A New Approach of Phonocardiogram Analysis for Screening Some of Cardio-vascular Diseases Based on Deep Learning
Background: Cardiovascular diseases are one of the leading causes of death worldwide. Therefore, early diagnosis of heart disease, evaluation of cardiovascular system using cardiac hearing and Phonocardiogram (PCG) analysis which is a low cost, non-invasive, rapid method, and automatic screening of...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | fas |
Published: |
Isfahan University of Medical Sciences
2022-04-01
|
Series: | مجله دانشکده پزشکی اصفهان |
Subjects: | |
Online Access: | https://jims.mui.ac.ir/article_16314_409703be8e0bdb09d476f63da82cc924.pdf |
_version_ | 1797723341091504128 |
---|---|
author | Ehsan Mohammadi Saeed Kermani Mahdi Nourian-Zavareh Alale Zare Hamed Aghapanah-Roudsari Maryam Samieinasab Hamid Sanei |
author_facet | Ehsan Mohammadi Saeed Kermani Mahdi Nourian-Zavareh Alale Zare Hamed Aghapanah-Roudsari Maryam Samieinasab Hamid Sanei |
author_sort | Ehsan Mohammadi |
collection | DOAJ |
description | Background: Cardiovascular diseases are one of the leading causes of death worldwide. Therefore, early diagnosis of heart disease, evaluation of cardiovascular system using cardiac hearing and Phonocardiogram (PCG) analysis which is a low cost, non-invasive, rapid method, and automatic screening of cardiovascular patients in remote areas is crucial. The aim of this study is to present a new method for screening heart patients based on signal processing (PCG) that is cheap and fast and has sufficient accuracy.Methods: In this study, for screening 2062 labeled PCG signals, by extracting new features and applying them in 1- Random forest network 2- K-nearest neighbors 3- Decision tree 4- Linear discriminant analysis 5- Logistic regression and 6- Deep neural network, six different models were constructed and each of them was evaluated by k fold cross-validation method (K = 10). The test data were applied to the mentioned models and based on the outputs of these models, three indicators of accuracy, sensitivity and specificity were calculated. We showed and developed a new solution in differentiating and screening some heart patients from healthy individuals using PCG analysis.Findings: Evaluation on the mentioned models was calculated by the three indicators, repeated 5 times and their mean and variance values were calculated. The highest sensitivity value is related to deep neural network (DNN) with sensitivity of 96.4 ± 0.14 and accuracy of 93.4 ± 0.11.Conclusion: The new differential features along with the success of the proposed deep neural network in differentiating and screening between PCGs of healthy individuals and heart patients, shows the efficiency of the proposed algorithm. This method can be further improved with simultaneous multimodal classifier and the application of the voting rule. |
first_indexed | 2024-03-12T10:01:28Z |
format | Article |
id | doaj.art-83794cc8decf4008bbdf52ff110df05c |
institution | Directory Open Access Journal |
issn | 1027-7595 1735-854X |
language | fas |
last_indexed | 2024-03-12T10:01:28Z |
publishDate | 2022-04-01 |
publisher | Isfahan University of Medical Sciences |
record_format | Article |
series | مجله دانشکده پزشکی اصفهان |
spelling | doaj.art-83794cc8decf4008bbdf52ff110df05c2023-09-02T11:40:52ZfasIsfahan University of Medical Sciencesمجله دانشکده پزشکی اصفهان1027-75951735-854X2022-04-014066110911410.48305/jims.2022.1631416314A New Approach of Phonocardiogram Analysis for Screening Some of Cardio-vascular Diseases Based on Deep LearningEhsan Mohammadi0Saeed Kermani1Mahdi Nourian-Zavareh2Alale Zare3Hamed Aghapanah-Roudsari4Maryam Samieinasab5Hamid Sanei6PhD Student, Department of Bioelectrics and Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranProfessor, Department of Bioelectrics and Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranMSc Graduate, Department of Bioelectrics and Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranMSc Graduate, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran5- PhD Student, Department of Bioelectrics and Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranPhD Student, Department of Bioelectrics and Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, IranProfessor of Cardiology, School of Medicine, Isfahan University of Medical Sciences, Isfahan, IranBackground: Cardiovascular diseases