{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T06:28:05Z","timestamp":1793946485912,"version":"4.8.0"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Endocrine"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:sec>\n            <jats:title>Background<\/jats:title>\n            <jats:p>As ultrasound (US) is the most accurate tool for assessing the thyroid nodule (TN) risk of malignancy (RoM), international societies have published various Thyroid Imaging and Reporting Data Systems (TIRADSs). With the recent advent of artificial intelligence (AI), clinicians and researchers should ask themselves how AI could interpret the terminology of the TIRADSs and whether or not AIs agree in the risk assessment of TNs. The study aim was to analyze the interobserver agreement (IOA) between AIs in assessing the RoM of TNs across various TIRADSs categories using a cases series created combining TIRADSs descriptors.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Methods<\/jats:title>\n            <jats:p>ChatGPT, Google Gemini, and Claude were compared. ACR-TIRADS, EU-TIRADS, and K-TIRADS, were employed to evaluate the AI assessment. Multiple written scenarios for the three TIRADS were created, the cases were evaluated by the three AIs, and their assessments were analyzed and compared. The IOA was estimated by comparing the kappa (\u03ba) values.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Results<\/jats:title>\n            <jats:p>Ninety scenarios were created. With ACR-TIRADS the IOA analysis gave \u03ba\u2009=\u20090.58 between ChatGPT and Gemini, 0.53 between ChatGPT and Claude, and 0.90 between Gemini and Claude. With EU-TIRADS it was observed \u03ba value\u2009=\u20090.73 between ChatGPT and Gemini, 0.62 between ChatGPT and Claude, and 0.72 between Gemini and Claude. With K-TIRADS it was found \u03ba\u2009=\u20090.88 between ChatGPT and Gemini, 0.70 between ChatGPT and Claude, and 0.61 between Gemini and Claude.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>Conclusion<\/jats:title>\n            <jats:p>This study found that there were non-negligible variability between the three AIs. Clinicians and patients should be aware of these new findings.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1007\/s12020-025-04272-1","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T08:32:54Z","timestamp":1747297974000},"page":"197-201","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Interobserver agreement between artificial intelligence models in the thyroid imaging and reporting data system (TIRADS) assessment of thyroid nodules"],"prefix":"10.1007","volume":"89","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6466-7221","authenticated-orcid":false,"given":"Andrea","family":"Leoncini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2125-4937","authenticated-orcid":false,"given":"Pierpaolo","family":"Trimboli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"issue":"17","key":"4272_CR1","doi-asserted-by":"publisher","first-page":"1764","DOI":"10.1056\/NEJMcp031436","volume":"351","author":"L Heged\u00fcs","year":"2004","unstructured":"L. Heged\u00fcs, Clinical practice. The thyroid nodule. N. Engl. J. Med. 351(17), 1764\u20131771 (2004). https:\/\/doi.org\/10.1056\/NEJMcp031436.","journal-title":"N. Engl. J. Med."},{"issue":"5","key":"4272_CR2","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.jacr.2017.01.046","volume":"14","author":"FN Tessler","year":"2017","unstructured":"F.N. Tessler, W.D. Middleton, E.G. Grant, J.K. Hoang, L.L. Berland, S.A. Teefey, J.J. Cronan, M.D. Beland, T.S. Desser, M.C. Frates, L.W. Hammers, U.M. Hamper, J.E. Langer, C.C. Reading, L.M. Scoutt, A.T. Stavros, 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). https:\/\/doi.org\/10.1016\/j.jacr.2017.01.046.","journal-title":"J. Am. Coll. Radiol."