{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T23:06:24Z","timestamp":1793919984592,"version":"4.8.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T00:00:00Z","timestamp":1757721600000},"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":["Endocrine"],"DOI":"10.1007\/s12020-025-04421-6","type":"journal-article","created":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T09:34:41Z","timestamp":1757756081000},"page":"1332-1338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Evaluation of large language models in patient education for hyperthyroidism: A comparative study of chatgpt, gemini, and deepseek"],"prefix":"10.1007","volume":"90","author":[{"given":"Xin","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruhai","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinqiong","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiran","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huibin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,13]]},"reference":[{"issue":"5","key":"4421_CR1","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1038\/nrendo.2018.18","volume":"14","author":"PN Taylor","year":"2018","unstructured":"P.N. Taylor, D. Albrecht, A. Scholz, G. Gutierrez-Buey, J.H. Lazarus, C.M. Dayan, O.E. Okosieme, Global epidemiology of hyperthyroidism and hypothyroidism. Nat. Reviews Endocrinol. 14(5), 301\u2013316 (2018)","journal-title":"Nat. Reviews Endocrinol."},{"issue":"15","key":"4421_CR2","doi-asserted-by":"publisher","first-page":"1472","DOI":"10.1001\/jama.2023.19052","volume":"330","author":"SY Lee","year":"2023","unstructured":"S.Y. Lee, E.N. Pearce, Hyperthyroidism: A review. Jama. 330(15), 1472\u20131483 (2023)","journal-title":"Jama"},{"key":"4421_CR3","doi-asserted-by":"publisher","first-page":"e48568","DOI":"10.2196\/48568","volume":"25","author":"J Liu","year":"2023","unstructured":"J. Liu, C. Wang, S. Liu, Utility of ChatGPT in clinical practice. J. Med. Internet Res. 25, e48568 (2023)","journal-title":"J. Med. Internet Res."},{"issue":"6","key":"4421_CR4","first-page":"887","volume":"11","author":"M Sallam","year":"2023","unstructured":"M. Sallam, ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. Healthc. (Basel Switzerland) 11(6), 887 (2023)","journal-title":"Healthc. (Basel Switzerland)"},{"issue":"6","key":"4421_CR5","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1093\/jamia\/ocad258","volume":"31","author":"S Tripathi","year":"2024","unstructured":"S. Tripathi, R. Sukumaran, T.S. Cook, Efficient healthcare with large Language models: optimizing clinical workflow and enhancing patient care. J. Am. Med. Inf. Association: JAMIA 31(6), 1436\u20131440 (2024)","journal-title":"J. Am. Med. Inf. Association: JAMIA"},{"issue":"1","key":"4421_CR6","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1007\/s00345-024-05146-3","volume":"42","author":"D Pompili","year":"2024","unstructured":"D. Pompili, Y. Richa, P. Collins, H. Richards, D.B. Hennessey, Using artificial intelligence to generate medical literature for urology patients: a comparison of three different large Language models. World J. Urol. 42(1), 455 (2024)","journal-title":"World J. Urol."},{"issue":"8032","key":"4421_CR7","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/s41586-024-07930-y","volume":"634","author":"L Zhou","year":"2024","unstructured":"L. Zhou, W. Schellaert, F. Mart\u00ednez-Plumed, Y. Moros-Daval, C. Ferri, J. Hern\u00e1ndez-Orallo, Larger and more instructable Language models become less reliable. Nature. 634(8032), 61\u201368 (2024)","journal-title":"Nature"},{"issue":"1","key":"4421_CR8","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1016\/j.bja.2023.09.030","volume":"132","author":"SS Patnaik","year":"2024","unstructured":"S.S. Patnaik, U. Hoffmann, Quantitative evaluation of ChatGPT versus bard responses to anaesthesia-related queries. Br. J. Anaesth. 132(1), 169\u2013171 (2024)","journal-title":"Br. J. Anaesth."},{"issue":"12","key":"4421_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Z. Ji, N. Lee, R. Frieske, T. Yu, D. Su, Y. Xu, E. Ishii, Y.J. Bang, A. Madotto, P. Fung, Survey of hallucination in natural Language generation. ACM Comput. Surveys. 