{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T00:39:29Z","timestamp":1793752769208,"version":"4.6.1"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:00:00Z","timestamp":1746403200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>In recent years, artificial intelligence (AI) tools have become widely studied for thyroid ultrasonography (USG) classification. The real-world applicability of these developed tools as pre-operative diagnostic aids is limited due to model overfitting, clinician trust, and a lack of gold standard surgical histology as ground truth class label. The ongoing dilemma within clinical thyroidology is surgical decision making for indeterminate thyroid nodules (ITN). Genomic sequencing classifiers (GSC) have been utilised for this purpose; however, costs and availability preclude universal adoption creating an inequity gap. We conducted this review to analyse the current evidence of AI in ITN diagnosis without the use of GSC.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>English language articles evaluating the diagnostic accuracy of AI for ITNs were identified. A systematic search of PubMed, Google Scholar, and Scopus from inception to 18 February 2025 was performed using comprehensive search strategies incorporating MeSH headings and keywords relating to AI, indeterminate thyroid nodules, and pre-operative diagnosis. This systematic review and meta-analysis was conducted in accordance with methods recommended by the Cochrane Collaboration (PROSPERO ID CRD42023438011).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The search strategy yielded 134 records after the removal of duplicates. A total of 20 models were presented in the seven studies included, five of which were radiological driven, one utilised natural language processing, and one focused on cytology. The pooled meta-analysis incorporated 16 area under the curve (AUC) results derived from 15 models across three studies yielding a combined estimate of 0.82 (95% CI: 0.81\u20130.84) indicating moderate-to-good classification performance across machine learning (ML) and deep learning (DL) architectures. However, substantial heterogeneity was observed, particularly among DL models (I\u00b2 = 99.7%, pooled AUC = 0.85, 95% CI: 0.85\u20130.86). Minimal heterogeneity was observed among ML models (I\u00b2 = 0.7%), with a pooled AUC of 0.75 (95% CI: 0.70\u20130.81). Meta-regression analysis performed suggests potential publication bias or systematic differences in model architectures, dataset composition, and validation methodologies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This review demonstrated the burgeoning potential of AI to be of clinical value in surgical decision making for ITNs; however, study-developed models were unsuitable for clinical implementation based on performance alone at their current states or lacked robust independent external validation. There is substantial capacity for further development in this field.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Systematic Review Registration<\/jats:title>\n                    <jats:p>\n                      <jats:uri>https:\/\/www.crd.york.ac.uk\/PROSPERO\/<\/jats:uri>\n                      , identifier CRD42023438011.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2025.1506729","type":"journal-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:10:40Z","timestamp":1746403840000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":15,"title":["Beyond genomics: artificial intelligence-powered diagnostics for indeterminate thyroid nodules\u2014a systematic review and meta-analysis"],"prefix":"10.3389","volume":"16","author":[{"given":"Karishma","family":"Jassal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Edwards","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Afsaneh","family":"Koohestani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendy","family":"Brown","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan W.","family":"Serpell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James C.","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2004.14.926","article-title":"Prevalence of thyroid disorders in the working population of Germany: ultrasonography screening in 96,278 unselected employees","volume":"14","author":"Reiners","year":"2004","journal-title":"Thyroid"},{"key":"B2","unstructured":"Thyroid incidentalomas: management approaches to nonpalpable nodules discovered incidentally on thyroid imaging\n          \n          \n            \n              Tan\n              GH\n            \n            \n              Gharib\n              H\n            \n          \n          \n          1997"},{"key":"B3","doi-asserted-by":"publisher","first-page":"995","DOI":"10.1016\/j.ejrad.2013.02.002","article-title":"Diagnostic performance of combined elastosonography scoring and high-resolution ultrasonography for the differentiation of benign and Malignant thyroid nodules","volume":"82","author":"Shweel","year":"2013","journal-title":"Eur J Radiol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/0002-9343(92)90163-6","article-title":"Thyroid cancer in thyroid nodules: finding a needle in the haystack","volume":"93","author":"Mazzaferri","year":"1992","journal-title":"Am J Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.5152\/dir.2021.20813","article-title":"Diagnostic performance rates of the ACR-tirads and EU-tirads based on histopathological evidence","volume":"27","author":"Hekimsoy","year":"2021","journal-title":"Diagn Interventional Radiol"},{"key":"B6","doi-asserted-by":"publisher","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"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1159\/000478927","article-title":"European thyroid association guidelines for ultrasound Malignancy risk stratification of thyroid nodules in adults: the EU-TIRADS","volume":"6","author":"Russ","year":"2017","journal-title":"Eur Thyroid J"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1309\/AJCPPHLWMI3JV4LA","article-title":"The Bethesda system for reporting thyroid