{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T15:56:49Z","timestamp":1787673409798,"version":"build-2736575974"},"reference-count":38,"publisher":"BMJ","issue":"5","license":[{"start":{"date-parts":[[2025,5,6]],"date-time":"2025-05-06T00:00:00Z","timestamp":1746489600000},"content-version":"unspecified","delay-in-days":5,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,4,22]]},"published-print":{"date-parts":[[2025,5]]},"abstract":"<jats:sec><jats:title>Objectives<\/jats:title><jats:p>To develop and validate a machine learning (ML) model to differentiate malignant from benign thyroid nodules (TNs) based on the routine data and provide diagnostic assistance for medical professionals.<\/jats:p><\/jats:sec><jats:sec><jats:title>Setting<\/jats:title><jats:p>A qualified panel of 1649 patients with TNs from one hospital were stratified by gender, age, free triiodothyronine (FT3), free thyroxine (FT4) and thyroid peroxidase antibody (TPOAB).<\/jats:p><\/jats:sec><jats:sec><jats:title>Participants<\/jats:title><jats:p>Thyroid function (TF) data of 1649 patients with TNs were collected in a single centre from January 2018 to June 2022, with a total of 273 males and 1376 females, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Measures<\/jats:title><jats:p>Seven popular ML models (Random Forest, Decision Tree, Logistic Regression (LR), K-Neighbours, Gaussian Naive Bayes, Multilayer Perception and Gradient Boosting) were developed to predict malignant and benign TNs, whose performance indicators included area under the curve (AUC), accuracy, recall, precision and F1 score.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>A total of 1649 patients were enrolled in this study, with the median age of 45.15\u00b113.41 years, and the male to female ratio was 1:5.055. In the multivariate LR analysis, statistically significant differences existed between the TNs group and thyroid cancer group in gender, age, free triiodothyronine (FT3), free thyroxine (FT4) and TPOAB. Among the seven tested ML models, the best performance was achieved in the Gradient Boosting model in terms of precision, AUC, accuracy, recall and F1 score, with the AUC of 0.82, accuracy of 79.4% and precision of 0.814 after experimental verification. FT4, TPOAB and FT3 were validated as the top three features in the Gradient Boosting model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study innovatively developed a predictive model for benign and malignant TNs based on the Gradient Boosting Decision Tree algorithm. For the first time, it validated the clinical predictive value of TF parameters (FT4, FT3) and TPOAB as key biomarkers.<\/jats:p><\/jats:sec>","DOI":"10.1136\/bmjopen-2024-093466","type":"journal-article","created":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T11:15:42Z","timestamp":1746616542000},"page":"e093466","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":4,"title":["Machine learning model for differentiating malignant from benign thyroid nodules based on the thyroid function data"],"prefix":"10.1136","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7792-7432","authenticated-orcid":false,"given":"Fuqiang","family":"Ma","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fengchang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenhui","family":"Lv","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhilin","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He-Rong","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lele","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0347-1580","authenticated-orcid":false,"given":"Nan","family":"Xiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,5,7]]},"reference":[{"key":"2025050704152524000_15.5.e093466.1","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":"JAMA"},{"key":"2025050704152524000_15.5.e093466.2","doi-asserted-by":"crossref","DOI":"10.1186\/s12902-022-01119-y","article-title":"The association of uric acid with the development of thyroid nodules: a retrospective cohort study","volume":"22","author":"Huang","year":"2022","journal-title":"BMC Endocr Disord"},{"key":"2025050704152524000_15.5.e093466.3","doi-asserted-by":"crossref","DOI":"10.3389\/fendo.2023.1113977","article-title":"Thyroid nodules: Global, economic, and personal burdens","volume":"14","author":"Uppal","year":"2023","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2025050704152524000_15.5.e093466.4","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1016\/j.suc.2014.02.004","article-title":"Evaluation of thyroid incidentaloma","volume":"94","author":"Wilhelm","year":"2014","journal-title":"Surg Clin North Am"},{"key":"2025050704152524000_15.5.e093466.5","doi-asserted-by":"publisher","DOI":"10.1038\/s41574-019-0263-x"},{"key":"2025050704152524000_15.5.e093466.6","first-page":"350","article-title":"A