Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

Table 4

Best classification scores.

Score, %	Features
Linear discriminant analysis
91.33 ± 1.75	HR	VLFn(Fr)	LF/HF(Fr)	VLF(wt)
90.30 ± 1.37	HR	VLFn(Fr)	VLF(wt)	(LF/HF)int
90.04 ± 1.85	HR	LF/HF(Fr)	VLF(wt)	VLFn(wt)
90.44 ± 1.60	HR	VLFn(Fr)	LF/HF(Fr)	SDVLF
90.11 ± 1.80	HR	LF/HF(Fr)	SDVLF	VLFn(wt)
90.16 ± 1.61	HR	SDVLF	VLFn(wt)	(LF/HF)int
Quadratic discriminant analysis
90.31 ± 1.71	HR	VLFn(Fr)	LF/HF(Fr)	VLF(wt)
3-nearest neighbors
87.14 ± 2.12	LF/HF(Fr)	SDVLF	VLFn(wt)	W1/2VLF
4-nearest neighbors
85.56 ± 2.40	SDVLF	VLFn(wt)	LF/HF(wt)	W1/2VLF
5-nearest neighbors
86.63 ± 1.30	HR	HF(Fr)	LFn(Fr)	W1/2VLF
Support vector machine, radial base function
86.73 ± 2.24	IAS	RF	a2LF	WVLF
Decision trees, max depth 5
87.10 ± 3.40	IARP	LF/HF(Fr)	IAS	WLF
Decision trees, no max depth
87.34 ± 3.08	IARP	LF/HF(Fr)	IAS	WLF
Naïve Bayes classifier
88.17 ± 1.07	VLF(Fr)	VLFn(Fr)	LF/HF(Fr)	W1/2LF