{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T20:35:28Z","timestamp":1788208528731,"version":"build-2803163510"},"reference-count":31,"publisher":"Bioscientifica","issue":"2","license":[{"start":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T00:00:00Z","timestamp":1781308800000},"content-version":"vor","delay-in-days":85,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["journals.bioscientifica.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Artificial intelligence (AI) chatbots are increasingly used in medicine, but their reliability in scenarios with multiple management options is unclear. Indeterminate thyroid nodules and low- and low-to-intermediate-risk papillary thyroid carcinoma (PTC) represent such cases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In a nationwide web-based survey, 201 members of the Hellenic Endocrine Society evaluated 12 clinical vignettes on indeterminate thyroid nodules and low- and low-to-intermediate-risk PTC. Their responses were compared with those generated by four conversational AI models (ChatGPT, Gemini, Copilot, and DeepSeek) at two time points, 11 months apart. DeepSeek was assessed only at the second time point. Chatbot outputs were assessed for agreement with endocrinologists\u2019 predominant answers, concordance with the most guideline-consistent options (American and European Thyroid Association recommendations), temporal stability, and inter-model agreement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Alignment between chatbots and endocrinologists\u2019 predominant responses was limited, reaching at most 25% across scenarios. In contrast, concordance with the most guideline-consistent options was higher, up to 83% (10\/12 scenarios), depending on the model and time point. Across 12 scenarios, ChatGPT, Gemini, and Copilot changed their responses in 4, 7, and 5 scenarios, respectively, with some updates moving closer to, and others further from, guideline-based answers. Inter-model agreement ranged from 33 to 67%, indicating substantial variability among chatbots.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>AI chatbots show evolving but inconsistent performance in complex thyroid management scenarios. While guideline concordance can be relatively high, substantial variability across models, limited temporal reproducibility, and poor alignment with clinical practice highlight the need for ongoing longitudinal evaluation before safe integration into clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1530\/etj-25-0385","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T12:06:53Z","timestamp":1774526813000},"update-policy":"https:\/\/doi.org\/10.1530\/crossmarkpolicy-17","source":"Crossref","is-referenced-by-count":2,"title":["Promise and pitfalls of AI chatbots in complex decision-making for thyroid nodules and papillary thyroid cancer"],"prefix":"10.1530","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7313-8391","authenticated-orcid":true,"given":"Grigoris","family":"Effraimidis","sequence":"first","affiliation":[{"name":"1"},{"name":"2"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Athanasios","family":"Kasotas","sequence":"additional","affiliation":[{"name":"2"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sofia","family":"Varsami","sequence":"additional","affiliation":[{"name":"4"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eleni","family":"Sazakli","sequence":"additional","affiliation":[{"name":"3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9978-5885","authenticated-orcid":true,"given":"Olga","family":"Karapanou","sequence":"additional","affiliation":[{"name":"5"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katerina","family":"Saltiki","sequence":"additional","affiliation":[{"name":"6"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2073-8523","authenticated-orcid":true,"given":"Marina","family":"Michalaki","sequence":"additional","affiliation":[{"name":"3"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"416","published-online":{"date-parts":[[2026,3,20]]},"reference":[{"key":"2026070714002521800_bib1","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2021"},{"key":"2026070714002521800_bib2","first-page":"589","article-title":"Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum","volume":"183","author":"Ayers","year":"2023","journal-title":"J Am Med Assoc Intern Med"},{"key":"2026070714002521800_bib3","doi-asserted-by":"crossref","DOI":"10.1093\/bmb\/ldaf017","article-title":"AI chatbots