Comparison of the Burden of Thyroid Cancer Among the European Union 15+Countries, 1990-2019 Estimates From the Global Burden of Disease Study","volume":"148","author":"Schuster-Bruce","year":"2022","journal-title":"Jama Otolaryngol"},{"key":"2025050704152524000_15.5.e093466.7","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.28562"},{"key":"2025050704152524000_15.5.e093466.8","doi-asserted-by":"crossref","DOI":"10.3390\/cancers14143357","article-title":"Artificial Intelligence for Thyroid Nodule Characterization: Where Are We Standing?","volume":"14","author":"Sorrenti","year":"2022","journal-title":"Cancers (Basel)"},{"key":"2025050704152524000_15.5.e093466.9","doi-asserted-by":"publisher","DOI":"10.1089\/thy.2015.0020"},{"key":"2025050704152524000_15.5.e093466.10","doi-asserted-by":"crossref","DOI":"10.12659\/MSM.937738","article-title":"A Review of the Role of Ultrasound Radiomics and Its Application and Limitations in the Investigation of Thyroid Disease","volume":"28","author":"Lu","year":"2022","journal-title":"Med Sci Monit"},{"key":"2025050704152524000_15.5.e093466.11","doi-asserted-by":"crossref","first-page":"597","DOI":"10.17219\/acem\/146776","article-title":"Thyroid nodule ultrasound accuracy in predicting thyroid malignancy based on TIRADS system","volume":"31","author":"Nie","year":"2022","journal-title":"Adv Clin Exp Med"},{"key":"2025050704152524000_15.5.e093466.12","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-017-05459-x","article-title":"Intraoperative frozen section can be reduced in thyroid nodules classified as Bethesda categories V and VI","volume":"7","author":"Huang","year":"2017","journal-title":"Sci Rep"},{"key":"2025050704152524000_15.5.e093466.13","doi-asserted-by":"crossref","first-page":"14","DOI":"10.3389\/fendo.2023.1091200","article-title":"Combined fine-needle aspiration and selective intraoperative frozen section to optimize prediction of malignant thyroid nodules: A retrospective cohort study of more than 3000 patients","volume":"14","author":"Mao","year":"2023","journal-title":"Front Endocrinol"},{"key":"2025050704152524000_15.5.e093466.14","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s40477-020-00453-y","article-title":"Computer-aided diagnostic system for thyroid nodule sonographic evaluation outperforms the specificity of less experienced examiners","volume":"23","author":"Fresilli","year":"2020","journal-title":"J Ultrasound"},{"key":"2025050704152524000_15.5.e093466.15","doi-asserted-by":"crossref","DOI":"10.3389\/fendo.2020.577537","article-title":"Machine Learning Algorithms for the Prediction of Central Lymph Node Metastasis in Patients With Papillary Thyroid Cancer","volume":"11","author":"Wu","year":"2020","journal-title":"Front Endocrinol (Lausanne)"},{"key":"2025050704152524000_15.5.e093466.16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2214\/AJR.22.27430","article-title":"Artificial Intelligence (AI) Tools for Thyroid Nodules on Ultrasound, From the AJR Special Series on AI Applications","volume":"219","author":"Wildman-Tobriner","year":"2022","journal-title":"AJR Am J Roentgenol"},{"key":"2025050704152524000_15.5.e093466.17","doi-asserted-by":"crossref","first-page":"1312","DOI":"10.1007\/s11547-021-01393-1","article-title":"Magnetic resonance imaging (MRI) radiomics of papillary thyroid cancer (PTC): a comparison of predictive performance of multiple classifiers modeling to identify cervical lymph node metastases before surgery","volume":"126","author":"Qin","year":"2021","journal-title":"Radiol Med"},{"key":"2025050704152524000_15.5.e093466.18","first-page":"171","article-title":"A pilot study of radiomics signature based on biparametric MRI for preoperative prediction of extrathyroidal extension in papillary thyroid carcinoma","volume":"29","author":"He","year":"2021","journal-title":"J Xray Sci Technol"},{"key":"2025050704152524000_15.5.e093466.19","doi-asserted-by":"crossref","DOI":"10.1155\/2021\/3984463","article-title":"Identification of Potential lncRNAs and miRNAs as Diagnostic Biomarkers for Papillary Thyroid Carcinoma Based on Machine Learning","volume":"2021","author":"Yang","year":"2021","journal-title":"Int J Endocrinol"},{"key":"2025050704152524000_15.5.e093466.20","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgaa950"},{"key":"2025050704152524000_15.5.e093466.21","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-16-0845"},{"key":"2025050704152524000_15.5.e093466.22","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1093\/humrep\/dex216","article-title":"Factors influencing women\u2019s preferences for subsequent management in the event of incomplete evacuation of the uterus after misoprostol treatment for