{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T13:45:53Z","timestamp":1780321553798,"version":"3.54.1"},"reference-count":28,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to evaluate the value of a machine learning model based on tongue features in the adjunctive diagnosis of Hashimoto\u2019s thyroiditis (HT) and its concomitant hypothyroidism.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Tongue images and related clinical data were retrospectively collected from 120 HT patients (60 each from the euthyroid group and the hypothyroidism group), and the tongue region was segmented by preprocessing, and the image feature dimensions were extracted with 1,125 dimensions. Therefore, four methods, namely, random forest (RF), logistic regression (LR), support vector machine (SVM), and decision tree (DT), were utilized for model training, and 80 tongue images of 40 patients from Lixin County People\u2019s Hospital in Anhui Province were utilized for external validation. The model performance evaluation indexes included AUC (Area Under the Curve), Sensitivity, Specificity, Positive Predictive Value (PPV), and Negative Predictive Value (NPV).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>t-Distributed Stochastic Neighbor Embedding (t-SNE) visualization based on the test set revealed a distinguishable clustering trend between the two groups. The key classification features included tongue texture uniformity, body morphological features, and color depth. The AUC of the four models was higher than 0.82, confirming that the tongue image features have significant predictive value for HT, and the lower limit of 95% CI for all models was higher than 0.75, indicating that the models had stable differentiation ability. The AUC of SVM (0.894) was the best, significantly higher than the other models (RF: 0.857, LR: 0.876, and DT:0.828), indicating that the SVM possesses the strongest ability to classify patients with and without HT and the highest stability. The SVM exhibited balanced performance, with a sensitivity of 0.804 and specificity of 0.936. Consequently, it represents the optimal model for achieving an equilibrium between recall and precision. In external validation, the efficacy of the four models is notable, and the trend is consistent with the test set. SVM still demonstrates notable performance and possesses the best generalization ability among the four models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The tongue image-based machine learning model can effectively assist in distinguishing euthyroid from hypothyroidism in HT, offering a non-invasive, low-cost, and intelligent tool for auxiliary diagnosis and disease risk monitoring in primary care settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2025.1673891","type":"journal-article","created":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:30:13Z","timestamp":1761715813000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Machine learning-assisted tongue image analysis for the diagnosis of Hashimoto\u2019s thyroiditis"],"prefix":"10.3389","volume":"12","author":[{"given":"Ting","family":"Ruan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingji","family":"Piao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingai","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyou","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxiao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchun","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1038\/nrendo.2018.18","article-title":"Global epidemiology of hyperthyroidism and hypothyroidism","volume":"14","author":"Taylor","year":"2018","journal-title":"Nat Rev Endocrinol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1020709","DOI":"10.3389\/fpubh.2022.1020709","article-title":"Global prevalence and epidemiological trends of Hashimoto's thyroiditis in adults: a systematic review and meta-analysis","volume":"10","author":"Hu","year":"2022","journal-title":"Front Public Health"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1801","DOI":"10.2147\/JMDH.S408117","article-title":"AI-assisted ultrasound for the early diagnosis of antibody-negative autoimmune thyroiditis","volume":"16","author":"Yao","year":"2023","journal-title":"J Multidiscip Healthc"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1210\/jc.2012-2978","article-title":"Clinical review: Hashimoto's thyroiditis and papillary thyroid carcinoma: is there a correlation?","volume":"98","author":"Jankovic","year":"2013","journal-title":"J Clin Endocrinol Metab"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.2741\/4437","article-title":"Ultrasonography in the diagnosis of Hashimoto's thyroiditis","volume":"21","author":"Wu","year":"2016","journal-title":"Front Biosci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"104622","DOI":"10.1016\/j.compbiomed.2021.104622","article-title":"Application of computer tongue image analysis technology in the diagnosis of NAFLD","volume":"135","author":"Jiang","year":"2021","journal-title":"Comput Biol Med"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"107096","DOI":"10.1016\/j.cmpb.2022.107096","article-title":"Human-computer interaction based health diagnostics using ResNet34 for tongue image classification","volume":"226","author":"Zhuang","year":"2022","journal-title":"Comput Methods Prog Biomed"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"105935","DOI":"10.1016\/j.compbiomed.2022.105935","article-title":"A multi-step approach for tongue image classification in patients with diabetes","volume":"149","author":"Li","year":"2022","journal-title":"Comput Biol Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3892\/mco.2023.2684","article-title":"Tongue texture may contribute to the assessment of malignant risk of thyroid nodules","volume":"19","author":"Li","year":"2023","journal-title":"Mol Clin