Fig. 4From: Advanced gastrointestinal stromal tumor: reliable classification of imatinib plasma trough concentration via machine learningThe performance of the XGBoost model was evaluated by tenfold cross‐validation in the training set and internal validation in the test set. A The mean AUROC for the XGBoost model in the training set (AUROC = 0.881). B The mean AUROC for the XGBoost model in the validation set (AUROC = 0.699). C The AUROC for the XGBoost model in the test set (AUROC = 0.725). D In the learning curve, the red dashed line represents the training set and the blue dashed line represents the validation set. Abbreviations: XGBoost, Extreme Gradient Boosting; AUROC, area under the receiver-operating characteristic curve; ROC, receiver operating characteristic; AUC, area under curveBack to article page