are one of the leading causes of death worldwide. Therefore, early diagnosis of heart disease, evaluation of cardiovascular system using cardiac hearing and Phonocardiogram (PCG) analysis which is a low cost, non-invasive, rapid method, and automatic screening of cardiovascular patients in remote areas is crucial. The aim of this study is to present a new method for screening heart patients based on signal processing (PCG) that is cheap and fast and has sufficient accuracy.Methods: In this study, for screening 2062 labeled PCG signals, by extracting new features and applying them in 1- Random forest network 2- K-nearest neighbors 3- Decision tree 4- Linear discriminant analysis 5- Logistic regression and 6- Deep neural network, six different models were constructed and each of them was evaluated by k fold cross-validation method (K = 10). The test data were applied to the mentioned models and based on the outputs of these models, three indicators of accuracy, sensitivity and specificity were calculated. We showed and developed a new solution in differentiating and screening some heart patients from healthy individuals using PCG analysis.Findings: Evaluation on the mentioned models was calculated by the three indicators, repeated 5 times and their mean and variance values were calculated. The highest sensitivity value is related to deep neural network (DNN) with sensitivity of 96.4 ± 0.14 and accuracy of 93.4 ± 0.11.Conclusion: The new differential features along with the success of the proposed deep neural network in differentiating and screening between PCGs of healthy individuals and heart patients, shows the efficiency of the proposed algorithm. This method can be further improved with simultaneous multimodal classifier and the application of the voting rule.https://jims.mui.ac.ir/article_16314_409703be8e0bdb09d476f63da82cc924.pdfcardiovascular diagnostic technicdeep learningdiagnostic screening programscardiovascular diseases |
spellingShingle | Ehsan Mohammadi Saeed Kermani Mahdi Nourian-Zavareh Alale Zare Hamed Aghapanah-Roudsari Maryam Samieinasab Hamid Sanei A New Approach of Phonocardiogram Analysis for Screening Some of Cardio-vascular Diseases Based on Deep Learning مجله دانشکده پزشکی اصفهان cardiovascular diagnostic technic deep learning diagnostic screening programs cardiovascular diseases |
title | A New Approach of Phonocardiogram Analysis for Screening Some of
Cardio-vascular Diseases Based on Deep Learning |
title_full | A New Approach of Phonocardiogram Analysis for Screening Some of
Cardio-vascular Diseases Based on Deep Learning |
title_fullStr | A New Approach of Phonocardiogram Analysis for Screening Some of
Cardio-vascular Diseases Based on Deep Learning |
title_full_unstemmed | A New Approach of Phonocardiogram Analysis for Screening Some of
Cardio-vascular Diseases Based on Deep Learning |
title_short | A New Approach of Phonocardiogram Analysis for Screening Some of
Cardio-vascular Diseases Based on Deep Learning |
title_sort | new approach of phonocardiogram analysis for screening some of cardio vascular diseases based on deep learning |
topic | cardiovascular diagnostic technic deep learning diagnostic screening programs cardiovascular diseases |
url | https://jims.mui.ac.ir/article_16314_409703be8e0bdb09d476f63da82cc924.pdf |
work_keys_str_mv | AT ehsanmohammadi anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT saeedkermani anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT mahdinourianzavareh anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT alalezare anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT hamedaghapanahroudsari anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT maryamsamieinasab anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT hamidsanei anewapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT ehsanmohammadi newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT saeedkermani newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT mahdinourianzavareh newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT alalezare newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT hamedaghapanahroudsari newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT maryamsamieinasab newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning AT hamidsanei newapproachofphonocardiogramanalysisforscreeningsomeofcardiovasculardiseasesbasedondeeplearning |