22 June 2026 : Clinical Research
Development and Validation of Machine-Learning-Based Prediction Models for Thyroid Diseases During Pregnancy
Guang Yang BCDEF 1, Yi Gao BCEF 1, Pengfei Liu BC 1, Jingwen Jiang BC 1, Hui Qiao ADEG 1*, Weixuan Sheng
ACDE 1
DOI: 10.12659/MSM.953235
Med Sci Monit 2026; 32:e953235
Figure 3 Model comparison and selectionThe figure shows the performance of 8 models (LR, Bayes, KNN, SVM, NNET, CART, XGBoost, and RF) using ROC and PRC to predict thyroid disease during pregnancy. (A) ROC curves of the 8 models; (B) PRCs of the 8 models. Abbreviations: Bayes, Bayesian approach; CART, classification and regression tree; KNN, k-nearest neighbors; LR, logistic regression; NNET, neural network; PRC, precision-recall curve; RF, random forest; ROC, receiver operating characteristic curve; SVM, support vector machine; XGBoost, extreme gradient boosting.