Entropy-Based Pattern Learning Based on Singular Spectrum Analysis Components for Assessment of Physiological Signals

Table 9

Performance evaluations for the proposed entropy-based pattern learning to detect the NSR-heart and CHF-heart states from RR-interval signals. SVM and LOOCV are used as pattern classifier and cross-validation strategy, respectively.

Study	EnM	DimEnM	DimIF	Accuracy	Sensitivity	Specificity
Our work	ApEn	12	4	73.49%	44.83%	88.89%
	SampEn	12	7	79.52%	51.72%	94.44%
	FuzzyEn	12	4	86.75%	75.86%	92.59%
	MSEn	12	8	81.93 %	65.52%	90.74%
MSE_RR [57]	MSEn	—	—	74.6%	72.9%	75.0%
MSE_dRR [57]	MSEn	—	—	85.6%	84.4%	86.8%

EnM, entropy measures; DimEnM, dimension of entropy measures; DimIF, dimension of input features.