Fig. 2: Receiver operating characteristic (ROC) curves and area under the curve (AUC) values for ensemble learning models used in CKD severity classification. | npj Digital Medicine

Fig. 2: Receiver operating characteristic (ROC) curves and area under the curve (AUC) values for ensemble learning models used in CKD severity classification.

From: Ensemble learning approaches for early prediction of chronic kidney disease based on polysomnographic phenotype analysis

Fig. 2: Receiver operating characteristic (ROC) curves and area under the curve (AUC) values for ensemble learning models used in CKD severity classification.

The models evaluated include. a Random Forest, b XGBoost, c LightGBM, and d CatBoost. These ROC curves illustrate the classification performance across different CKD stages, comparing original and oversampled PSG-derived data results.

Back to article page