{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T09:35:58Z","timestamp":1793352958443,"version":"4.5.0"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20230301"],"award-info":[{"award-number":["GZC20230301"]}]},{"name":"CAMS Innovation Fund for Medical Science","award":["2024-I2M-C&T-B-023"],"award-info":[{"award-number":["2024-I2M-C&T-B-023"]}]},{"name":"Beijing Natural Science Foundation","award":["L258065"],"award-info":[{"award-number":["L258065"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Urol"],"DOI":"10.1186\/s12894-026-02228-9","type":"journal-article","created":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T08:16:03Z","timestamp":1781943363000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Evaluation of ChatGPT-4o\u2019s and DeepSeek R1\u2019s responses to urological problems: a comparative study"],"prefix":"10.1186","volume":"26","author":[{"given":"Hanbo","family":"Lu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusa","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxu","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yushi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"2228_CR1","doi-asserted-by":"publisher","first-page":"e58158","DOI":"10.2196\/58158","volume":"26","author":"X Chen","year":"2024","unstructured":"Chen X, Wang L, You M, Liu W, Fu Y, Xu J, et al. Evaluating and Enhancing Large Language Models\u2019 Performance in Domain-Specific Medicine: Development and Usability Study With DocOA. J Med Internet Res. 2024;26:e58158.","journal-title":"J Med Internet Res"},{"issue":"4","key":"2228_CR2","doi-asserted-by":"publisher","first-page":"688","DOI":"10.1097\/JU.0000000000003615","volume":"210","author":"R Davis","year":"2023","unstructured":"Davis R, Eppler M, Ayo-Ajibola O, Loh-Doyle JC, Nabhani J, Samplaski M, et al. Evaluating the Effectiveness of Artificial Intelligence-powered Large Language Models Application in Disseminating Appropriate and Readable Health Information in Urology. J Urol. 2023;210(4):688\u201394.","journal-title":"J Urol"},{"issue":"2","key":"2228_CR3","doi-asserted-by":"publisher","first-page":"e0000198","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, Elepano 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.","journal-title":"PLOS Digit Health"},{"key":"2228_CR4","doi-asserted-by":"publisher","first-page":"e64284","DOI":"10.2196\/64284","volume":"11","author":"B Wei","year":"2025","unstructured":"Wei B. Performance Evaluation and Implications of Large Language Models in Radiology Board Exams: Prospective Comparative Analysis. JMIR Med Educ. 2025;11:e64284.","journal-title":"JMIR Med Educ"},{"issue":"1","key":"2228_CR5","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1186\/s12909-025-07896-z","volume":"25","author":"EC Ceki\u0307c","year":"2025","unstructured":"Ceki\u0307c EC, Tavsan O. Evaluating large language models using national endodontic specialty examination questions: are they ready for real-world dentistry? BMC Med Educ. 2025;25(1):1308.","journal-title":"BMC Med Educ"},{"issue":"3","key":"2228_CR7","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.","journal-title":"Nat Med"},{"issue":"8","key":"2228_CR8","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.","journal-title":"Nat Med"},{"key":"2228_CR9","doi-asserted-by":"publisher","first-page":"e63430","DOI":"10.2196\/63430","volume":"10","author":"BT Bicknell","year":"2024","unstructured":"Bicknell BT, Butler D, Whalen S, Ricks J, Dixon CJ, Clark AB, et al. ChatGPT-4 Omni Performance in USMLE Disciplines and Clinical Skills: Comparative Analysis. JMIR Med Educ. 2024;10:e63430.","journal-title":"JMIR Med Educ"},{"issue":"2","key":"2228_CR10","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1213\/ANE.0000000000006892","volume":"139","author":"MC Angel","year":"2024","unstructured":"Angel MC, Rinehart JB, Cannesson MP, Baldi P. Clinical Knowledge and Reasoning Abilities of AI Large Language Models in Anesthesiology: A Comparative Study on the American Board of Anesthesiology Examination. Anesth Analg. 