cytopathology","volume":"132","author":"Cibas","year":"2009","journal-title":"Am J Clin Pathol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1159\/000339959","article-title":"The Bethesda system for reporting thyroid cytopathology: A meta-analysis","volume":"56","author":"Bongiovanni","year":"2012","journal-title":"Acta Cytologic"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s12022-011-9182-7","article-title":"Update in thyroid fine needle aspiration","volume":"22","author":"Faquin","year":"2011","journal-title":"Endocr Pathol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1159\/000334218","article-title":"Variability in the atypia of undetermined significance\/follicular lesion of undetermined significance diagnosis in the Bethesda System for Reporting Thyroid Cytopathology: Sources and recommendations","volume":"55","author":"Ohori","year":"2011","journal-title":"Acta Cytol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2017.0500","article-title":"The 2017 bethesda system for reporting thyroid cytopathology","volume":"27","author":"Cibas","year":"2017","journal-title":"Thyroid"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ando.2022.04.001","article-title":"Fine-needle aspiration cytology repetition in thyroid nodules with non-diagnostic findings or atypia of undetermined significance\/follicular lesions of undetermined significance: Does time matters","volume":"83","author":"Benido Silva","year":"2022","journal-title":"Ann Endocrinol (Paris)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"36","DOI":"10.5144\/0256-4947.2021.36","article-title":"The value of repeating fine-needle aspiration for thyroid nodules","volume":"41","author":"Doubi","year":"2021","journal-title":"Ann Saudi Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1111\/cen.14400","article-title":"National differences in cost analysis of Afirma Genomic sequencing classifier","volume":"94","author":"Ronen","year":"2021","journal-title":"Clin Endocrinol (Oxf)"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1111\/j.1445-2197.2008.04764.x","article-title":"Hemithyroidectomy: A heuristics perspective","volume":"78","author":"Serpell","year":"2008","journal-title":"ANZ J Surg"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1097\/SLA.0b013e3181ae5426","article-title":"Hypothyroidism following hemithyroidectomy: A retrospective review","volume":"250","author":"Su","year":"2009","journal-title":"Ann Surg"},{"key":"B18","first-page":"399","article-title":"Risk factors for hematoma after thyroidectomy: Results from the nationwide inpatient sample","volume-title":"Surgery (United states)","author":"Weiss","year":"2014"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2018.4616","article-title":"Performance of a multigene genomic classifier in thyroid nodules with indeterminate cytology: A prospective blinded multicenter study","volume":"5","author":"Nikiforov","year":"2019","journal-title":"JAMA Oncol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2020.5935","article-title":"Effectiveness of molecular testing techniques for diagnosis of indeterminate thyroid nodules: A randomized clinical trial","volume":"7","author":"Livhits","year":"2021","journal-title":"JAMA Oncol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.v124.8","article-title":"Analytical performance of the ThyroSeq v3 genomic classifier for cancer diagnosis in thyroid nodules","volume":"124","author":"Nikiforova","year":"2018","journal-title":"Cancer"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2022.0189","article-title":"Preoperative identification of medullary thyroid carcinoma (MTC): clinical validation of the afirma MTC RNA-sequencing classifier","volume":"32","author":"Randolph","year":"2022","journal-title":"Thyroid"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2018.0380","article-title":"Machine learning-assisted system for thyroid nodule diagnosis","volume":"29","author":"Zhang","year":"2019","journal-title":"Thyroid"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106823","article-title":"Deep convolutional neural networks in thyroid disease detection: A multi-classification comparison by ultrasonography and computed tomography","volume":"220","author":"Zhang","year":"2022","journal-title":"Comput Methods Programs BioMed"},{"key":"B25","doi-asserted-by":"publisher","first-page":"43","DOI":"10.4103\/jpi.jpi_43_18","article-title":"Artificial intelligence in cytopathology: A neural network to identify papillary carcinoma on thyroid fine-needle aspiration cytology smears","volume":"9","author":"Sanyal","year":"2018","journal-title":"J Pathol Inform"},{"key":"B26","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s12957-019-1558-z","article-title":"Automatic thyroid nodule recognition and diagnosis in ultrasound imaging with the YOLOv2 neural network","volume":"17","author":"Wang","year":"2019","journal-title":"World J Surg Oncol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-018-5772-9","article-title":"Computer-aided diagnosis system for thyroid nodules on ultrasonography: diagnostic performance and reproducibility based on the experience level of operators","volume":"29","author":"Jeong","year":"2019","journal-title":"Eur Radiol"},{"key":"B28","first-page":"CRD42023438011","article-title":"Beyond genomics: artificial intelligence powered diagnostics for indeterminate thyroid nodules - A systematic review and meta-analysis","author":"Jassal","year":"2023","journal-title":"PROSPERO"},{"key":"B29","article-title":"Analysing and presenting results","volume-title":"Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy. Version10","author":"Macaskill","year":"2010"},{"key":"B30","volume-title":"Preferred Reporting Items for Systematic Reviews and Meta-analysis Statement","author":"Moher","year":"2009"},{"key":"B31","volume-title":"Encyclopedia of Machine Learning","author":"Sammut","year":"2011"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.7326\/M18-1376","article-title":"PROBAST: A tool to assess the risk of bias and applicability of prediction model