Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics / Kublanov Vladimir S.,Dolganov Anton Yu.,Belo David,Gamboa Hugo // APPLIED BIONICS AND BIOMECHANICS. - 2017. - V. , l. .

ISSN/EISSN:

1176-2322 / 1754-2103

Type:

Article

Abstract:

The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components.

Author keywords:

EMPIRICAL MODE DECOMPOSITION; OBSTRUCTIVE SLEEP-APNEA; HEART-RATE-VARIABILITY; ECG; DYNAMICS; SYSTEM; HEALTH

DOI:

10.1155/2017/5985479

Web of Science ID:

ISI:000407088900001

Соавторы в МНС:

—

Другие поля

Поле	Значение
Publisher	HINDAWI LTD
Address	ADAM HOUSE, 3RD FLR, 1 FITZROY SQ, LONDON, W1T 5HF, ENGLAND
Language	English
Article-Number	5985479
EISSN	1754-2103
Keywords-Plus	EMPIRICAL MODE DECOMPOSITION; OBSTRUCTIVE SLEEP-APNEA; HEART-RATE-VARIABILITY; ECG; DYNAMICS; SYSTEM; HEALTH
Research-Areas	Engineering; Robotics
Web-of-Science-Categories	Engineering, Biomedical; Robotics
Author-Email	kublanov@mail.ru
ResearcherID-Numbers	Dolganov, Anton/O-9365-2017
ORCID-Numbers	Dolganov, Anton/0000-0003-2318-9144
Funding-Acknowledgement	Act 211 Government of the Russian Federation {[}02.A03.21.0006]; FCT {[}AHA CMUP-ERI/HCI/0046/2013]
Funding-Text	The work was supported by the Act 211 Government of the Russian Federation, Contract no. 02.A03.21.0006, and by the FCT project AHA CMUP-ERI/HCI/0046/2013.
Number-of-Cited-References	38
Usage-Count-Last-180-days	3
Usage-Count-Since-2013	3
Journal-ISO	Appl. Bionics Biomech.
Doc-Delivery-Number	FC8JZ