2024;139(2):349\u201356.","journal-title":"Anesth Analg"},{"key":"2228_CR11","doi-asserted-by":"publisher","first-page":"e48002","DOI":"10.2196\/48002","volume":"9","author":"S Takagi","year":"2023","unstructured":"Takagi S, Watari T, Erabi A, Sakaguchi K. Performance of GPT-3.5 and GPT-4 on the Japanese Medical Licensing Examination: Comparison Study. JMIR Med Educ. 2023;9:e48002.","journal-title":"JMIR Med Educ"},{"key":"2228_CR12","doi-asserted-by":"publisher","first-page":"e52784","DOI":"10.2196\/52784","volume":"10","author":"S Ming","year":"2024","unstructured":"Ming S, Guo Q, Cheng W, Lei B. Influence of Model Evolution and System Roles on ChatGPT\u2019s Performance in Chinese Medical Licensing Exams: Comparative Study. JMIR Med Educ. 2024;10:e52784.","journal-title":"JMIR Med Educ"},{"issue":"2","key":"2228_CR13","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, Jiang JW, Huo XY, Chen ZL, 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.","journal-title":"Am J Clin Exp Urol"},{"issue":"1","key":"2228_CR14","doi-asserted-by":"publisher","first-page":"8384","DOI":"10.1038\/s41467-024-52417-z","volume":"15","author":"P Qiu","year":"2024","unstructured":"Qiu P, Wu C, Zhang X, Lin W, Wang H, Zhang Y, et al. Towards building multilingual language model for medicine. Nat Commun. 2024;15(1):8384.","journal-title":"Nat Commun"},{"key":"2228_CR15","doi-asserted-by":"publisher","first-page":"104791","DOI":"10.1016\/j.jbi.2025.104791","volume":"163","author":"Y Peng","year":"2025","unstructured":"Peng Y, Malin BA, Rousseau JF, Wang Y, Xu Z, Xu X, et al. From GPT to DeepSeek: Significant gaps remain in realizing AI in healthcare. J Biomed Inf. 2025;163:104791.","journal-title":"J Biomed Inf"},{"issue":"4","key":"2228_CR16","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1001\/jama.2024.21700","volume":"333","author":"S Bedi","year":"2025","unstructured":"Bedi S, Liu Y, Orr-Ewing L, Dash D, Koyejo S, Callahan A, et al. Testing and Evaluation of Health Care Applications of Large Language Models: A Systematic Review. JAMA. 2025;333(4):319\u201328.","journal-title":"JAMA"},{"key":"2228_CR17","doi-asserted-by":"crossref","unstructured":"Lievin V, Hother CE, Motzfeldt AG, Winther O. Can large language models reason about medical questions? Patterns (N Y). 2024;5(3):100943.","DOI":"10.1016\/j.patter.2024.100943"},{"issue":"1","key":"2228_CR18","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1038\/s41746-025-01780-2","volume":"8","author":"M Zhu","year":"2025","unstructured":"Zhu M, Lin H, Jiang J, Jinia AJ, Jee J, Pichotta K, et al. Large language model trained on clinical oncology data predicts cancer progression. NPJ Digit Med. 2025;8(1):397.","journal-title":"NPJ Digit Med"},{"issue":"10","key":"2228_CR19","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1016\/j.jacr.2023.05.003","volume":"20","author":"A Rao","year":"2023","unstructured":"Rao A, Kim J, Kamineni M, Pang M, Lie W, Dreyer KJ, et al. Evaluating GPT as an Adjunct for Radiologic Decision Making: GPT-4 Versus GPT-3.5 in a Breast Imaging Pilot. J Am Coll Radiol. 2023;20(10):990\u20137.","journal-title":"J Am Coll Radiol"},{"issue":"1","key":"2228_CR20","doi-asserted-by":"publisher","first-page":"20512","DOI":"10.1038\/s41598-023-46995-z","volume":"13","author":"M Rosol","year":"2023","unstructured":"Rosol M, Gasior JS, Laba J, Korzeniewski K, Mlynczak M. Evaluation of the performance of GPT-3.5 and GPT-4 on the Polish Medical Final Examination. Sci Rep. 2023;13(1):20512.","journal-title":"Sci Rep"},{"issue":"1","key":"2228_CR21","doi-asserted-by":"publisher","first-page":"e427","DOI":"10.1002\/bco2.427","volume":"6","author":"H Collin","year":"2025","unstructured":"Collin H, Roberts MJ, Keogh K, Siriwardana A, Basto M. Improving clinical efficiency using retrieval-augmented generation in urologic oncology: A guideline-enhanced artificial intelligence approach. BJUI Compass. 2025;6(1):e427.","journal-title":"BJUI Compass"},{"issue":"1","key":"2228_CR23","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s10916-025-02213-z","volume":"49","author":"J Wu","year":"2025","unstructured":"Wu J, Wang Z, Qin Y. Performance of DeepSeek-R1 and ChatGPT-4o on the Chinese National Medical Licensing Examination: A Comparative Study. J Med Syst. 2025;49(1):74.","journal-title":"J Med Syst"},{"issue":"1","key":"2228_CR24","doi-asserted-by":"publisher","first-page":"e0000433","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.","journal-title":"PLOS Digit Health"},{"issue":"1","key":"2228_CR25","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.1186\/s12903-025-07035-6","volume":"25","author":"I Sozen Yanik","year":"2025","unstructured":"Sozen Yanik I, Sahin Hazir D, Bilgin Avsar D. Cross-lingual performance of large language models in maxillofacial prosthodontics: a comparative evaluation. BMC Oral Health. 