55(12), 1\u201338 (2023)","journal-title":"ACM Comput. Surveys"},{"issue":"4","key":"4421_CR10","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/s41433-023-02772-w","volume":"38","author":"O Kleinig","year":"2024","unstructured":"O. Kleinig, C. Gao, J.G. Kovoor, A.K. Gupta, S. Bacchi, W.O. Chan, How to use large Language models in ophthalmology: from prompt engineering to protecting confidentiality. Eye (London England). 38(4), 649\u2013653 (2024)","journal-title":"Eye (London England)"},{"issue":"1","key":"4421_CR11","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1177\/17085381241240550","volume":"33","author":"E Chervonski","year":"2025","unstructured":"E. Chervonski, K.B. Harish, C.B. Rockman, M. Sadek, K.A. Teter, G.R. Jacobowitz, T.L. Berland, J. Lohr, C. Moore, T.S. Maldonado, Generative artificial intelligence chatbots May provide appropriate informational responses to common vascular surgery questions by patients. VASCULAR. 33(1), 229\u2013237 (2025)","journal-title":"VASCULAR"},{"issue":"8","key":"4421_CR12","doi-asserted-by":"publisher","first-page":"928","DOI":"10.1001\/jamasurg.2024.1621","volume":"159","author":"P Chung","year":"2024","unstructured":"P. Chung, C.T. Fong, A.M. Walters, N. Aghaeepour, M. Yetisgen, V.N. O\u2019Reilly-Shah, Large Language model capabilities in perioperative risk prediction and prognostication. JAMA Surg. 159(8), 928\u2013937 (2024)","journal-title":"JAMA Surg."},{"issue":"1","key":"4421_CR13","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1038\/s41698-024-00733-4","volume":"8","author":"N Carl","year":"2024","unstructured":"N. Carl, F. Schramm, S. Haggenm\u00fcller, J.N. Kather, M.J. Hetz, C. Wies, M.S. Michel, F. Wessels, T.J. Brinker, Large Language model use in clinical oncology. NPJ Precision Oncol. 8(1), 240 (2024)","journal-title":"NPJ Precision Oncol."},{"issue":"17","key":"4421_CR14","doi-asserted-by":"publisher","first-page":"5101","DOI":"10.3390\/jcm13175101","volume":"13","author":"K Shah","year":"2024","unstructured":"K. Shah, A.Y. Xu, Y. Sharma, M. Daher, C. McDonald, B.G. Diebo, A.H. Daniels, Large Language model prompting techniques for advancement in clinical medicine. J. Clin. Med. 13(17), 5101 (2024)","journal-title":"J. Clin. Med."},{"issue":"3","key":"4421_CR15","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1007\/s00066-024-02342-3","volume":"201","author":"C Trapp","year":"2025","unstructured":"C. Trapp, N. Schmidt-Hegemann, M. Keilholz, S.F. Brose, S.N. Marschner, S. Sch\u00f6necker, S.H. Maier, D.C. Dehelean, M. Rottler, D. Konnerth et al., Patient- and clinician-based evaluation of large Language models for patient education in prostate cancer radiotherapy. Strahlentherapie Und Onkologie: Organ. Der Deutschen Rontgengesellschaft [et al]. 201(3), 333\u2013342 (2025)","journal-title":"Strahlentherapie Und Onkologie: Organ. Der Deutschen Rontgengesellschaft [et al]"},{"key":"4421_CR16","doi-asserted-by":"publisher","unstructured":"D. Guo, D. Yang, H. Zhang, J. Song, R. Zhang, R. Xu, Q. Zhu, S. Ma, P. Wang, X. Bi, Deepseek-r1: incentivizing reasoning capability in Llms via reinforcement learning. ArXiv Preprint arXiv:250112948 2025 https:\/\/doi.org\/10.48550\/arXiv.2501.12948","DOI":"10.48550\/arXiv.2501.12948"},{"issue":"16","key":"4421_CR17","doi-asserted-by":"publisher","first-page":"3113","DOI":"10.1038\/s41433-024-03231-w","volume":"38","author":"R Anguita","year":"2024","unstructured":"R. Anguita, C. Downie, L. Ferro Desideri, M.S. Sagoo, Assessing large Language models\u2019 accuracy in providing patient support for choroidal melanoma. Eye (London England). 38(16), 3113\u20133117 (2024)","journal-title":"Eye (London England)"},{"issue":"5","key":"4421_CR18","first-page":"e59960","volume":"16","author":"M Tepe","year":"2024","unstructured":"M. Tepe, E. Emekli, Assessing the responses of large Language models (ChatGPT-4, gemini, and Microsoft Copilot) to frequently asked questions in breast imaging: A study on readability and accuracy. Cureus. 16(5), e59960 (2024)","journal-title":"Cureus"},{"issue":"1","key":"4421_CR19","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/s10916-023-02021-3","volume":"47","author":"H Song","year":"2023","unstructured":"H. Song, Y. Xia, Z. Luo, H. Liu, Y. Song, X. Zeng, T. Li, G. Zhong, J. Li, M. Chen et al., Evaluating the performance of different large Language models on health consultation and patient education in urolithiasis. J. Med. Syst. 47(1), 125 (2023)","journal-title":"J. Med. Syst."