Oncol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"103693","DOI":"10.1016\/j.jbi.2021.103693","article-title":"A tongue features fusion approach to predicting prediabetes and diabetes with machine learning","volume":"115","author":"Li","year":"2021","journal-title":"J Biomed Inform"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"787143","DOI":"10.3389\/fcimb.2022.787143","article-title":"Oral-gut microbiome analysis in patients with metabolic-associated fatty liver disease having different tongue image feature","volume":"12","author":"Lu","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"100493","DOI":"10.1016\/j.imr.2020.100493","article-title":"Tongue features of patients with coronavirus disease 2019: a retrospective cross-sectional study","volume":"9","author":"Pang","year":"2020","journal-title":"Integr Med Res"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"103460","DOI":"10.1016\/j.ebiom.2021.103460","article-title":"Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study","volume":"69","author":"Yu","year":"2021","journal-title":"EBioMedicine"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"e014369","DOI":"10.1161\/CIRCIMAGING.122.014369","article-title":"Machine learning from quantitative coronary computed tomography angiography predicts fractional flow reserve-defined ischemia and impaired myocardial blood flow","volume":"15","author":"Lin","year":"2022","journal-title":"Circ Cardiovasc Imaging"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"14571","DOI":"10.1038\/s41598-024-64150-0","article-title":"Tongue image fusion and analysis of thermal and visible images in diabetes mellitus using machine learning techniques","volume":"14","author":"Thirunavukkarasu","year":"2024","journal-title":"Sci Rep"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"271","DOI":"10.3390\/jpm13020271","article-title":"Construction of tongue image-based machine learning model for screening patients with gastric precancerous lesions","volume":"13","author":"Ma","year":"2023","journal-title":"J Pers Med"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"6","DOI":"10.3760\/j.issn:0578-1426.2007.08.038","article-title":"Chinese Society of Endocrinology. Chinese guidelines for diagnosis and treatment of thyroid diseases: laboratory and auxiliary examinations for thyroid disorders","volume":"46","year":"2007","journal-title":"Chin J Int Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1142\/s0219720005001004","article-title":"Minimum redundancy feature selection from microarray gene expression data","volume":"3","author":"Ding","year":"2005","journal-title":"J Bioinforma Comput Biol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1007\/s10822-022-00442-9","article-title":"Evolution of support vector machine and regression modeling in Chemoinformatics and drug discovery","volume":"36","author":"Rodr\u00edguez-P\u00e9rez","year":"2022","journal-title":"J Comput Aided Mol Des"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.dadm.2018.10.004","article-title":"Decision tree supports the interpretation of CSF biomarkers in Alzheimer's disease","volume":"11","author":"Babapour Mofrad","year":"2019","journal-title":"Alzheimers Dement"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"102649","DOI":"10.1016\/j.autrev.2020.102649","article-title":"Hashimoto's thyroiditis: an update on pathogenic mechanisms, diagnostic protocols, therapeutic strategies, and potential malignant transformation","volume":"19","author":"Ralli","year":"2020","journal-title":"Autoimmun Rev"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.autrev.2014.01.007","article-title":"Hashimoto thyroiditis: clinical and diagnostic criteria","volume":"13","author":"Caturegli","year":"2014","journal-title":"Autoimmun Rev"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"101834","DOI":"10.1016\/j.eclinm.2023.101834","article-title":"Development of a tongue image-based machine learning tool for the diagnosis of gastric cancer: a prospective multicentre clinical cohort study","volume":"57","author":"Yuan","year":"2023","journal-title":"EClinicalMedicine"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.imr.2018.03.001","article-title":"Advances in automated tongue diagnosis techniques","volume":"8","author":"Tania","year":"2019","journal-title":"Integr Med Res."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1186\/s12911-021-01508-8","article-title":"Tongue image quality assessment based on a deep convolutional neural network","volume":"21","author":"Jiang","year":"2021","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"7961494","DOI":"10.1155\/2017\/7961494","article-title":"Diagnostic method of diabetes based on support vector machine and tongue images","volume":"2017","author":"Zhang","year":"2017","journal-title":"Biomed Res Int"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"104429","DOI":"10.1016\/j.ijmedinf.2021.104429","article-title":"Establishment of noninvasive diabetes risk prediction model based on tongue features and machine learning techniques","volume":"149","author":"Li","year":"2021","journal-title":"Int J Med Inform"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1946316","DOI":"10.1080\/20002297.2021.1946316","article-title":"Microbial characteristics across different tongue coating types in a healthy population","volume":"13","author":"Chen","year":"2021","journal-title":"J Oral Microbiol"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1673891\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T05:30:15Z","timestamp":1761715815000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1673891\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":28,"alternative-id":["10.3389\/fmed.2025.1673891"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1673891","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,29]]},"article-number":"1673891"}}