{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T14:08:06Z","timestamp":1790690886955,"version":"4.1.0"},"reference-count":24,"publisher":"The Endocrine Society","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Convolutional neural networks can classify thyroid nodules on ultrasound, yet published models are seldom available for independent testing, require machine learning expertise to develop and deploy, and are validated mostly on papillary thyroid carcinoma.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To test whether an autonomous (\u201cagentic\u201d), no-code artificial intelligence (AI) agent can develop a calibrated thyroid nodule malignancy classifier and validate it internally and on an external cohort spanning multiple cancer histologies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This was a retrospective, computational diagnostic study. A no-code agent (Hugging Face ML-Intern) autonomously audited the data, selected and trained the model, and calibrated probabilities, using the open-source TN5000 dataset. The locked ResNet-18 model was externally validated on 232 nodules from the University of Colorado and benchmarked against a previously published classifier evaluated on the same source.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the internal test set, the agentic model achieved an area under the receiver-operating-characteristic curve (AUROC) of 0.94 (95% CI, 0.92-0.95), sensitivity 0.90, and specificity 0.81. On external validation, the model achieved an AUROC of 0.90 (95% CI, 0.85-0.93); sensitivity was 0.92, specificity 0.68, positive predictive value 0.52, and negative predictive value 0.96, exceeding the performance of the benchmark model (AUROC 0.83; paired DeLong P = .03). Missed cancers clustered among follicular pattern tumors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An agentic, no-code AI workflow produced a calibrated, externally validated thyroid nodule classifier, supporting accessible, reproducible, and independently testable medical AI development. Prospective validation and local recalibration are required before clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1210\/clinem\/dgag351","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:36:20Z","timestamp":1787657780000},"source":"Crossref","is-referenced-by-count":0,"title":["An agentic, no-code artificial intelligence workflow for developing a thyroid nodule ultrasound malignancy classifier"],"prefix":"10.1210","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3540-4913","authenticated-orcid":false,"given":"Johnson","family":"Thomas","sequence":"first","affiliation":[{"name":"Department of Endocrinology, Mercy Hospital , Springfield, MO 65807 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8574-1972","authenticated-orcid":false,"given":"Nikita","family":"Pozdeyev","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado Anschutz , Aurora, CO 80045 ,","place":["USA"]},{"name":"Division of Endocrinology, Diabetes and Metabolism, University of Colorado Anschutz , Aurora, CO 80045 ,","place":["USA"]},{"name":"Colorado Center for Personalized Medicine, University of Colorado Anschutz , Aurora, CO 80045 ,","place":["USA"]},{"name":"University of Colorado Cancer Center, University of Colorado Anschutz , Aurora, CO 80045 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"80","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"issue":"11","key":"2026092909394039600_dgag351-B1","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.2174\/0118715303264254231117113456","article-title":"The application of artificial intelligence in thyroid nodules: a systematic review based on bibliometric analysis","volume":"24","author":"Peng","year":"2024","journal-title":"Endocr Metab Immune Disord Drug Targets"},{"issue":"7","key":"2026092909394039600_dgag351-B2","doi-asserted-by":"crossref","first-page":"1684","DOI":"10.1210\/clinem\/dgae277","article-title":"From bench-to-bedside: how artificial intelligence is changing thyroid nodule diagnostics, a systematic review","volume":"109","author":"Sant","year":"2024","journal-title":"J Clin Endocrinol Metab"},{"issue":"2","key":"2026092909394039600_dgag351-B3","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1210\/clinem\/dgaf530","article-title":"Artificial intelligence applications in thyroid cancer care","volume":"111","author":"Pozdeyev","year":"2026","journal-title":"J Clin Endocrinol Metab"},{"issue":"1","key":"2026092909394039600_dgag351-B4","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"},{"issue":"5","key":"2026092909394039600_dgag351-B5","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.jacr.2017.01.046","article-title":"ACR Thyroid Imaging, Reporting and Data System (TI-RADS): white paper of the