},{"key":"4421_CR20","first-page":"358","volume":"253","author":"BD Weiss","year":"2003","unstructured":"B.D. Weiss, Health literacy. Am. Med. Assoc. 253, 358 (2003)","journal-title":"Am. Med. Assoc."},{"issue":"12","key":"4421_CR21","doi-asserted-by":"publisher","first-page":"2629","DOI":"10.1007\/s10439-023-03272-4","volume":"51","author":"L Giray","year":"2023","unstructured":"L. Giray, Prompt engineering with chatgpt: A guide for academic writers. Ann. Biomed. Eng. 51(12), 2629\u20132633 (2023)","journal-title":"Ann. Biomed. Eng"},{"issue":"6","key":"4421_CR22","first-page":"101260","volume":"6","author":"B Chen","year":"2025","unstructured":"B. Chen, Z. Zhang, N. Langren\u00e9, S. Zhu, Unleashing the potential of prompt engineering for large Language models. Patterns (New York NY). 6(6), 101260 (2025)","journal-title":"Patterns (New York NY)"},{"key":"4421_CR23","first-page":"478","volume":"2024","author":"X. Zhang","year":"2024","unstructured":"X. Zhang, N. Talukdar, S. Vemulapalli, S. Ahn, J. Wang, H. Meng, S.M. Bin Murtaza, D. Leshchiner, A.A. Dave, D.F. Joseph et al., Comparison of Prompt Engineering and Fine-Tuning Strategies in Large Language Models in the Classification of Clinical Notes. AMIA Joint Summits on Translational Science proceedings AMIA Joint Summits on Translational Science 2024, 2024, 478\u2013487","journal-title":"AMIA Joint Summits on Translational Science proceedings AMIA Joint Summits on Translational Science"},{"issue":"4","key":"4421_CR24","first-page":"586","volume":"43","author":"Y Sonoda","year":"2025","unstructured":"Y. Sonoda, R. Kurokawa, A. Hagiwara, Y. Asari, T. Fukushima, J. Kanzawa, W. Gonoi, O. Abe, Structured clinical reasoning prompt enhances llm\u2019s diagnostic capabilities in diagnosis please quiz cases. Japanese J. Radiol. 43(4), 586\u2013592 (2025)","journal-title":"Japanese J. Radiol."},{"issue":"1","key":"4421_CR25","doi-asserted-by":"publisher","first-page":"17341","DOI":"10.1038\/s41598-024-66933-x","volume":"14","author":"D Patel","year":"2024","unstructured":"D. Patel, G. Raut, E. Zimlichman, S.N. Cheetirala, G.N. Nadkarni, B.S. Glicksberg, D.U. Apakama, E.J. Bell, R. Freeman, P. Timsina et al., Evaluating prompt engineering on GPT-3.5\u2019s performance in USMLE-style medical calculations and clinical scenarios generated by GPT-4. Sci. Rep. 14(1), 17341 (2024)","journal-title":"Sci. Rep."},{"issue":"3","key":"4421_CR26","doi-asserted-by":"publisher","first-page":"509","DOI":"10.1007\/s00296-023-05473-5","volume":"44","author":"BN Coskun","year":"2024","unstructured":"B.N. Coskun, B. Yagiz, G. Ocakoglu, E. Dalkilic, Y. Pehlivan, Assessing the accuracy and completeness of artificial intelligence Language models in providing information on methotrexate use. Rheumatol. Int. 44(3), 509\u2013515 (2024)","journal-title":"Rheumatol. Int."},{"issue":"2","key":"4421_CR27","first-page":"e79221","volume":"17","author":"A Temsah","year":"2025","unstructured":"A. Temsah, K. Alhasan, I. Altamimi, A. Jamal, A. Al-Eyadhy, K.H. Malki, M.H. Temsah, DeepSeek in healthcare: revealing opportunities and steering challenges of a new Open-Source artificial intelligence frontier. Cureus. 17(2), e79221 (2025)","journal-title":"Cureus"}],"container-title":["Endocrine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12020-025-04421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12020-025-04421-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12020-025-04421-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T18:02:42Z","timestamp":1765908162000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12020-025-04421-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,13]]},"references-count":27,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["4421"],"URL":"https:\/\/doi.org\/10.1007\/s12020-025-04421-6","relation":{},"ISSN":["1559-0100"],"issn-type":[{"value":"1559-0100","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,13]]},"assertion":[{"value":"16 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 September 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 September 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study did not involve human or animal experiments. Therefore, ethics committee approval was not required.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}