Fig. 2From: Enhancement of hepatitis virus immunoassay outcome predictions in imbalanced routine pathology data by data balancing and feature selection before the application of support vector machines a Hepatitis B virus (HBV) and b Hepatitis C virus (HCV) SVM plots post SMOTE to overcome HBV/HCV immunoassay class imbalance, and random forest to identify the top three predictors of HBV or HCV positive/negative immunoassay class. For HBV and HCV SVM visualisation, the SVM was sliced at ALT equal to 35Â IU/LBack to article page