{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T13:38:11Z","timestamp":1781703491334,"version":"3.54.5"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Sun Yat-sen University Undergraduate Teaching Quality Project","award":["2024"],"award-info":[{"award-number":["2024"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Educ"],"DOI":"10.1186\/s12909-025-08184-6","type":"journal-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T16:18:53Z","timestamp":1762877933000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["DeepSeek-R1 for automated scoring in radiology residency examinations: an agreement and test\u2013retest reliability study"],"prefix":"10.1186","volume":"25","author":[{"given":"Shanshan","family":"Niu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaobin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanfang","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"issue":"1","key":"8184_CR1","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1186\/s12903-025-06034-x","volume":"25","author":"\u00d6F Kaygisiz","year":"2025","unstructured":"Kaygisiz \u00d6F, Teke MT. Can deepseek and ChatGPT be used in the diagnosis of oral pathologies? BMC Oral Health. 2025;25(1):638. https:\/\/doi.org\/10.1186\/s12903-025-06034-x.","journal-title":"BMC Oral Health"},{"issue":"16","key":"8184_CR2","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1001\/jama.2023.5321","volume":"329","author":"CE Haupt","year":"2023","unstructured":"Haupt CE, Marks M. AI-Generated medical Advice-GPT and beyond. JAMA. 2023;329(16):1349\u201350. https:\/\/doi.org\/10.1001\/jama.2023.5321.","journal-title":"JAMA"},{"issue":"2","key":"8184_CR3","doi-asserted-by":"publisher","first-page":"e79221","DOI":"10.7759\/cureus.79221","volume":"17","author":"A Temsah","year":"2025","unstructured":"Temsah A, Alhasan K, Altamimi I, et al. DeepSeek in healthcare: revealing opportunities and steering challenges of a new Open-Source artificial intelligence frontier. Cureus. 2025;17(2):e79221. https:\/\/doi.org\/10.7759\/cureus.79221.","journal-title":"Cureus"},{"key":"8184_CR4","doi-asserted-by":"publisher","first-page":"105871","DOI":"10.1016\/j.ijmedinf.2025.105871","volume":"198","author":"M Zhou","year":"2025","unstructured":"Zhou M, Pan Y, Zhang Y, et al. Evaluating AI-generated patient education materials for spinal surgeries: comparative analysis of readability and DISCERN quality across ChatGPT and deepseek models. Int J Med Inf. 2025;198:105871. https:\/\/doi.org\/10.1016\/j.ijmedinf.2025.105871.","journal-title":"Int J Med Inf"},{"issue":"8","key":"8184_CR5","doi-asserted-by":"publisher","first-page":"2546","DOI":"10.1038\/s41591-025-03727-2","volume":"31","author":"S Sandmann","year":"2025","unstructured":"Sandmann S, Hegselmann S, Fujarski M, et al. Benchmark evaluation of deepseek large Language models in clinical decision-making. Nat Med. 2025;31(8):2546\u20139. https:\/\/doi.org\/10.1038\/s41591-025-03727-2.","journal-title":"Nat Med"},{"issue":"8","key":"8184_CR6","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","volume":"31","author":"M Tordjman","year":"2025","unstructured":"Tordjman M, Liu Z, Yuce M, et al. Comparative benchmarking of the deepseek large Language model on medical tasks and clinical reasoning. Nat Med. 2025;31(8):2550\u20135. https:\/\/doi.org\/10.1038\/s41591-025-03726-3.","journal-title":"Nat Med"},{"issue":"1","key":"8184_CR7","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1186\/s12903-025-06267-w","volume":"25","author":"T \u00d6zcivelek","year":"2025","unstructured":"\u00d6zcivelek T, \u00d6zcan B. Comparative evaluation of responses from DeepSeek-R1, ChatGPT-o1, ChatGPT-4, and dental GPT chatbots to patient inquiries about dental and maxillofacial prostheses. BMC Oral Health. 2025;25(1):871. https:\/\/doi.org\/10.1186\/s12903-025-06267-w.","journal-title":"BMC Oral Health"},{"key":"8184_CR8","doi-asserted-by":"publisher","unstructured":"Dincer HA, Dogu D. Evaluating artificial intelligence in patient education: DeepSeek-V3 versus ChatGPT-4o in answering common questions on laparoscopic cholecystectomy. ANZ J Surg. 2025;11. https:\/\/doi.org\/10.1111\/ans.70198.","DOI":"10.1111\/ans.70198"},{"issue":"1","key":"8184_CR9","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s13054-025-05468-7","volume":"29","author":"X Wu","year":"2025","unstructured":"Wu X, Huang Y, He Q. A large Language model improves clinicians\u2019 diagnostic performance in complex critical illness cases. Crit Care. 2025;29(1):230. https:\/\/doi.org\/10.1186\/s13054-025-05468-7.","journal-title":"Crit Care"},{"issue":"6","key":"8184_CR10","doi-asserted-by":"publisher","first-page":"4056","DOI":"10.1097\/JS9.000000000000238","volume":"111","author":"L Chan","year":"2025","unstructured":"Chan L, Xu X, Lv K. DeepSeek-R1 and GPT-4 are comparable in a complex diagnostic challenge: a historical control study. Int J Surg. 2025;111(6):4056\u20139. https:\/\/doi.org\/10.1097\/JS9.000000000000238.","journal-title":"Int J Surg"},{"issue":"2","key":"8184_CR11","doi-asserted-by":"publisher","first-page":"176","DOI":"10.62347\/UIAP7979","volume":"13","author":"PW Luo","year":"2025","unstructured":"Luo PW, Liu JW, Xie X, et al. DeepSeek vs chatgpt: a comparison study of their performance in answering prostate cancer radiotherapy questions in multiple languages. Am