biostudies-literatureUnknown12Li W<h4>Objective</h4>This study aimed at establishing a new model to predict malignant thyroid nodules using machine learning algorithms.<h4>Methods</h4>A retrospective study was performed on 274 patients with thyroid nodules who underwent fine-needle aspiration (FNA) cytology or surgery from October 2018 to 2020 in Xianyang Central Hospital. The least absolute shrinkage and selection operator (lasso) regression analysis and logistic analysis were applied to screen and identified variables. Six machine learning algorithms, including Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Naive Bayes Classifier (NBC), Random Forest (RF), and Logistic Regression (LR), were employed and compared in constructing the predictive model, coupled with preoperative cliFrontiers in oncology968784https://www.ebi.ac.uk/biostudies/studies/S-EPMC9774948biostudies-literatureIncorporation of a machine learning pathological diagnosis algorithm into the thyroid ultrasound imaging data improves the diagnosis risk of malignant thyroid nodules.PMC9774948He CFang JKang WWang BSun CXu CLiu WLi WLiu YLi XYin CHong TChen YfalseIncorporation of a machine learning pathological diagnosis algorithm into the thyroid ultrasound imaging data improves the diagnosis risk of malignant thyroid nodules.<h4>Objective</h4>This study aimed at establishing a new model to predict malignant thyroid nodules using machine learning algorithms.<h4>Methods</h4>A retrospective study was performed on 274 patients with thyroid nodules who underwent fine-needle aspiration (FNA) cytology or surgery from October 2018 to 2020 in Xianyang Central Hospital. The least absolute shrinkage and selection operator (lasso) regression analysis and logistic analysis were applied to screen and identified variables. Six machine learning algorithms, including Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Naive Bayes Classifier (NBC), Random Forest (RF), and Logistic Regression (LR), were employed and compared in constructing the predictive model, coupled with preoperative cli2022-01-01T00:00:00Z20222025-04-04T21:55:05.201Z2025-04-04T21:55:05.201ZS-EPMC97749483656818910.3389/fonc.2022.968784