versus human healthcare professionals: a systematic review and meta-analysis of empathy in patient care","volume":"156","author":"Howcroft","year":"2025","journal-title":"Br Med Bull"},{"key":"2026070714002521800_bib4","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1001\/jama.2018.0898","article-title":"The diagnosis and management of thyroid nodules: a review","volume":"319","author":"Durante","year":"2018","journal-title":"J Am Med Assoc"},{"key":"2026070714002521800_bib5","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1111\/j.1365-2362.2009.02162.x","article-title":"Very high prevalence of thyroid nodules detected by high frequency (13 MHz) ultrasound examination","volume":"39","author":"Guth","year":"2009","journal-title":"Eur J Clin Invest"},{"key":"2026070714002521800_bib6","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1038\/nrendo.2016.110","article-title":"The changing incidence of thyroid cancer","volume":"12","author":"Kitahara","year":"2016","journal-title":"Nat Rev Endocrinol"},{"key":"2026070714002521800_bib7","first-page":"5","article-title":"Trends in the incidence of thyroid cancer among US persons from 2000 to 2019","volume":"33","author":"Yu","year":"2024","journal-title":"Cancer Epidemiol"},{"key":"2026070714002521800_bib8","doi-asserted-by":"crossref","DOI":"10.1177\/10732748221135447","article-title":"The incidence trend of papillary thyroid carcinoma in the United States during 2003\u20132017","volume":"29","author":"Li","year":"2022","journal-title":"Cancer Control"},{"key":"2026070714002521800_bib9","article-title":"Key data from the 2024 European Thyroid Association annual meeting: differentiated thyroid carcinoma","volume":"86","author":"Haissaguerre","year":"2025","journal-title":"Ann Endocrinol"},{"key":"2026070714002521800_bib10","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1177\/10507256251363120","article-title":"2025 American Thyroid Association management guidelines for adult patients with differentiated thyroid cancer","volume":"35","author":"Ringel","year":"2025","journal-title":"Thyroid"},{"key":"2026070714002521800_bib11","doi-asserted-by":"crossref","first-page":"1177","DOI":"10.1007\/s13187-019-01576-5","article-title":"Websites, websites everywhere: how thyroid cancer patients use the internet","volume":"35","author":"Chang","year":"2020","journal-title":"J Cancer Educ"},{"key":"2026070714002521800_bib12","doi-asserted-by":"crossref","first-page":"51","DOI":"10.17294\/2330-0698.2029","article-title":"Patient perspectives on the use of artificial intelligence in health care: a scoping review","volume":"11","author":"Moy","year":"2024","journal-title":"J Patient Centered Res Rev"},{"key":"2026070714002521800_bib13","doi-asserted-by":"crossref","DOI":"10.2196\/47564","article-title":"User intentions to use ChatGPT for self-diagnosis and health-related purposes: cross-sectional survey study","volume":"10","author":"Shahsavar","year":"2023","journal-title":"JMIR Hum Factors"},{"key":"2026070714002521800_bib14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1089\/thy.2015.0020","article-title":"2015 American Thyroid Association management guidelines for adult patients with thyroid nodules and differentiated thyroid cancer","volume":"26","author":"Haugen","year":"2016","journal-title":"Thyroid"},{"key":"2026070714002521800_bib15","doi-asserted-by":"crossref","DOI":"10.1530\/ETJ-21-0046","article-title":"2022 ETA consensus statement: indications for post-surgical radioiodine therapy in differentiated thyroid cancer","volume":"11","author":"Pacini","year":"2022","journal-title":"Eur Thyroid J"},{"key":"2026070714002521800_bib16","doi-asserted-by":"crossref","DOI":"10.1530\/ETJ-23-0067","article-title":"2023 European Thyroid Association clinical practice guidelines for thyroid nodule management","volume":"12","author":"Durante","year":"2023","journal-title":"Eur Thyroid J"},{"key":"2026070714002521800_bib17","doi-asserted-by":"crossref","DOI":"10.1210\/jendso\/bvaf003","article-title":"Assessing ChatGPT\u2019s capability in addressing thyroid cancer patient queries","volume":"9","author":"Gorris","year":"2025","journal-title":"J Endocr Soc"},{"key":"2026070714002521800_bib18","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.36483","article-title":"Accuracy and reliability of chatbot responses to physician questions","volume":"6","author":"Goodman","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2026070714002521800_bib19","doi-asserted-by":"crossref","DOI":"10.1530\/ETJ-25-0013","article-title":"Active