Fig. 1From: Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machinesReceiver-operator characteristic (ROC) curves for a HBV and b HCV summarising the six models under consideration for improving prediction for imbalanced data. The models are: Downsize = simple downsizing; Downsize RF = simple downsizing with random forest variable selection; MDS = multiple downsizing; MDS RF = multiple downsizing with random forest variable selection; SMOTE = Synthetic Minority Oversampling; SMOTE RF = Synthetic Minority Oversampling with random forest variable selectionBack to article page