Imbalanced target prediction with pattern discovery on clinical data repositories

Table 4 F1-scores and G-means of pattern discovery and the referenced non-interpretable methods

Methods	F1-score	G-mean
pattern discovery	0.345 ^a	0.633 ^a
RUSBoost (RUS) [10]	0.302	0.588
SVM + SMOTE (SSVM)	0.338	0.625
boosted SVM for imbalanced data (BSI)	0.375	0.657
JRip + BSI	0.362	0.648
UnderBagging (UB)	0.354	0.651

^aAverage testing results from our experiment; other results reported or projected from the reference [20]

ISSN: 1472-6947