miscarriage","volume":"32","author":"Hentzen","year":"2017","journal-title":"Hum Reprod"},{"key":"2025050704152524000_15.5.e093466.23","doi-asserted-by":"publisher","DOI":"10.1016\/j.pec.2010.10.031"},{"key":"2025050704152524000_15.5.e093466.24","doi-asserted-by":"publisher","DOI":"10.1001\/jama.286.15.1897"},{"key":"2025050704152524000_15.5.e093466.25","doi-asserted-by":"crossref","DOI":"10.3389\/fcvm.2023.1093363","article-title":"Infective endocarditis: Do we have an effective risk score model? A systematic review","volume":"10","author":"Rizzo","year":"2023","journal-title":"Front Cardiovasc Med"},{"key":"2025050704152524000_15.5.e093466.26","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2021.635771","article-title":"Application of Machine Learning Algorithms to Predict Central Lymph Node Metastasis in T1-T2, Non-invasive, and Clinically Node Negative Papillary Thyroid Carcinoma","volume":"8","author":"Zhu","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"2025050704152524000_15.5.e093466.27","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/9919269","article-title":"Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review","volume":"2023","author":"Xu","year":"2023","journal-title":"J Healthc Eng"},{"key":"2025050704152524000_15.5.e093466.28","doi-asserted-by":"crossref","DOI":"10.1093\/jnci\/dju097","article-title":"Thyroid-stimulating hormone, thyroglobulin, and thyroid hormones and risk of differentiated thyroid carcinoma: the EPIC study","volume":"106","author":"Rinaldi","year":"2014","journal-title":"J Natl Cancer Inst"},{"key":"2025050704152524000_15.5.e093466.29","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1007\/s40618-018-0968-z","article-title":"Association of benign thyroid diseases with thyroid cancer risk: a meta-analysis of prospective observational studies","volume":"42","author":"Liang","year":"2019","journal-title":"J Endocrinol Invest"},{"key":"2025050704152524000_15.5.e093466.30","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1002\/hed.25691","article-title":"Fasting serum glucose, thyroid\u2010stimulating hormone, and thyroid hormones and risk of papillary thyroid cancer: A case\u2010control study","volume":"41","author":"Hu","year":"2019","journal-title":"Head Neck"},{"key":"2025050704152524000_15.5.e093466.31","doi-asserted-by":"crossref","first-page":"936","DOI":"10.1093\/humrep\/deac048","article-title":"Predicting the likelihood of successful medical treatment of early pregnancy loss: development and internal validation of a clinical prediction model","volume":"37","author":"Hamel","year":"2022","journal-title":"Hum Reprod"},{"key":"2025050704152524000_15.5.e093466.32","doi-asserted-by":"publisher","DOI":"10.1210\/jc.2015-3100"},{"key":"2025050704152524000_15.5.e093466.33","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-010-9316-6"},{"key":"2025050704152524000_15.5.e093466.34","doi-asserted-by":"crossref","first-page":"2277","DOI":"10.1002\/hed.25691","article-title":"Fasting serum glucose, thyroid-stimulating hormone, and thyroid hormones and risk of papillary thyroid cancer: A case-control study","volume":"41","author":"Hu","year":"2019","journal-title":"Head Neck"},{"key":"2025050704152524000_15.5.e093466.35","doi-asserted-by":"crossref","first-page":"13","DOI":"10.3389\/fendo.2022.992566","article-title":"The associations between thyroid-related hormones and the risk of thyroid cancer: An overall and dose-response meta-analysis","volume":"13","author":"Wang","year":"2022","journal-title":"Front Endocrinol"},{"key":"2025050704152524000_15.5.e093466.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.endonu.2014.06.002"},{"key":"2025050704152524000_15.5.e093466.37","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3343\/alm.2019.39.1.3","article-title":"Laboratory Testing in Thyroid Conditions - Pitfalls and Clinical Utility","volume":"39","author":"Soh","year":"2019","journal-title":"Ann Lab Med"},{"key":"2025050704152524000_15.5.e093466.38","first-page":"313","article-title":"Both thyroid autoimmunity and increased serum TSH are independent risk factors for malignancy in patients with thyroid nodules","volume":"36","author":"Boi","year":"2013","journal-title":"J Endocrinol Invest"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-093466","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T11:15:47Z","timestamp":1746616547000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-093466"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":38,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5,7]]},"published-print":{"date-parts":[[2025,5]]}},"alternative-id":["10.1136\/bmjopen-2024-093466"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-093466","relation":{},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}