Fig. 3From: Strategies for improving the performance of prediction models for response to immune checkpoint blockade therapy in cancerROC curves of the combined dataset for all algorithms Comparison of ROC curves among Random Forest (A), LASSO (B), and XGBoost (C) based on the combined dataset. Each colored dashed curve indicates one tenfold cross validation replicate. The solid black curve indicates the average curve across ten replicates. Results were averaged across ten tenfold cross-validations. The average area under the curve (AUC) were calculated over the ten replicatesBack to article page