{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T12:23:08Z","timestamp":1787660588101,"version":"build-2736575974"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Surg Today"],"DOI":"10.1007\/s00595-026-03472-0","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:37:12Z","timestamp":1787657832000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Rasch-based analysis comparing the performance of updated multimodal large language models and surgeons on the Japanese surgical specialist examination"],"prefix":"10.1007","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":"Ayane","family":"Kawata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Toshinori","family":"Hirai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hidetoshi","family":"Eguchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akinobu","family":"Taketomi","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":[[2026,8,25]]},"reference":[{"key":"3472_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bj.2025.100868","author":"C Lin","year":"2025","unstructured":"Lin C, Kuo CF. Roles and potential of large language models in healthcare: a comprehensive review. Biomed J. 2025. https:\/\/doi.org\/10.1016\/j.bj.2025.100868.","journal-title":"Biomed J"},{"key":"3472_CR2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-025-02954-4","author":"S Shool","year":"2025","unstructured":"Shool S, Adimi S, Saboori Amleshi R, Bitaraf E, Golpira R, Tara M. A systematic review of large language model (LLM) evaluations in clinical medicine. BMC Med Inform Decis Mak. 2025. https:\/\/doi.org\/10.1186\/s12911-025-02954-4.","journal-title":"BMC Med Inform Decis Mak"},{"key":"3472_CR3","doi-asserted-by":"publisher","DOI":"10.1177\/03000605251347556","author":"EN Liang","year":"2025","unstructured":"Liang EN, Pei S, Staibano P, van der Woerd B. Clinical applications of large language models in medicine and surgery: a scoping review. J Int Med Res. 2025. https:\/\/doi.org\/10.1177\/03000605251347556.","journal-title":"J Int Med Res"},{"key":"3472_CR4","doi-asserted-by":"publisher","DOI":"10.1001\/JAMASURG.2024.1621","author":"P Chung","year":"2024","unstructured":"Chung P, Fong CT, Walters AM, Aghaeepour N, Yetisgen M, O\u2019Reilly-Shah VN. JAMA Surg. 2024;159:928\u201337. https:\/\/doi.org\/10.1001\/JAMASURG.2024.1621. Large Language Model Capabilities in Perioperative Risk Prediction and Prognostication. JAMA Surg [Internet]."},{"key":"3472_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/S10143-025-03785-7","author":"V Sanker","year":"2025","unstructured":"Sanker V, Nordin EOR, Heesen P, Elfadali MA, Anwar M, Chintapalli RD, et al. Current trends and future prospects of language models and processing systems in spine surgery - a scoping review. Neurosurg Rev. 2025. https:\/\/doi.org\/10.1007\/S10143-025-03785-7.","journal-title":"Neurosurg Rev"},{"key":"3472_CR6","doi-asserted-by":"publisher","DOI":"10.1186\/S12909-025-07938-6","author":"Y Miyamoto","year":"2025","unstructured":"Miyamoto Y, Nakaura T, Nakamura H, Hirai T, Iwatsuki M. Performance of multimodal large language models in the Japanese surgical specialist examination. BMC Med Educ. 2025. https:\/\/doi.org\/10.1186\/S12909-025-07938-6.","journal-title":"BMC Med Educ"},{"key":"3472_CR7","doi-asserted-by":"publisher","DOI":"10.2196\/69313","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. https:\/\/doi.org\/10.2196\/69313.","journal-title":"JMIR Med Educ"},{"key":"3472_CR8","doi-asserted-by":"publisher","first-page":"4347","DOI":"10.1016\/j.acra.2025.04.060","volume":"32","author":"T Nakaura","year":"2025","unstructured":"Nakaura T, Takamure H, Kobayashi N, Shiraishi K, Yoshida N, Nagayama Y, et al. Evaluating the performance of reasoning large language models on Japanese radiology board examination questions. Acad Radiol. 2025;32:4347\u201354. https:\/\/doi.org\/10.1016\/j.acra.2025.04.060.","journal-title":"Acad Radiol"},{"key":"3472_CR9","doi-asserted-by":"publisher","first-page":"1258","DOI":"10.1007\/S12149-025-02084-X","volume":"39","author":"R Ito","year":"2025","unstructured":"Ito R, Kato K, Higashi M, Abe Y, Minamimoto R, Kato K, et al. Vision-language model performance on the Japanese Nuclear Medicine Board Examination: high accuracy in text but challenges with image interpretation. Ann Nucl Med. 2025;39:1258\u201366. https:\/\/doi.org\/10.1007\/S12149-025-02084-X.","journal-title":"Ann Nucl Med"},{"key":"3472_CR10","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1016\/j.jos.2025.03.003","volume":"30","author":"J Maruyama","year":"2025","unstructured":"Maruyama J, Maki S, Furuya T, Nagashima Y, Kitagawa K, Toki Y, et al. Retrieval-augmented generation enhances large language model performance on the Japanese orthopedic board examination. J Orthop Sci. 2025;30:1193\u20138. https:\/\/doi.org\/10.1016\/j.jos.2025.03.003.","journal-title":"J Orthop Sci"},{"key":"3472_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/J.JSURG.2025.103442","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. https:\/\/doi.org\/10.1016\/J.JSURG.2025.103442.","journal-title":"J