Prediagnosis of Obstructive Sleep Apnea via Multiclass MTS

Table 4

A comparison.

Method	Selected attributes	Pattern	Accuracy (%)
MMTS	Age, weight, SBP, DBP, DI3 DI4	normal	87.5%	Average
		mild	66.67%	84.38%
		moderate	100%
		severe	83.33%
Logistic Regression	Gender, age, height, weight, BMI, SBP, DBP, ESS, SOS, DI3, DI4, PLM	normal	50.00%	55.33%
		mild	50.00%
		moderate	33.33%
		severe	100.00%
BPN	Gender, age, height, weight, BMI, SBP, DBP, ESS, SOS, DI3, DI4, PLM	normal	25.00%	34.04%
		mild	33.33%
		moderate	11.11%
		severe	66.70%
LVQ	Gender, age, height, weight, BMI, SBP, DBP, ESS, SOS, DI3, DI4, PLM	normal	50.00%	47.22%
		mild	16.67%
		moderate	22.22%
		severe	100.00%
SVM	Age, height, weight, BMI, SBP, DBP, ESS, SOS, DI3, DI4, PLM	normal	37.50%	53.82%
		mild	66.67%
		moderate	11.11%
		severe	100.00%
C4.5	Age, weight, BMI, SBP, SOS, DI4	normal	37.50%	63.54%
		mild	50.00%
		moderate	66.67%
		severe	100.00%
RS	Gender, Age, weight, SBP, ESS, SOS	normal	25.00%	13.20%
		mild	16.67%
		moderate	11.11%
		severe	0.00%