Application of machine learning models in predicting the risk of thromboembolic events in patients with nonvariceal gastrointestinal bleeding

Figure 2 The area under the receiver operating characteristic curve of different machine learning models with the internal validation set and the external validation set. A: The area under the receiver operating characteristic curve of different machine learning models with the internal validation set; B: The area under the receiver operating characteristic curve of different machine learning L models with the external validation set. CatBoost: Categorical boosting; LassoLR: L1 regularized logistic regression; SVM: Support vector machines; XGBoost: Extreme gradient boosting.