42(7):685\u201396. https:\/\/doi.org\/10.1007\/s11604-024-01552-0.","journal-title":"Jpn J Radiol"},{"issue":"4","key":"7938_CR6","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1001\/jamasurg.2023.6496","volume":"159","author":"TA Rengers","year":"2024","unstructured":"Rengers TA, Thiels CA, Salehinejad H. Academic surgery in the era of large language models: a review. JAMA Surg. 2024;159(4):445\u201350. https:\/\/doi.org\/10.1001\/jamasurg.2023.6496.","journal-title":"JAMA Surg"},{"issue":"8","key":"7938_CR7","doi-asserted-by":"publisher","first-page":"700","DOI":"10.1308\/rcsann.2024.0023","volume":"106","author":"J Chan","year":"2024","unstructured":"Chan J, Dong T, Angelini GD. The performance of large language models in intercollegiate membership of the Royal college of surgeons examination. Ann R Coll Surg Engl. 2024;106(8):700\u20134. https:\/\/doi.org\/10.1308\/rcsann.2024.0023.","journal-title":"Ann R Coll Surg Engl"},{"issue":"5","key":"7938_CR8","doi-asserted-by":"publisher","first-page":"269","DOI":"10.4174\/astr.2023.104.5.269","volume":"104","author":"N Oh","year":"2023","unstructured":"Oh N, Choi GS, Lee WY. ChatGPT goes to the operating room: evaluating GPT-4 performance and its potential in surgical education and training in the era of large language models. Ann Surg Treat Res. 2023;104(5):269\u201373. https:\/\/doi.org\/10.4174\/astr.2023.104.5.269.","journal-title":"Ann Surg Treat Res"},{"issue":"12","key":"7938_CR9","doi-asserted-by":"publisher","DOI":"10.1097\/GOX.0000000000005448","volume":"11","author":"AA Al Qurashi","year":"2023","unstructured":"Al Qurashi AA, Albalawi IAS, Halawani IR, et al. Can a machine ace the test?? Assessing GPT-4.0\u2019s precision in plastic surgery board examinations. Plast Reconstr Surg. 2023;11(12):e5448. https:\/\/doi.org\/10.1097\/GOX.0000000000005448.","journal-title":"Plast Reconstr Surg"},{"issue":"8","key":"7938_CR10","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1007\/s11604-024-01561-z","volume":"42","author":"Y Hirano","year":"2024","unstructured":"Hirano Y, Hanaoka S, Nakao T, et al. Gpt-4 turbo with vision fails to outperform text-only GPT-4 turbo in the Japan diagnostic radiology board examination. Jpn J Radiol. 2024;42(8):918\u201326. https:\/\/doi.org\/10.1007\/s11604-024-01561-z.","journal-title":"Jpn J Radiol"},{"issue":"24","key":"7938_CR11","doi-asserted-by":"publisher","first-page":"00819","DOI":"10.1016\/j.acra.2024.10.035","volume":"S1076\u20136332","author":"T Nakaura","year":"2024","unstructured":"Nakaura T, Yoshida N, Kobayashi N, et al. Performance of multimodal large Language models in Japanese diagnostic radiology board examinations (2021\u20132023). Acad Radiol. 2024;S1076\u20136332(24):00819\u20135. https:\/\/doi.org\/10.1016\/j.acra.2024.10.035.","journal-title":"Acad Radiol"},{"issue":"1","key":"7938_CR12","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232411","volume":"310","author":"D Li","year":"2024","unstructured":"Li D, Gupta K, Bhaduri M, Sathiadoss P, Bhatnagar S, Chong J. Comparing. GPT-3.5 and GPT-4 accuracy and drift in radiology diagnosis please cases. Radiology. 2024;310(1):e232411. https:\/\/doi.org\/10.1148\/radiol.232411.","journal-title":"Radiology"},{"key":"7938_CR13","doi-asserted-by":"publisher","unstructured":"Fatemi M, Rafiee B, Tang M, Talamadupula K. Concise Reasoning via Reinforcement Learning. arXiv:250405185. Published online May 15, 2025:https:\/\/doi.org\/10.48550\/arXiv.2504.05185. https:\/\/arxiv.org\/abs\/2504.05185","DOI":"10.48550\/arXiv.2504.05185"},{"issue":"8","key":"7938_CR14","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat Med. 2023;29(8):1930\u201340. https:\/\/doi.org\/10.1038\/s41591-023-02448-8.","journal-title":"Nat Med"},{"key":"7938_CR15","doi-asserted-by":"publisher","DOI":"10.2196\/52865","volume":"25","author":"B Mesk\u00f3","year":"2023","unstructured":"Mesk\u00f3 B. The impact of multimodal large language models on health care\u2019s future. J Med Internet Res. 2023;25:e52865. https:\/\/doi.org\/10.2196\/52865.","journal-title":"J Med Internet Res"},{"issue":"3","key":"7938_CR16","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.240153","volume":"312","author":"N Hayden","year":"2024","unstructured":"Hayden N, Gilbert S, Poisson LM, Griffith B, Klochko C. Performance of GPT-4 with vision on text- and image-based ACR diagnostic radiology in-training examination questions. Radiology. 2024;312(3):e240153. https:\/\/doi.org\/10.1148\/radiol.240153.","journal-title":"Radiology"},{"issue":"6663","key":"7938_CR17","doi-asserted-by":"publisher","first-page":"adk6139","DOI":"10.1126\/science.adk6139","volume":"381","author":"EJ Topol","year":"2023","unstructured":"Topol EJ. As artificial intelligence goes multimodal, medical applications multiply. Science. 2023;381(6663):adk6139. https:\/\/doi.org\/10.1126\/science.adk6139.","journal-title":"Science"}],"container-title":["BMC Medical Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-025-07938-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12909-025-07938-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-025-07938-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T12:16:17Z","timestamp":1760012177000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmededuc.biomedcentral.com\/articles\/10.1186\/s12909-025-07938-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,9]]},"references-count":17,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["7938"],"URL":"https:\/\/doi.org\/10.1186\/s12909-025-07938-6","relation":{},"ISSN":["1472-6920"],"issn-type":[{"value":"1472-6920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,9]]},"assertion":[{"value":"26 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not available.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"The present study analyzed exam items sourced from publicly accessible archives of the Japan Surgical Society. Since no human or animal data were involved, ethical review was deemed unnecessary. All data was anonymized and processed in compliance with applicable data protection standards.","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":"1379"}}