{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:48:20Z","timestamp":1791571700553,"version":"4.3.4"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"National Natural Science Foundation of China and Natural Science Foundation of Beijing, China"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-55656-w","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T23:12:47Z","timestamp":1780701167000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A comparative study of large language models (ChatGPT\/DeepSeek) in generating structured thyroid ultrasound reports"],"prefix":"10.1038","volume":"16","author":[{"given":"Li","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xue","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huiyu","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"issue":"1","key":"55656_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/RUQ.0000000000000447","volume":"36","author":"SD O\u2019Connor","year":"2020","unstructured":"O\u2019Connor, S. D. et al. Structured Reporting in Ultrasound. Ultrasound Q. 36 (1), 1\u20135 (2020).","journal-title":"Ultrasound Q."},{"issue":"21","key":"55656_CR2","doi-asserted-by":"publisher","first-page":"5463","DOI":"10.1158\/0008-5472.CAN-19-0579","volume":"79","author":"GK Savova","year":"2019","unstructured":"Savova, G. K. et al. Use of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical Records. Cancer Res. 79 (21), 5463\u20135470 (2019).","journal-title":"Cancer Res."},{"key":"55656_CR3","doi-asserted-by":"crossref","unstructured":"The Lancet Digital H. Large language models: a new chapter in digital health. Lancet Digit. Health ;6(1). (2024).","DOI":"10.1016\/S2589-7500(23)00254-6"},{"issue":"1","key":"55656_CR4","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1177\/08465371231171125","volume":"75","author":"MW Wagner","year":"2023","unstructured":"Wagner, M. W. & Ertl-Wagner, B. B. Accuracy of Information and References Using ChatGPT-3 for Retrieval of Clinical Radiological Information. Can. Assoc. Radiol. J. 75 (1), 69\u201373 (2023).","journal-title":"Can. Assoc. Radiol. J."},{"issue":"7944","key":"55656_CR5","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1038\/d41586-023-00056-7","volume":"613","author":"H Else","year":"2023","unstructured":"Else, H. Abstracts written by ChatGPT fool scientists. Nature 613 (7944), 423 (2023).","journal-title":"Nature"},{"issue":"3","key":"55656_CR6","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1016\/j.urolonc.2019.11.002","volume":"38","author":"K Ginsburg","year":"2020","unstructured":"Ginsburg, K. et al. Should all prostate needle biopsy Gleason score 4\u2009+\u20094\u2009=\u20098 prostate cancers be high risk? Implications for shared decision-making and patient counselling. Urologic Oncology: Seminars Original Investigations. 38 (3), 78 (2020).","journal-title":"Urologic Oncology: Seminars Original Investigations"},{"issue":"3","key":"55656_CR7","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1038\/s41571-018-0116-x","volume":"16","author":"LM Lowenstein","year":"2018","unstructured":"Lowenstein, L. M. et al. Active surveillance for prostate and thyroid cancers: evolution in clinical paradigms and lessons learned. Nat. Reviews Clin. Oncol. 16 (3), 168\u2013184 (2018).","journal-title":"Nat. Reviews Clin. Oncol."},{"issue":"4","key":"55656_CR8","doi-asserted-by":"publisher","first-page":"e230725","DOI":"10.1148\/radiol.230725","volume":"307","author":"LC Adams","year":"2023","unstructured":"Adams, L. C. et al. Leveraging GPT-4 for Post Hoc Transformation of Free-Text Radiology Reports into Structured Reporting: A Multilingual Feasibility Study. radiology 307 (4), e230725 (2023).","journal-title":"radiology"},{"issue":"1","key":"55656_CR9","doi-asserted-by":"publisher","first-page":"e232133","DOI":"10.1148\/radiol.232133","volume":"311","author":"A Cozzi","year":"2024","unstructured":"Cozzi, A. et al. BI-RADS Category Assignments by GPT-3.5, GPT-4, and Google Bard: A Multilanguage Study. Radiology 311 (1), e232133 (2024).","journal-title":"Radiology"},{"key":"55656_CR10","doi-asserted-by":"publisher","first-page":"111458","DOI":"10.1016\/j.ejrad.2024.111458","volume":"175","author":"H Jiang","year":"2024","unstructured":"Jiang, H. et al. Transforming free-text radiology reports into structured reports using ChatGPT: A study on thyroid ultrasonography. Eur. J. Radiol. 175, 111458 (2024).","journal-title":"Eur. J. Radiol."},{"key":"55656_CR11","unstructured":"Guo, D. et al. Deepseek-R1: Incentivizing reasoning capability in llms via reinforcement learning. ; arXiv preprint arXiv:2501:12948. (2025)."