Comparison of machine learning methods for the arterial hypertension diagnostics

Vladimir S. Kublanov, Anton Yu Dolganov, David Belo, Hugo Gamboa

Research output: Contribution to journalArticle

12 Citations (Scopus)
3 Downloads (Pure)

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.

Original languageEnglish
Article number5985479
JournalApplied Bionics and Biomechanics
Volume2017
DOIs
Publication statusPublished - 2017

Fingerprint

Discriminant Analysis
Discriminant analysis
Learning systems
Hypertension
Decision Trees
Decision trees
Support vector machines
Feature extraction
Healthy Volunteers
Classifiers
Heart Rate
Machine Learning
Support Vector Machine
Datasets

Keywords

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

Cite this

Kublanov, Vladimir S. ; Dolganov, Anton Yu ; Belo, David ; Gamboa, Hugo. / Comparison of machine learning methods for the arterial hypertension diagnostics. In: Applied Bionics and Biomechanics. 2017 ; Vol. 2017.
@article{feebbc0ad6414955b1a8644ba657e3e2,
title = "Comparison of machine learning methods for the arterial hypertension diagnostics",
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.",
keywords = "EMPIRICAL MODE DECOMPOSITION, OBSTRUCTIVE SLEEP-APNEA, HEART-RATE-VARIABILITY, ECG, DYNAMICS, SYSTEM, HEALTH",
author = "Kublanov, {Vladimir S.} and Dolganov, {Anton Yu} and David Belo and Hugo Gamboa",
note = "Act 211 Government of the Russian Federation (02.A03.21.0006) FCT (AHA CMUP-ERI/HCI/0046/2013)",
year = "2017",
doi = "10.1155/2017/5985479",
language = "English",
volume = "2017",
journal = "Applied Bionics and Biomechanics",
issn = "1176-2322",
publisher = "IOS Press",

}

Comparison of machine learning methods for the arterial hypertension diagnostics. / Kublanov, Vladimir S.; Dolganov, Anton Yu; Belo, David; Gamboa, Hugo.

In: Applied Bionics and Biomechanics, Vol. 2017, 5985479, 2017.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Comparison of machine learning methods for the arterial hypertension diagnostics

AU - Kublanov, Vladimir S.

AU - Dolganov, Anton Yu

AU - Belo, David

AU - Gamboa, Hugo

N1 - Act 211 Government of the Russian Federation (02.A03.21.0006) FCT (AHA CMUP-ERI/HCI/0046/2013)

PY - 2017

Y1 - 2017

N2 - 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.

AB - 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.

KW - EMPIRICAL MODE DECOMPOSITION

KW - OBSTRUCTIVE SLEEP-APNEA

KW - HEART-RATE-VARIABILITY

KW - ECG

KW - DYNAMICS

KW - SYSTEM

KW - HEALTH

UR - http://www.scopus.com/inward/record.url?scp=85031328575&partnerID=8YFLogxK

U2 - 10.1155/2017/5985479

DO - 10.1155/2017/5985479

M3 - Article

VL - 2017

JO - Applied Bionics and Biomechanics

JF - Applied Bionics and Biomechanics

SN - 1176-2322

M1 - 5985479

ER -