surveillance for low-risk papillary thyroid microcarcinoma","volume":"14","author":"Effraimidis","year":"2025","journal-title":"Eur Thyroid J"},{"key":"2026070714002521800_bib20","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1007\/s42000-025-00698-4","article-title":"Nationwide web survey on implementing the 2023 ETA guidelines for second-line management of thyroid nodules with atypia of undetermined significance","volume":"24","author":"Sazakli","year":"2025","journal-title":"Hormones"},{"key":"2026070714002521800_bib21","first-page":"1039","article-title":"The 2023 Bethesda system for reporting thyroid cytopathology","volume":"33","author":"Ali","year":"2023","journal-title":"Thyroid"},{"key":"2026070714002521800_bib22","doi-asserted-by":"crossref","first-page":"1133","DOI":"10.1186\/s12909-024-06115-5","article-title":"The future of AI clinicians","volume":"24","author":"Huang","year":"2024","journal-title":"BMC Med Educ"},{"key":"2026070714002521800_bib23","article-title":"Evaluating the performance of ChatGPT in thyroid eye disease","volume":"12","author":"Wang","year":"2025","journal-title":"Front Med"},{"key":"2026070714002521800_bib24","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1056\/AIoa2300151","article-title":"Comparative evaluation of large language models in clinical oncology","volume":"1","author":"Rydzewski","year":"2024","journal-title":"NEJM AI"},{"key":"2026070714002521800_bib25","doi-asserted-by":"crossref","first-page":"7810","DOI":"10.3390\/jcm13247810","article-title":"Comparison of the accuracy and consistency of different AI chatbots in providing nutritional advice","volume":"13","author":"Ponzo","year":"2024","journal-title":"J Clin Med"},{"key":"2026070714002521800_bib26","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1007\/s12020-024-03750-2","article-title":"Assessment of ChatGPT\u2019s adherence to ETA thyroid nodule management guideline","volume":"85","author":"Deniz","year":"2024","journal-title":"Endocrine"},{"key":"2026070714002521800_bib27","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1055\/s-0044-1782165","article-title":"Response generated by large language models depends on the structure of the prompt","volume":"34","author":"Sarangi","year":"2024","journal-title":"Indian J Radiol Imag"},{"key":"2026070714002521800_bib28","doi-asserted-by":"crossref","first-page":"315","DOI":"10.1007\/s12020-024-04121-7","article-title":"Comparative evaluation of ChatGPT-4, ChatGPT-3.5 and Google Gemini on PCOS management","volume":"88","author":"Gunesli","year":"2024","journal-title":"Endocrine"},{"key":"2026070714002521800_bib29","article-title":"Accuracy of AI systems against clinical practice guidelines","volume":"7","author":"Rossettini","year":"2025","journal-title":"Front Digit Health"},{"key":"2026070714002521800_bib30","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1055\/s-0043-1777289","article-title":"Radiological differential diagnoses based on imaging patterns","volume":"34","author":"Sarangi","year":"2024","journal-title":"Indian J Radiol Imag"},{"key":"2026070714002521800_bib31","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1055\/s-0044-1787974","article-title":"Radiologic decision-making for imaging in pulmonary embolism","volume":"34","author":"Sarangi","year":"2024","journal-title":"Indian J Radiol Imag"}],"container-title":["European Thyroid Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/etj.bioscientifica.com\/view\/journals\/etj\/15\/2\/ETJ-25-0385.xml","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/etj.bioscientifica.com\/downloadpdf\/journals\/etj\/15\/2\/ETJ-25-0385.xml","content-type":"text\/html","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.bioscientifica.com\/etj\/article-pdf\/doi\/10.1530\/ETJ-25-0385\/503350\/etj-25-0385.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/journals.bioscientifica.com\/etj\/article-pdf\/doi\/10.1530\/ETJ-25-0385\/503350\/etj-25-0385.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T18:00:37Z","timestamp":1783447237000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.bioscientifica.com\/etj\/article\/15\/2\/ETJ250385\/75622\/Promise-and-pitfalls-of-AI-chatbots-in-complex"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1530\/etj-25-0385","relation":{},"ISSN":["2235-0802","2235-0640"],"issn-type":[{"value":"2235-0802","type":"electronic"},{"value":"2235-0640","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3,20]]},"article-number":"ETJ250385"}}