©The Author(s) 2026.
World J Gastroenterol. Jan 21, 2026; 32(3): 115527
Published online Jan 21, 2026. doi: 10.3748/wjg.v32.i3.115527
Published online Jan 21, 2026. doi: 10.3748/wjg.v32.i3.115527
Figure 3 The calibration curve of different machine learning models.
A: Categorical boosting, L1 regularized logistic regression; B: Random forest for predicting thromboembolic events showed good performance. CatBoost: Categorical boosting; LassoLR: L1 regularized logistic regression; SVM: Support vector machines; XGBoost: Extreme gradient boosting.
- Citation: Lu C, Cheng HY, Zhu RK, Zhou YD, Sun KF, Xu L, Sang JZ, Chen JE, Yu CH, Qin YL, Li L. Application of machine learning models in predicting the risk of thromboembolic events in patients with nonvariceal gastrointestinal bleeding. World J Gastroenterol 2026; 32(3): 115527
- URL: https://www.wjgnet.com/1007-9327/full/v32/i3/115527.htm
- DOI: https://dx.doi.org/10.3748/wjg.v32.i3.115527