{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:43:29Z","timestamp":1791650609656,"version":"4.3.4"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T00:00:00Z","timestamp":1777248000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"JSPS KAKENHI","award":["JP24K11980"],"award-info":[{"award-number":["JP24K11980"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Gen Thorac Cardiovasc Surg"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1007\/s11748-026-02304-9","type":"journal-article","created":{"date-parts":[[2026,4,27]],"date-time":"2026-04-27T07:27:58Z","timestamp":1777274878000},"page":"950-962","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Performance of large language models on the Japanese cardiovascular surgery board examination: a comparative analysis of eight contemporary AI models with educational implications"],"prefix":"10.1007","volume":"74","author":[{"given":"Kentaro","family":"Kasa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daisuke","family":"Yoshimaru","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hiroki","family":"Ohta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takao","family":"Ohki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hirotaka James","family":"Okano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,27]]},"reference":[{"issue":"7972","key":"2304_CR1","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, Chung HW, et al. Large language models encode clinical knowledge. Nature. 2023;620(7972):172\u201380. https:\/\/doi.org\/10.1038\/s41586-023-06291-2.","journal-title":"Nature"},{"issue":"3","key":"2304_CR2","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M, et al. Toward expert-level medical question answering with large language models. Nat Med. 2025;31(3):943\u201350. https:\/\/doi.org\/10.1038\/s41591-024-03423-7.","journal-title":"Nat Med"},{"issue":"1","key":"2304_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s43856-023-00370-1","volume":"3","author":"J Clusmann","year":"2023","unstructured":"Clusmann J, Kolbinger FR, Muti HS, Carrero ZI, Eckardt JN, Laleh NG, et al. The future landscape of large language models in medicine. Commun Med. 2023;3(1):141. https:\/\/doi.org\/10.1038\/s43856-023-00370-1.","journal-title":"Commun Med"},{"issue":"13","key":"2304_CR4","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1001\/jama.2017.18391","volume":"319","author":"AL Beam","year":"2018","unstructured":"Beam AL, Kohane IS. Big data and machine learning in health care. JAMA. 2018;319(13):1317\u20138. https:\/\/doi.org\/10.1001\/jama.2017.18391.","journal-title":"JAMA"},{"issue":"10","key":"2304_CR5","doi-asserted-by":"publisher","first-page":"e767","DOI":"10.1016\/S2589-7500(24)00151-1","volume":"6","author":"G Quer","year":"2024","unstructured":"Quer G, Topol EJ. The potential for large language models to transform cardiovascular medicine. Lancet Digit Health. 2024;6(10):e767\u201371. https:\/\/doi.org\/10.1016\/S2589-7500(24)00151-1.","journal-title":"Lancet Digit Health"},{"issue":"2","key":"2304_CR6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"TH Kung","year":"2023","unstructured":"Kung TH, Cheatham M, Medenilla A, Sillos C, De Leon L, Elepa\u00f1o C, et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLOS Digit Health. 2023;2(2):e0000198. https:\/\/doi.org\/10.1371\/journal.pdig.0000198.","journal-title":"PLOS Digit Health"},{"key":"2304_CR7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.13375","author":"H Nori","year":"2023","unstructured":"Nori H, King N, McKinney SM, Carignan D, Horvitz E. Capabilities of GPT-4 on medical challenge problems. arXiv. 2023. https:\/\/doi.org\/10.48550\/arXiv.2303.13375.","journal-title":"arXiv"},{"key":"2304_CR8","doi-asserted-by":"publisher","DOI":"10.2196\/45312","volume":"9","author":"A Gilson","year":"2023","unstructured":"Gilson A, Safranek CW, Huang T, Socrates V, Chi L, Taylor RA, et al. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med Educ. 2023;9:e45312. https:\/\/doi.org\/10.2196\/45312.","journal-title":"JMIR Med Educ"},{"issue":"3","key":"2304_CR9","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1016\/j.mcpdig.2023.06.004","volume":"1","author":"NJ Al-Shakarchi","year":"2023","unstructured":"Al-Shakarchi NJ, Haq IU. ChatGPT performance in the UK Medical Licensing Assessment: How to train the next generation? Mayo Clin Proc Digit Health. 