},{"issue":"5","key":"4272_CR3","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1159\/000478927","volume":"6","author":"G Russ","year":"2017","unstructured":"G. Russ, S.J. Bonnema, M.F. Erdogan, C. Durante, R. Ngu, L. Leenhardt, European thyroid association guidelines for ultrasound malignancy risk stratification of thyroid nodules in adults: the EU-TIRADS. Eur. Thyroid. J. 6(5), 225\u2013237 (2017). https:\/\/doi.org\/10.1159\/000478927.","journal-title":"Eur. Thyroid. J."},{"issue":"12","key":"4272_CR4","doi-asserted-by":"publisher","first-page":"2094","DOI":"10.3348\/kjr.2021.0713","volume":"22","author":"EJ Ha","year":"2021","unstructured":"E.J. Ha, S.R. Chung, D.G. Na, H.S. Ahn, J. Chung, J.Y. Lee, J.S. Park, R.E. Yoo, J.H. Baek, S.M. Baek, S.W. Cho, Y.J. Choi, S.Y. Hahn, S.L. Jung, J.H. Kim, S.K. Kim, S.J. Kim, C.Y. Lee, H.K. Lee, J.H. Lee, M. Choi, 2021 Korean thyroid imaging reporting and data system and imaging-based management of thyroid nodules: Korean society of thyroid radiology consensus statement and recommendations. Korean J. Radiol. 22(12), 2094\u20132123 (2021). https:\/\/doi.org\/10.3348\/kjr.2021.0713.","journal-title":"Korean J. Radiol."},{"issue":"1","key":"4272_CR5","doi-asserted-by":"publisher","first-page":"e231481","DOI":"10.1148\/radiol.231481","volume":"309","author":"C Durante","year":"2023","unstructured":"C. Durante, L. Heged\u00fcs, D.G. Na, E. Papini, J.A. Sipos, J.H. Baek, A. Frasoldati, G. Grani, E. Grant, E. Horvath, J.K. Hoang, S.J. Mandel, W.D. Middleton, R. Ngu, L.A. Orloff, J.H. Shin, P. Trimboli, J.H. Yoon, F.N. Tessler, International expert consensus on US lexicon for thyroid nodules. Radiology 309(1), e231481 (2023). https:\/\/doi.org\/10.1148\/radiol.231481.","journal-title":"Radiology"},{"issue":"19","key":"4272_CR6","doi-asserted-by":"publisher","first-page":"4740","DOI":"10.3390\/cancers13194740","volume":"13","author":"F Bini","year":"2021","unstructured":"F. Bini, A. Pica, L. Azzimonti et al., Artificial intelligence in thyroid field-A comprehensive review. Cancers 13(19), 4740 (2021). https:\/\/doi.org\/10.3390\/cancers13194740.","journal-title":"Cancers"},{"issue":"2","key":"4272_CR7","doi-asserted-by":"publisher","first-page":"e230242","DOI":"10.1530\/ETJ-23-0242","volume":"13","author":"T Piticchio","year":"2024","unstructured":"T. Piticchio, G. Russ, M. Radzina, F. Frasca, C. Durante, P. Trimboli, Head-to-head comparison of American, European, and Asian TIRADSs in thyroid nodule assessment: systematic review and meta-analysis. Eur. Thyroid. J. 13(2), e230242 (2024). https:\/\/doi.org\/10.1530\/ETJ-23-0242.","journal-title":"Eur. Thyroid. J."},{"issue":"2","key":"4272_CR8","doi-asserted-by":"publisher","first-page":"e220134","DOI":"10.1530\/ETJ-22-0134","volume":"12","author":"T Solymosi","year":"2023","unstructured":"T. Solymosi, L. Heged\u0171s, S.J. Bonnema, A. Frasoldati, L. Jambor, Z. Karanyi, G.L. Kovacs, E. Papini, K. Rucz, G. Russ, E.V. Nagy, Considerable interobserver variation calls for unambiguous definitions of thyroid nodule ultrasound characteristics. Eur. Thyroid. J. 12(2), e220134 (2023). https:\/\/doi.org\/10.1530\/ETJ-22-0134.","journal-title":"Eur. Thyroid. J."