The use of class imbalanced learning methods on ULSAM data to predict the case–control status in genome-wide association studies

Journal of Big Data

Table 6 The performances of support vector machine with imbalanced learning methods with using clumped SNPs

Imbalanced learning methods number of SNP 29		Prediction class		PPV*	NPV**	Sensitivity	Specificity	F1 score	Accuracy
SVM		Controls	Cases
Reel class	Controls	278	0	0.00	0.83	0.00	1.00	0.00	0.83
Reel class	Cases	57	0	0.00	0.83	0.00	1.00	0.00	0.83
SMOTE		Controls	Cases
Reel class	Controls	190	84	0.76	0.85	0.89	0.69	0.82	0.79
Reel class	Cases	34	263	0.76	0.85	0.89	0.69	0.82	0.79
SVM SMOTE		Controls	Cases
Reel class	Controls	225	53	0.81	0.77	0.77	0.81	0.79	0.79
Reel class	Cases	67	226	0.81	0.77	0.77	0.81	0.79	0.79
ADASYN		Controls	Cases
Reel class	Controls	201	83	0.75	0.83	0.86	0.71	0.80	0.78
Reel class	Cases	42	249	0.75	0.83	0.86	0.71	0.80	0.78
RUS		Controls	Cases
Reel class	Controls	44	12	0.72	0.79	0.72	0.79	0.72	0.76
Reel class	Cases	12	31	0.72	0.79	0.72	0.79	0.72	0.76