ML-BUSMetab: Machine Learning-Based Metabolomic Profiling for Predicting Aspirin Response in Colorectal Cancer Chemoprevention: A Multi-Model Explainable Artificial Intelligence Approach with External Validation.

Among traditional ML models, pairwise differences between GBM_sklearn and the remaining gradient boosting methods (LightGBM, XGBoost, and CatBoost) did not reach statistical significance after correction (adjusted p > 0.05), suggesting comparable discriminative ability within this model family.

also in 111,027 other papers