2025;25(1):1630.","journal-title":"BMC Oral Health"},{"key":"2228_CR26","doi-asserted-by":"publisher","first-page":"101730","DOI":"10.1016\/j.artd.2025.101730","volume":"33","author":"S Gurbuz","year":"2025","unstructured":"Gurbuz S, Bahar H, Yavuz U, Keskin A, Karslioglu B, Solak Y. Comparative Efficacy of ChatGPT and DeepSeek in Addressing Patient Queries on Gonarthrosis and Total Knee Arthroplasty. Arthroplast Today. 2025;33:101730.","journal-title":"Arthroplast Today"},{"issue":"1","key":"2228_CR27","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1038\/s41746-024-01083-y","volume":"7","author":"N Mehandru","year":"2024","unstructured":"Mehandru N, Miao BY, Almaraz ER, Sushil M, Butte AJ, Alaa A. Evaluating large language models as agents in the clinic. NPJ Digit Med. 2024;7(1):84.","journal-title":"NPJ Digit Med"},{"issue":"1","key":"2228_CR28","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1038\/s41746-025-01670-7","volume":"8","author":"E Asgari","year":"2025","unstructured":"Asgari E, Montana-Brown N, Dubois M, Khalil S, Balloch J, Yeung JA, et al. A framework to assess clinical safety and hallucination rates of LLMs for medical text summarisation. NPJ Digit Med. 2025;8(1):274.","journal-title":"NPJ Digit Med"},{"issue":"1","key":"2228_CR29","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","volume":"31","author":"J Gallifant","year":"2025","unstructured":"Gallifant J, Afshar M, Ameen S, Aphinyanaphongs Y, Chen S, Cacciamani G, et al. The TRIPOD-LLM reporting guideline for studies using large language models. Nat Med. 2025;31(1):60\u20139.","journal-title":"Nat Med"},{"issue":"10","key":"2228_CR30","doi-asserted-by":"publisher","first-page":"e0333411","DOI":"10.1371\/journal.pone.0333411","volume":"20","author":"X Li","year":"2025","unstructured":"Li X, Yan X, Lai H. The ethical challenges in the integration of artificial intelligence and large language models in medical education: A scoping review. PLoS ONE. 2025;20(10):e0333411.","journal-title":"PLoS ONE"},{"issue":"1","key":"2228_CR31","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/s12910-025-01243-z","volume":"26","author":"SC Nouis","year":"2025","unstructured":"Nouis SC, Uren V, Jariwala S. Evaluating accountability, transparency, and bias in AI-assisted healthcare decision- making: a qualitative study of healthcare professionals\u2019 perspectives in the UK. BMC Med Ethics. 2025;26(1):89.","journal-title":"BMC Med Ethics"},{"issue":"1","key":"2228_CR32","doi-asserted-by":"publisher","first-page":"30794","DOI":"10.1038\/s41598-024-81052-3","volume":"14","author":"R Xu","year":"2024","unstructured":"Xu R, Hong Y, Zhang F, Xu H. Evaluation of the integration of retrieval-augmented generation in large language model for breast cancer nursing care responses. Sci Rep. 2024;14(1):30794.","journal-title":"Sci Rep"},{"issue":"4","key":"2228_CR33","doi-asserted-by":"publisher","first-page":"104667","DOI":"10.1016\/j.amjoto.2025.104667","volume":"46","author":"S Prasad","year":"2025","unstructured":"Prasad S, Langlie J, Pasick L, Chen R, Franzmann E. 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.","journal-title":"Am J Otolaryngol"}],"container-title":["BMC Urology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12894-026-02228-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12894-026-02228-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12894-026-02228-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T21:01:54Z","timestamp":1790370114000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12894-026-02228-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2228"],"URL":"https:\/\/doi.org\/10.1186\/s12894-026-02228-9","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-9012062\/v1","asserted-by":"object"}]},"ISSN":["1471-2490"],"issn-type":[{"value":"1471-2490","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 September 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The original online version of this article was revised: The affiliation for the corresponding author, Dongxing Qiu, was incorrect and has now been updated.","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable. This study did not involve human participants, human data, human tissue, animal experiments, patient records, medical images, or identifiable personal information. The analysis was based solely on pre-existing urology examination questions used for educational assessment and responses generated by large language models. No individual-level data from examinees, patients, clinicians, or platform users were collected, processed, or analyzed. Therefore, ethics approval and informed consent were not required.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"212"}}