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

Figure 4 The decision curve analysis of different machine learning models. The results showed that compared with the D-dimer, all machine learning models demonstrated higher net benefits across most threshold probability ranges. CatBoost: Categorical boosting; LassoLR: L1 regularized logistic regression; SVM: Support vector machines; XGBoost: Extreme gradient boosting.