studies","volume":"170","author":"Wolff","year":"2019","journal-title":"Ann Intern Med"},{"key":"B33","first-page":"W1","article-title":"PROBAST: A tool to assess risk of bias and applicability of prediction model studies: Explanation and elaboration","volume-title":"Annals of Internal Medicine","author":"Moons","year":"2019"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1111\/cen.14612","article-title":"Risk stratification of indeterminate thyroid nodules using ultrasound and machine learning algorithms","volume":"96","author":"Gild","year":"2022","journal-title":"Clin Endocrinol (Oxf)"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2021.09.015","article-title":"Risk stratifying indeterminate thyroid nodules with machine learning","volume":"270","author":"Luong","year":"2022","journal-title":"J Surg Res"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2023.108114","article-title":"AI diagnosis of Bethesda category IV thyroid nodules","volume":"26","author":"Yao","year":"2023","journal-title":"iScience"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2022.03.020","article-title":"Machine learning\u2013assisted diagnostic system for indeterminate thyroid nodules","volume":"48","author":"Chen","year":"2022","journal-title":"Ultrasound Med Biol"},{"key":"B38","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1111\/cyt.13180","article-title":"An artificial neural network for the prediction of the risk of Malignancy in category III Bethesda thyroid lesions","volume":"34","author":"Saini","year":"2023","journal-title":"Cytopathology"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1530\/ETJ-21-0129","article-title":"External validation of AIBx, an artificial intelligence model for risk stratification, in thyroid nodules","volume":"11","author":"Swan","year":"2022","journal-title":"Eur Thyroid J"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2019.0752","article-title":"AIBx, artificial intelligence model to risk stratify thyroid nodules","volume":"30","author":"Thomas","year":"2020","journal-title":"Thyroid"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(21)00041-8","article-title":"Deep learning-based artificial intelligence model to assist thyroid nodule diagnosis and management: a multicentre diagnostic study","volume":"3","author":"Peng","year":"2021","journal-title":"Lancet Digit Health"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.9.3.034501","article-title":"A machine-learning algorithm for distinguishing Malignant from benign indeterminate thyroid nodules using ultrasound radiomic features","volume":"9","author":"Keutgen","year":"2022","journal-title":"J Med Imaging"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560","article-title":"Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): Architecture, component evaluation and applications","volume":"17","author":"Savova","year":"2010","journal-title":"J Am Med Inf Assoc"},{"key":"B44","unstructured":"Deep residual learning for image recognition\n          \n          \n            \n              He\n              K\n            \n            \n              Zhang\n              X\n            \n            \n              Ren\n              S\n            \n            \n              Sun\n              J\n            \n          \n          \n          2015"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"He","year":"2016"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2009.5206848","article-title":"ImageNet: A large-scale hierarchical image database","volume-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","author":"Deng","year":"2009"},{"key":"B47","unstructured":"Swin transformer: hierarchical vision transformer using shifted windows\n          \n          \n            \n              Liu\n              Z\n            \n            \n              Lin\n              Y\n            \n            \n              Cao\n              Y\n            \n            \n              Hu\n              H\n            \n            \n              Wei\n              Y\n            \n            \n              Zhang\n              Z"},{"key":"B48","unstructured":"An introduction to convolutional neural networks\n          \n          \n            \n              O\u2019Shea\n              K\n            \n            \n              Nash\n              R\n            \n          \n          \n          2015"},{"key":"B49","article-title":"K-nearest neighbour classifiers-A tutorial","volume-title":"ACM Computing Surveys","author":"Cunningham","year":"2021"},{"key":"B50","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.243","article-title":"Densely connected convolutional networks","volume-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Huang","year":"2017"},{"key":"B51","volume-title":"Aggregated Residual Transformations for Deep Neural Networks","author":"Xie","year":"2016"},{"key":"B52","volume-title":"Ambiguous and Incomplete: Natural Language Processing Reveals Problematic Reporting Styles in Thyroid Ultrasound Reports Corresponding Author: Running title: Natural Language Processing in Thyroid Ultrasounds","author":"Dedhia","year":""},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1016\/j.jss.2020.07.018","article-title":"Thyroid ultrasound reports: will TI-RADS improve natural language processing capture of critical thyroid nodule features","volume":"256","author":"Chen","year":"2020","journal-title":"J Surg Res"},{"key":"B54","volume-title":"AI-Generated Content Enhanced Computer-Aided Diagnosis Model for Thyroid Nodules: A ChatGPT-Style Assistant","author":"Yao","year":"2024"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1506729\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T00:10:49Z","timestamp":1746403849000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2025.1506729\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,5]]},"references-count":54,"alternative-id":["10.3389\/fendo.2025.1506729"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2025.1506729","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,5]]},"article-number":"1506729"}}