Surg Educ"},{"key":"3472_CR12","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-07856-7","author":"MC G\u00fcl","year":"2025","unstructured":"G\u00fcl MC. Large language models underperform in European general surgery board examinations: a comparative study with experts and surgical residents. BMC Med Educ. 2025. https:\/\/doi.org\/10.1186\/s12909-025-07856-7.","journal-title":"BMC Med Educ"},{"key":"3472_CR13","doi-asserted-by":"publisher","first-page":"1392","DOI":"10.1007\/S11604-024-01633-0","volume":"42","author":"T Oura","year":"2024","unstructured":"Oura T, Tatekawa H, Horiuchi D, Matsushita S, Takita H, Atsukawa N, et al. Diagnostic accuracy of vision-language models on Japanese diagnostic radiology, nuclear medicine, and interventional radiology specialty board examinations. Jpn J Radiol. 2024;42:1392\u20138. https:\/\/doi.org\/10.1007\/S11604-024-01633-0.","journal-title":"Jpn J Radiol"},{"key":"3472_CR14","doi-asserted-by":"publisher","first-page":"857","DOI":"10.2147\/AMEP.S479801","volume":"15","author":"M Sallam","year":"2024","unstructured":"Sallam M, Al-Salahat K, Eid H, Egger J, Puladi B. Human versus artificial intelligence: ChatGPT-4 outperforming Bing, Bard, ChatGPT-3.5 and humans in clinical chemistry multiple-choice questions. Adv Med Educ Pract. 2024;15:857\u201371. https:\/\/doi.org\/10.2147\/AMEP.S479801.","journal-title":"Adv Med Educ Pract"},{"key":"3472_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/J.CAEAI.2025.100481","volume":"9","author":"Y Wang","year":"2025","unstructured":"Wang Y, Huang J, Du L, Guo Y, Liu Y, Wang R. Evaluating large language models as raters in large-scale writing assessments: a psychometric framework for reliability and validity. Comput Educ Artif Intell. 2025;9:100481. https:\/\/doi.org\/10.1016\/J.CAEAI.2025.100481.","journal-title":"Comput Educ Artif Intell"},{"key":"3472_CR16","doi-asserted-by":"publisher","DOI":"10.3389\/FRAI.2025.1614874","author":"MEVC Souto","year":"2025","unstructured":"Souto MEVC, Fernandes AC, Silva ABS, de Freitas Ribeiro LH, de Medeiros Fernandes TAA. A multi-model longitudinal assessment of ChatGPT performance on medical residency examinations. Front Artif Intell. 2025. https:\/\/doi.org\/10.3389\/FRAI.2025.1614874.","journal-title":"Front Artif Intell"},{"key":"3472_CR17","doi-asserted-by":"publisher","DOI":"10.1038\/S41598-024-60405-Y","author":"H Shojaee-Mend","year":"2024","unstructured":"Shojaee-Mend H, Mohebbati R, Amiri M, Atarodi A. Evaluating the strengths and weaknesses of large language models in answering neurophysiology questions. Sci Rep. 2024. https:\/\/doi.org\/10.1038\/S41598-024-60405-Y.","journal-title":"Sci Rep"},{"key":"3472_CR18","doi-asserted-by":"publisher","DOI":"10.1186\/S12909-025-06796-6","author":"AKK Law","year":"2025","unstructured":"Law AKK, So J, Lui CT, Choi YF, Cheung KH, Kei-ching Hung K, et al. AI versus human-generated multiple-choice questions for medical education: a cohort study in a high-stakes examination. BMC Med Educ. 2025. https:\/\/doi.org\/10.1186\/S12909-025-06796-6.","journal-title":"BMC Med Educ"},{"key":"3472_CR19","doi-asserted-by":"publisher","DOI":"10.1148\/RADIOL.240609","author":"P Mukherjee","year":"2023","unstructured":"Mukherjee P, Hou B, Suri A, Zhuang Y, Parnell C, Lee N, et al. Evaluation of GPT large language model performance on RSNA 2023 case of the day questions. Radiology. 2023. https:\/\/doi.org\/10.1148\/RADIOL.240609.","journal-title":"Radiology"},{"key":"3472_CR20","doi-asserted-by":"publisher","unstructured":"Nakaura T, Uetani H, Yoshida N, Kobayashi N, Nagayama Y, Kidoh M, et al. Intra-axial primary brain tumor differentiation: comparing large language models on structured MRI reports vs. radiologists on images. European Radiology 2025 [Internet]. Springer; 2025. pp. 1\u201311. https:\/\/doi.org\/10.1007\/S00330-025-11924-3.","DOI":"10.1007\/S00330-025-11924-3"}],"container-title":["Surgery Today"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00595-026-03472-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00595-026-03472-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00595-026-03472-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:37:12Z","timestamp":1787657832000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00595-026-03472-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":20,"alternative-id":["3472"],"URL":"https:\/\/doi.org\/10.1007\/s00595-026-03472-0","relation":{"references":[{"id-type":"doi","id":"10.1001\/JAMASURG.2024.1621","asserted-by":"subject"}]},"ISSN":["0941-1291","1436-2813"],"issn-type":[{"value":"0941-1291","type":"print"},{"value":"1436-2813","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]},"assertion":[{"value":"13 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Takeshi Nakaura received research funding from Nemoto Kyorindo Co., Ltd. The other authors declare no conflicts of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}]}}