},{"issue":"5","key":"55656_CR12","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.jacr.2017.01.046","volume":"14","author":"FN Tessler","year":"2017","unstructured":"Tessler, F. N. et al. ACR Thyroid Imaging, Reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J. Am. Coll. Radiol. 14 (5), 587\u2013595 (2017).","journal-title":"J. Am. Coll. Radiol."},{"issue":"2","key":"55656_CR13","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/s12020-020-02441-y","volume":"70","author":"J Zhou","year":"2020","unstructured":"Zhou, J. et al. 2020 Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS. Endocrine 70 (2), 256\u2013279 (2020).","journal-title":"Endocrine"},{"issue":"1","key":"55656_CR14","first-page":"33","volume":"12","author":"MJ Shi","year":"2025","unstructured":"Shi, M. J. et al. Performance of GPT-4 for automated prostate biopsy decision-making based on mpMRI: a multi-center evidence study. Mil Med. Res. 12 (1), 33 (2025).","journal-title":"Mil Med. Res."},{"key":"55656_CR15","unstructured":"Kohavi, R. A study of cross-validation and bootstrap for accuracy estimation and model selection. International joint conference on Artificial intelligence. Morgan Kaufmann Publishers Inc. (1995)."},{"issue":"3","key":"55656_CR16","doi-asserted-by":"publisher","first-page":"e231362","DOI":"10.1148\/radiol.231362","volume":"308","author":"MA Fink","year":"2023","unstructured":"Fink, M. A. et al. Potential of ChatGPT and GPT-4 for Data Mining of Free-Text CT Reports on Lung Cancer. Radiology 308 (3), e231362 (2023).","journal-title":"Radiology"},{"issue":"6","key":"55656_CR17","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1007\/s11695-023-06603-5","volume":"33","author":"JS Samaan","year":"2023","unstructured":"Samaan, J. S. et al. Assessing the Accuracy of Responses by the Language Model ChatGPT to Questions Regarding Bariatric Surgery. Obes. Surg. 33 (6), 1790\u20131796 (2023).","journal-title":"Obes. Surg."},{"issue":"Pt1","key":"55656_CR18","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","volume":"61","author":"KL Gwet","year":"2008","unstructured":"Gwet, K. L. Computing inter-rater reliability and its variance in the presence of high agreement. Br. J. Math. Stat. Psychol. 61 (Pt1), 29\u201348 (2008).","journal-title":"Br. J. Math. Stat. Psychol."},{"issue":"4","key":"55656_CR19","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1177\/1536867X1801800408","volume":"18","author":"D Klein","year":"2018","unstructured":"Klein, D. Implementing a general framework for assessing interrater agreement in Stata. Stata J. 18 (4), 871\u2013901 (2018).","journal-title":"Stata J."},{"issue":"1","key":"55656_CR20","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"J Landis","year":"1977","unstructured":"Landis, J. & Koch, G. The measurement of observer agreement for categorical data. Biometrics 33 (1), 159\u2013174 (1977).","journal-title":"Biometrics"},{"issue":"8","key":"55656_CR21","doi-asserted-by":"publisher","first-page":"2550","DOI":"10.1038\/s41591-025-03726-3","volume":"31","author":"M Tordjman","year":"2025","unstructured":"Tordjman, M. et al. Comparative benchmarking of the DeepSeek large language model on medical tasks and clinical reasoning. Nat. Med. 31 (8), 2550\u20132555 (2025).","journal-title":"Nat. Med."},{"issue":"12","key":"55656_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3571730","volume":"55","author":"Z Ji","year":"2023","unstructured":"Ji, Z. et al. Survey of Hallucination in Natural Language Generation. ACM Comput. Surv. 55 (12), 1\u201338 (2023).","journal-title":"ACM Comput. Surv."},{"issue":"6","key":"55656_CR23","doi-asserted-by":"publisher","first-page":"e2431696","DOI":"10.2214\/AJR.24.31696","volume":"223","author":"JE Lee","year":"2024","unstructured":"Lee, J. E., Park, K. S. & Kim, Y. H. Lung Cancer Staging Using Chest CT and FDG PET\/CT Free-Text Reports: Comparison Among Three ChatGPT Large Language Models and Six Human Readers of Varying Experience. AJR Am. J. Roentgenol. 223 (6), e2431696 (2024).","journal-title":"AJR Am. J. Roentgenol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55656-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55656-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55656-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T12:02:45Z","timestamp":1787054565000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-55656-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["55656"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-55656-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"17 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was performed in line with the principles of the Declaration of Helsinki. The approval of this study was from Beijing Chao-yang Hospital Medical Science Research Ethics Committee.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25784"}}