J Clin Exp Urol. 2025;13(2):176\u201385. https:\/\/doi.org\/10.62347\/UIAP7979.","journal-title":"Am J Clin Exp Urol"},{"key":"8184_CR12","doi-asserted-by":"publisher","first-page":"2139","DOI":"10.1016\/j.csbj.2025.05.019","volume":"27","author":"D Spitzl","year":"2025","unstructured":"Spitzl D, Mergen M, Bauer U, et al. Leveraging large Language models for accurate classification of liver lesions from MRI reports. Comput Struct Biotechnol J. 2025;27:2139\u201346. https:\/\/doi.org\/10.1016\/j.csbj.2025.05.019.","journal-title":"Comput Struct Biotechnol J"},{"issue":"9","key":"8184_CR13","doi-asserted-by":"publisher","first-page":"5970","DOI":"10.1097\/JS9.0000000000002763","volume":"111","author":"J Zhang","year":"2025","unstructured":"Zhang J, Liu J, Guo M, et al. DeepSeek-assisted LI-RADS classification: AI-driven precision in hepatocellular carcinoma diagnosis. Int J Surg. 2025;111(9):5970\u20139. https:\/\/doi.org\/10.1097\/JS9.0000000000002763.","journal-title":"Int J Surg"},{"issue":"3","key":"8184_CR14","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.aopr.2025.05.001","volume":"5","author":"P Xu","year":"2025","unstructured":"Xu P, Wu Y, Jin K, et al. DeepSeek-R1 outperforms gemini 2.0 Pro, openai o1, and o3-mini in bilingual complex ophthalmology reasoning. Adv Ophthalmol Pract Res. 2025;5(3):189\u201395. https:\/\/doi.org\/10.1016\/j.aopr.2025.05.001.","journal-title":"Adv Ophthalmol Pract Res"},{"issue":"1","key":"8184_CR15","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1186\/s12909-025-07195-7","volume":"25","author":"S Ramlogan","year":"2025","unstructured":"Ramlogan S, Raman V, Ramlogan S. A pilot study of the performance of chat GPT and other large Language models on a written final year periodontology exam. BMC Med Educ. 2025;25(1):727. https:\/\/doi.org\/10.1186\/s12909-025-07195-7.","journal-title":"BMC Med Educ"},{"issue":"1","key":"8184_CR16","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1186\/s12909-025-07493-0","volume":"25","author":"F Temizsoy Korkmaz","year":"2025","unstructured":"Temizsoy Korkmaz F, Ok F, Karip B, et al. A structured evaluation of LLM-generated step-by-step instructions in cadaveric brachial plexus dissection. BMC Med Educ. 2025;25(1):903. https:\/\/doi.org\/10.1186\/s12909-025-07493-0.","journal-title":"BMC Med Educ"},{"key":"8184_CR17","doi-asserted-by":"publisher","unstructured":"Prasad S, Langlie J, Pasick L, et al. Evaluating advanced AI reasoning models: ChatGPT-4.0 and DeepSeek-R1 diagnostic performance in otolaryngology: a comparative analysis. Am J Otolaryngol. 2025;46(4):104667. https:\/\/doi.org\/10.1016\/j.amjoto.2025.104667.","DOI":"10.1016\/j.amjoto.2025.104667"},{"issue":"3","key":"8184_CR18","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1001\/jamadermatol.2017.5890","volume":"154","author":"S Hessam","year":"2018","unstructured":"Hessam S, Scholl L, Sand M, et al. A novel severity assessment scoring system for hidradenitis suppurativa. JAMA Dermatol. 2018;154(3):330\u20135. https:\/\/doi.org\/10.1001\/jamadermatol.2017.5890.","journal-title":"JAMA Dermatol"},{"key":"8184_CR19","doi-asserted-by":"publisher","unstructured":"B\u00fcy\u00fcktoka RE, Surucu M, Erekli Derinkaya PB, et al. Applying large Language model for automated quality scoring of radiology requisitions using a standardized criteria. Eur Radiol. 2025;20. https:\/\/doi.org\/10.1007\/s00330-025-11933-2.","DOI":"10.1007\/s00330-025-11933-2"},{"issue":"1","key":"8184_CR20","doi-asserted-by":"publisher","first-page":"1146","DOI":"10.1186\/s12909-025-07718-2","volume":"25","author":"HMTW Seneviratne","year":"2025","unstructured":"Seneviratne HMTW, Manathunga SS. Artificial intelligence assisted automated short answer question scoring tool shows high correlation with human examiner markings. BMC Med Educ. 2025;25(1):1146. https:\/\/doi.org\/10.1186\/s12909-025-07718-2.","journal-title":"BMC Med Educ"},{"key":"8184_CR21","doi-asserted-by":"publisher","unstructured":"Runyon C. Using large Language models (LLMs) to apply analytic rubrics to score post-encounter notes. Med Teach 2025:1\u20139. https:\/\/doi.org\/10.1080\/0142159X.2025.2504106.","DOI":"10.1080\/0142159X.2025.2504106"}],"container-title":["BMC Medical Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-025-08184-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12909-025-08184-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-025-08184-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T16:18:53Z","timestamp":1762877933000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmededuc.biomedcentral.com\/articles\/10.1186\/s12909-025-08184-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"references-count":21,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["8184"],"URL":"https:\/\/doi.org\/10.1186\/s12909-025-08184-6","relation":{},"ISSN":["1472-6920"],"issn-type":[{"value":"1472-6920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"29 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 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":"Since the study did not encompass research involving human biological materials, it was granted an exemption from ethics approval by the Institutional Review Board of the Fifth Affiliated Hospital of Sun Yat-sen University.","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":"1581"}}