2023;1(3):309\u201310. https:\/\/doi.org\/10.1016\/j.mcpdig.2023.06.004.","journal-title":"Mayo Clin Proc Digit Health"},{"issue":"1","key":"2304_CR10","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-024-06309-x","volume":"24","author":"Y Chen","year":"2024","unstructured":"Chen Y, Huang X, Yang F, Lin H, Lin H, Zheng Z, et al. Performance of ChatGPT and Bard on the medical licensing examinations varies across different cultures: A comparison study. BMC Med Educ. 2024;24(1):1372. https:\/\/doi.org\/10.1186\/s12909-024-06309-x.","journal-title":"BMC Med Educ"},{"issue":"4","key":"2304_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsurg.2025.103442","volume":"82","author":"JP Bereuter","year":"2025","unstructured":"Bereuter JP, Geissler ME, Klimova A, Steiner RP, Pfeiffer K, Kolbinger FR, et al. Benchmarking vision capabilities of large language models in surgical examination questions. J Surg Educ. 2025;82(4):103442. https:\/\/doi.org\/10.1016\/j.jsurg.2025.103442.","journal-title":"J Surg Educ"},{"issue":"1","key":"2304_CR12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000433","volume":"3","author":"Y Tanaka","year":"2024","unstructured":"Tanaka Y, Nakata T, Aiga K, Etani T, Muramatsu R, Katagiri S, et al. Performance of generative pretrained transformer on the national medical licensing examination in Japan. PLOS Digit Health. 2024;3(1):e0000433. https:\/\/doi.org\/10.1371\/journal.pdig.0000433.","journal-title":"PLOS Digit Health"},{"key":"2304_CR13","doi-asserted-by":"publisher","DOI":"10.2196\/63129","volume":"10","author":"Y Miyazaki","year":"2024","unstructured":"Miyazaki Y, Hata M, Omori H, Hirashima A, Nakagawa Y, Eto M, et al. Performance of ChatGPT-4o on the Japanese medical licensing examination: evalution of accuracy in text-only and image-based questions. JMIR Med Educ. 2024;10:e63129. https:\/\/doi.org\/10.2196\/63129.","journal-title":"JMIR Med Educ"},{"issue":"6","key":"2304_CR14","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.17641","volume":"7","author":"JB Longwell","year":"2024","unstructured":"Longwell JB, Hirsch I, Binder F, Gonzalez Conchas GA, Mau D, Jang R, et al. Performance of large language models on medical oncology examination questions. JAMA Netw Open. 2024;7(6):e2417641. https:\/\/doi.org\/10.1001\/jamanetworkopen.2024.17641.","journal-title":"JAMA Netw Open"},{"issue":"8","key":"2304_CR15","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, Miki S, Kikuchi T, Nakamura Y, 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":"12","key":"2304_CR16","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.46721","volume":"6","author":"MC Schubert","year":"2023","unstructured":"Schubert MC, Wick W, Venkataramani V. Performance of large language models on a neurology board-style examination. JAMA Netw Open. 2023;6(12):e2346721. https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.46721.","journal-title":"JAMA Netw Open"},{"key":"2304_CR17","doi-asserted-by":"publisher","DOI":"10.2196\/69313","volume":"11","author":"H Maruyama","year":"2025","unstructured":"Maruyama H, Toyama Y, Takanami K, Takase K, Kamei T. Role of artificial intelligence in surgical training by assessing GPT-4 and GPT-4o on the Japan surgical board examination with text-only and image-accompanied questions: performance evaluation study. JMIR Med Educ. 2025;11:e69313. https:\/\/doi.org\/10.2196\/69313.","journal-title":"JMIR Med Educ"},{"issue":"3","key":"2304_CR18","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.56402","volume":"16","author":"N Nakajima","year":"2024","unstructured":"Nakajima N, Fujimori T, Furuya M, Kanie Y, Imai H, Kita K, et al. A comparison between GPT-3.5, GPT-4, and GPT-4V: Can the large language model (ChatGPT) pass the Japanese Board of Orthopaedic Surgery Examination? Cureus. 2024;16(3):e56402. https:\/\/doi.org\/10.7759\/cureus.56402.","journal-title":"Cureus"},{"issue":"6","key":"2304_CR19","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1227\/neu.0000000000002632","volume":"93","author":"R Ali","year":"2023","unstructured":"Ali R, Tang OY, Connolly ID, Zadnik Sullivan PL, Shin JH, Fridley JS, et al. Performance of ChatGPT and GPT-4 on neurosurgery written board examinations. Neurosurgery. 2023;93(6):1353\u201365. https:\/\/doi.org\/10.1227\/neu.0000000000002632.","journal-title":"Neurosurgery"}],"container-title":["General Thoracic and Cardiovascular Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11748-026-02304-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11748-026-02304-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11748-026-02304-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T00:04:41Z","timestamp":1791072281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11748-026-02304-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":19,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["2304"],"URL":"https:\/\/doi.org\/10.1007\/s11748-026-02304-9","relation":{},"ISSN":["1863-6705","1863-6713"],"issn-type":[{"value":"1863-6705","type":"print"},{"value":"1863-6713","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"16 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 April 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no conflict of interest regarding this article.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study utilized publicly available examination materials with explicit permission from the Japanese Board of Cardiovascular Surgery. The study did not involve human subjects or patient data; therefore, institutional review board approval was not required.","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}}]}}