Table 3.

Cross-validation results for different feature representations using class and probabilistic information.

Features	Dimension	ACC	Sn	Sp	MCC	AUC
PF	130	0.858	0.840	0.876	0.722	0.914
CF	130	0.838	0.848	0.828	0.684	0.895
PCF	260	0.864	0.880	0.848	0.733	0.920
Optimal PF	50	0.868	0.884	0.852	0.743	0.920
Optimal CF	5	0.868	0.880	0.856	0.743	0.902
Optimal PCF	5	0.868	0.884	0.852	0.741	0.907