ACR TI-RADS committee","volume":"14","author":"Tessler","year":"2017","journal-title":"J Am Coll Radiol"},{"issue":"1","key":"2026092909394039600_dgag351-B6","doi-asserted-by":"crossref","first-page":"162","DOI":"10.2214\/AJR.17.19192","article-title":"Interobserver variability of sonographic features used in the American College of Radiology Thyroid Imaging Reporting and Data System","volume":"211","author":"Hoang","year":"2018","journal-title":"AJR Am J Roentgenol"},{"issue":"4","key":"2026092909394039600_dgag351-B7","doi-asserted-by":"crossref","DOI":"10.1530\/ETJ-22-0027","article-title":"Malignancy rates in thyroid nodules: a long-term cohort study of 17,592 patients","volume":"11","author":"Grussendorf","year":"2022","journal-title":"Eur Thyroid J"},{"issue":"2","key":"2026092909394039600_dgag351-B8","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S1470-2045(18)30762-9","article-title":"Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study","volume":"20","author":"Li","year":"2019","journal-title":"Lancet Oncol"},{"issue":"3","key":"2026092909394039600_dgag351-B9","doi-asserted-by":"crossref","first-page":"695","DOI":"10.1148\/radiol.2019181343","article-title":"Management of thyroid nodules seen on US images: deep learning may match performance of radiologists","volume":"292","author":"Buda","year":"2019","journal-title":"Radiology"},{"issue":"2","key":"2026092909394039600_dgag351-B10","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1177\/10507256251412316","article-title":"Artificial intelligence applications in thyroid cancer diagnosis: 2026 update","volume":"36","author":"Thomas","year":"2026","journal-title":"Thyroid"},{"key":"2026092909394039600_dgag351-B11","article-title":"Machine learning for diagnosis of malignant thyroid nodules based on thyroid ultrasound: systematic review and meta-analysis of studies with external datasets","volume":"16","author":"Gatta","year":"2025","journal-title":"Eur J Radiol Open"},{"key":"2026092909394039600_dgag351-B12","author":"Trirat"},{"key":"2026092909394039600_dgag351-B13","author":"Reedi"},{"issue":"1","key":"2026092909394039600_dgag351-B14","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1038\/s41597-025-05757-4","article-title":"TN5000: an ultrasound image dataset for thyroid nodule detection and classification","volume":"12","author":"Zhang","year":"2025","journal-title":"Sci Data"},{"issue":"2","key":"2026092909394039600_dgag351-B15","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1210\/clinem\/dgad530","article-title":"Thyroid cancer polygenic risk score improves classification of thyroid nodules as benign or malignant","volume":"109","author":"Pozdeyev","year":"2024","journal-title":"J Clin Endocrinol Metab"},{"key":"2026092909394039600_dgag351-B16","doi-asserted-by":"crossref","unstructured":"Thomas J, Pozdeyev N. 2026. An Agentic, No Code Artificial Intelligence Workflow for Developing and Externally Validating a Thyroid Nodule Ultrasound Malignancy Classifier. Zenodo. doi:10.5281\/zenodo.21896286.","DOI":"10.64898\/2026.06.23.26356395"},{"key":"2026092909394039600_dgag351-B17","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD + AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026092909394039600_dgag351-B18","author":"Thomas"},{"key":"2026092909394039600_dgag351-B19","doi-asserted-by":"publisher","author":"He","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026092909394039600_dgag351-B20","author":"PyTorch Contributors"},{"key":"2026092909394039600_dgag351-B21","unstructured":"Wightman R, Raw N, Soare A, et al \u00a0rwightman\/pytorch-image-models: v0.8.10dev0 Release. Zenodo. Published February 7, 2023. doi:10.5281\/zenodo.7618837"},{"key":"2026092909394039600_dgag351-B22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-98688-8_16","volume-title":"Medical Image Understanding and Analysis","author":"Qi","year":"2026"},{"key":"2026092909394039600_dgag351-B23","author":"Loshchilov"},{"key":"2026092909394039600_dgag351-B24","author":"Guo"}],"container-title":["The Journal of Clinical Endocrinology &amp; Metabolism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article-pdf\/doi\/10.1210\/clinem\/dgag351\/71465226\/dgag351.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article-pdf\/doi\/10.1210\/clinem\/dgag351\/71465226\/dgag351.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:39:53Z","timestamp":1790689193000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article\/doi\/10.1210\/clinem\/dgag351\/8845433"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1210\/clinem\/dgag351","relation":{},"ISSN":["0021-972X","1945-7197"],"issn-type":[{"value":"0021-972X","type":"print"},{"value":"1945-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]},"article-number":"dgag351"}}