Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics
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 a...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2017-01-01
|
| Series: | Applied Bionics and Biomechanics |
| Online Access: | http://dx.doi.org/10.1155/2017/5985479 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832547284657635328 |
|---|---|
| author | Vladimir S. Kublanov Anton Yu. Dolganov David Belo Hugo Gamboa |
| author_facet | Vladimir S. Kublanov Anton Yu. Dolganov David Belo Hugo Gamboa |
| author_sort | Vladimir S. Kublanov |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-56f5896387ad40179f37476c2eb74609 |
| institution | Kabale University |
| issn | 1176-2322 1754-2103 |
| language | English |
| publishDate | 2017-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Applied Bionics and Biomechanics |
| spelling | doaj-art-56f5896387ad40179f37476c2eb746092025-02-03T06:45:25ZengWileyApplied Bionics and Biomechanics1176-23221754-21032017-01-01201710.1155/2017/59854795985479Comparison of Machine Learning Methods for the Arterial Hypertension DiagnosticsVladimir S. Kublanov0Anton Yu. Dolganov1David Belo2Hugo Gamboa3Research Medical and Biological Engineering Centre of High Technologies, Ural Federal University, Mira 19, Yekaterinburg 620002, RussiaResearch Medical and Biological Engineering Centre of High Technologies, Ural Federal University, Mira 19, Yekaterinburg 620002, RussiaLaboratório de Instrumentação, Engenharia Biomédica e Física da Radiação (LIBPhys-UNL), Departamento de Física, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa, Monte da Caparica, 2892-516 Caparica, PortugalLaboratório de Instrumentação, Engenharia Biomédica e Física da Radiação (LIBPhys-UNL), Departamento de Física, Faculdade de Ciências e Tecnologia da Universidade Nova de Lisboa, Monte da Caparica, 2892-516 Caparica, PortugalThe 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.http://dx.doi.org/10.1155/2017/5985479 |
| spellingShingle | Vladimir S. Kublanov Anton Yu. Dolganov David Belo Hugo Gamboa Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics Applied Bionics and Biomechanics |
| title | Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics |
| title_full | Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics |
| title_fullStr | Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics |
| title_full_unstemmed | Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics |
| title_short | Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics |
| title_sort | comparison of machine learning methods for the arterial hypertension diagnostics |
| url | http://dx.doi.org/10.1155/2017/5985479 |
| work_keys_str_mv | AT vladimirskublanov comparisonofmachinelearningmethodsforthearterialhypertensiondiagnostics AT antonyudolganov comparisonofmachinelearningmethodsforthearterialhypertensiondiagnostics AT davidbelo comparisonofmachinelearningmethodsforthearterialhypertensiondiagnostics AT hugogamboa comparisonofmachinelearningmethodsforthearterialhypertensiondiagnostics |