Table 5.

Parameters with the highest accuracy (mean ± standard deviation), when comparing the groups of patients FG vs RG.

Data Base	Classification Techniques	Reduction Dimensionality Techniques	Parameters Selected	Accuracy (%)
Dataset1	NN	Forward Selection	PF(f/VT), PA(TI/TTot), PA(TI), PA(RR), PA(f/VT), IQR(TTot), IQR(CD1-TI), IQR(RR), IQR(f/VT)	50.00 ± 1.6
		Bidirectional Search	PF(f/VT), PF(TI/TTot), PA(TI), PA(RR), PA(f/VT), P(TTot)	58.36 ± 1.3
Dataset2	NN	Forward Selection	S(CD1-TTot), $\overline{X}$(CD1-f/VT), IQR(CD1-f/VT), K(CD2-RR), Sk(CD1-f/VT), K(CD1-f/VT)	83.31 ± 3.4
		Bidirectional Search	S(CD1-TTot),$\overline{X}$(CD1-f/VT), IQR(CD1-f/VT), K(CD2-RR), Sk(CD1-f/VT), K(CD1-f/VT), S(CD1-f/VT), $\overline{X}$(CA5-TI/TTot), S(CD1-TI), K(CD1-TTot), Sk(CD1-TTot), IQR(CD2-RR), K(CD4-TE)	91.62 ± 4.9
Dataset1	LDA	Forward Selection	PF(f/VT), PA(f/VT), PA(TE), PA(TI/TTot), P(f/VT)	76.00 ± 10.8
		Bidirectional Search	$\overline{X}$(CD2-RR), S(CD2-RR)	75.34 ± 11.3
Dataset2	LDA	Forward Selection	PA(f/VT), IQR(TTot)	75.36 ± 11.3
		Bidirectional Search	$\overline{X}$(CD2-RR)	80.15 ± 10.6