},{"issue":"2","key":"4272_CR9","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1089\/thy.2019.0360","volume":"30","author":"A Persichetti","year":"2020","unstructured":"A. Persichetti, E. Di Stasio, C. Coccaro, F. Graziano, A. Bianchini, V. Di Donna, S. Corsello, D. Valle, G. Bizzarri, A. Frasoldati, A. Pontecorvi, E. Papini, R. Guglielmi, Inter- and intraobserver agreement in the assessment of thyroid nodule ultrasound features and classification systems: a blinded multicenter study. Thyroid 30(2), 237\u2013242 (2020). https:\/\/doi.org\/10.1089\/thy.2019.0360.","journal-title":"Thyroid"},{"issue":"1","key":"4272_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1530\/EC-17-0336","volume":"7","author":"G Grani","year":"2018","unstructured":"G. Grani, L. Lamartina, V. Cantisani, M. Maranghi, P. Lucia, C. Durante, Interobserver agreement of various thyroid imaging reporting and data systems. Endocr. Connect. 7(1), 1\u20137 (2018). https:\/\/doi.org\/10.1530\/EC-17-0336.","journal-title":"Endocr. Connect."},{"key":"4272_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1191\/0962280204sm365ra","volume":"13","author":"MM Shoukri","year":"2004","unstructured":"M.M. Shoukri, M.H. Asyali, A. Donner, Sample size requirements for the design of reliability study: review and new results. Stat. Methods Med. Res. 13, 1\u201321 (2004).","journal-title":"Stat. Methods Med. Res."},{"issue":"17","key":"4272_CR12","doi-asserted-by":"publisher","first-page":"4316","DOI":"10.3390\/cancers13174316","volume":"13","author":"G Russ","year":"2021","unstructured":"G. Russ, P. Trimboli, C. Buffet, The new era of TIRADSs to stratify the risk of malignancy of thyroid nodules: strengths, weaknesses and pitfalls. Cancers 13(17), 4316 (2021). https:\/\/doi.org\/10.3390\/cancers13174316.","journal-title":"Cancers"},{"issue":"5","key":"4272_CR13","doi-asserted-by":"publisher","first-page":"2877","DOI":"10.1007\/s00330-020-07384-6","volume":"31","author":"PH Kim","year":"2021","unstructured":"P.H. Kim, C.H. Suh, J.H. Baek, S.R. Chung, Y.J. Choi, J.H. Lee, Unnecessary thyroid nodule biopsy rates under four ultrasound risk stratification systems: a systematic review and meta-analysis. Eur. Radiol. 31(5), 2877\u20132885 (2021). https:\/\/doi.org\/10.1007\/s00330-020-07384-6.","journal-title":"Eur. Radiol."},{"issue":"1","key":"4272_CR14","doi-asserted-by":"publisher","first-page":"117","DOI":"10.3803\/EnM.2023.1670","volume":"38","author":"L Joo","year":"2023","unstructured":"L. Joo, M.K. Lee, J.Y. Lee, E.J. Ha, D.G. Na, Diagnostic performance of ultrasound-based risk stratification systems for thyroid nodules: a systematic review and meta-analysis. Endocrinol. Metab. 38(1), 117\u2013128 (2023). https:\/\/doi.org\/10.3803\/EnM.2023.1670.","journal-title":"Endocrinol. Metab."},{"issue":"4","key":"4272_CR15","doi-asserted-by":"publisher","first-page":"877","DOI":"10.1007\/s40618-024-02518-9","volume":"48","author":"P Trimboli","year":"2024","unstructured":"P. Trimboli, A. Colombo, E. Gamarra, L. Ruinelli, A. Leoncini, Performance of computer scientists in the assessment of thyroid nodules using TIRADS lexicons. J. Endocrinol. Invest. 48(4), 877\u2013883 (2024). https:\/\/doi.org\/10.1007\/s40618-024-02518-9.","journal-title":"J. Endocrinol. Invest."}],"container-title":["Endocrine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12020-025-04272-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12020-025-04272-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12020-025-04272-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T01:59:35Z","timestamp":1757555975000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12020-025-04272-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":15,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,7]]}},"alternative-id":["4272"],"URL":"https:\/\/doi.org\/10.1007\/s12020-025-04272-1","relation":{},"ISSN":["1559-0100"],"issn-type":[{"value":"1559-0100","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,15]]},"assertion":[{"value":"4 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}