Utilizing machine learning for early screening of thyroid nodules: a dual-center cross-sectional study in China

作者全名：Weng, Shuwei; Ding, Chen; Hu, Die; Chen, Jin; Liu, Yang; Liu, Wenwu; Chen, Yang; Guo, Xin; Cao, Chenghui; Yi, Yuting; Yang, Yanyi; Peng, Daoquan

作者地址：[Weng, Shuwei; Hu, Die; Chen, Jin; Liu, Wenwu; Chen, Yang; Guo, Xin; Cao, Chenghui; Yi, Yuting; Peng, Daoquan] Cent South Univ, Xiangya Hosp 2, Dept Cardiol, Changsha, Hunan, Peoples R China; [Weng, Shuwei; Hu, Die; Chen, Jin; Liu, Wenwu; Chen, Yang; Guo, Xin; Cao, Chenghui; Yi, Yuting; Peng, Daoquan] Res Inst Blood Lipid & Atherosclerosis, Changsha, Hunan, Peoples R China; [Ding, Chen] Soochow Univ, Affiliated Hosp 4, Suzhou Dushu Lake Hosp, Dept Cardiol,Med Ctr, Suzhou, Jiangsu, Peoples R China; [Liu, Yang] Third Mil Med Univ, Xinqiao Hosp,Army Med Univ, Chongqing Clin Res Ctr Kidney & Urol Dis, Dept Nephrol,Key Lab Prevent & Treatment Chron Kid, Chongqing, Peoples R China; [Yang, Yanyi] Cent South Univ, Xiangya Hosp 2, Hlth Management Ctr, Changsha, Hunan, Peoples R China; [Yang, Yanyi] Hunan Prov Clin Med Res Ctr Intelligent Management, Changsha, Hunan, Peoples R China

通信作者：Peng, DQ (通讯作者)，Cent South Univ, Xiangya Hosp 2, Dept Cardiol, Changsha, Hunan, Peoples R China.; Peng, DQ (通讯作者)，Res Inst Blood Lipid & Atherosclerosis, Changsha, Hunan, Peoples R China.; Yang, YY (通讯作者)，Cent South Univ, Xiangya Hosp 2, Hlth Management Ctr, Changsha, Hunan, Peoples R China.; Yang, YY (通讯作者)，Hunan Prov Clin Med Res Ctr Intelligent Management, Changsha, Hunan, Peoples R China.

来源：FRONTIERS IN ENDOCRINOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001256845200001

JCR分区：Q2

影响因子：3.9

年份：2024

卷号：15

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：thyroid nodule; machine learning; early screening; urine iodine; ensemble learning methods

摘要：Background Thyroid nodules, increasingly prevalent globally, pose a risk of malignant transformation. Early screening is crucial for management, yet current models focus mainly on ultrasound features. This study explores machine learning for screening using demographic and biochemical indicators.Methods Analyzing data from 6,102 individuals and 61 variables, we identified 17 key variables to construct models using six machine learning classifiers: Logistic Regression, SVM, Multilayer Perceptron, Random Forest, XGBoost, and LightGBM. Performance was evaluated by accuracy, precision, recall, F1 score, specificity, kappa statistic, and AUC, with internal and external validations assessing generalizability. Shapley values determined feature importance, and Decision Curve Analysis evaluated clinical benefits.Results Random Forest showed the highest internal validation accuracy (78.3%) and AUC (89.1%). LightGBM demonstrated robust external validation performance. Key factors included age, gender, and urinary iodine levels, with significant clinical benefits at various thresholds. Clinical benefits were observed across various risk thresholds, particularly in ensemble models.Conclusion Machine learning, particularly ensemble methods, accurately predicts thyroid nodule presence using demographic and biochemical data. This cost-effective strategy offers valuable insights for thyroid health management, aiding in early detection and potentially improving clinical outcomes. These findings enhance our understanding of the key predictors of thyroid nodules and underscore the potential of machine learning in public health applications for early disease screening and prevention.

基金机构：National Natural Science Foundation of China [81870336, 82100496]; Scientific Research Launch Project for new employees of the Second Xiangya Hospital of Central South University

基金资助正文：The author(s) declare financial support was received for the research, authorship, and/or publication of this article. This study was supported by the National Natural Science Foundation of China(Grant No. 81870336 to DP and Grant No. 82100496 to DH) and the Scientific Research Launch Project for new employees of the Second Xiangya Hospital of Central South University (to DH).