Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound
Heart failure (HF) is a devastating condition that impairs people’s lives and health. Because of the high morbidity and mortality associated with HF, early detection is becoming increasingly critical. Many studies have focused on the field of heart disease diagnosis based on heart sound (HS), demons...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/20/10322 |
_version_ | 1797475594933370880 |
---|---|
author | Huanyu Zhang Ruwei Wang Hong Zhou Shudong Xia Sixiang Jia Yiteng Wu |
author_facet | Huanyu Zhang Ruwei Wang Hong Zhou Shudong Xia Sixiang Jia Yiteng Wu |
author_sort | Huanyu Zhang |
collection | DOAJ |
description | Heart failure (HF) is a devastating condition that impairs people’s lives and health. Because of the high morbidity and mortality associated with HF, early detection is becoming increasingly critical. Many studies have focused on the field of heart disease diagnosis based on heart sound (HS), demonstrating the feasibility of sound signals in heart disease diagnosis. In this paper, we propose a non-invasive early diagnosis method for HF based on a deep learning (DL) network and the Korotkoff sound (KS). The accuracy of the KS-based HF prediagnosis was investigated utilizing continuous wavelet transform (CWT) features, Mel frequency cepstrum coefficient (MFCC) features, and signal segmentation. Fivefold cross-validation was applied to the four DL models: AlexNet, VGG19, ResNet50, and Xception, and the performance of each model was evaluated using accuracy (Acc), specificity (Sp), sensitivity (Se), area under curve (AUC), and time consumption (Tc). The results reveal that the performance of the four models on MFCC datasets is significantly improved when compared to CWT datasets, and each model performed considerably better on the non-segmented dataset than on the segmented dataset, indicating that KS signal segmentation and feature extraction had a significant impact on the KS-based CHF prediagnosis performance. Our method eventually achieves the prediagnosis results of Acc (96.0%), Se (97.5%), and Sp (93.8%) based on a comparative study of the model and the data set. The research demonstrates that the KS-based prediagnosis method proposed in this paper could accomplish accurate HF prediagnosis, which will offer new research approaches and a more convenient way to achieve early HF prevention. |
first_indexed | 2024-03-09T20:47:22Z |
format | Article |
id | doaj.art-20dc2a50736c44978ae42ee5dcff4c58 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T20:47:22Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-20dc2a50736c44978ae42ee5dcff4c582023-11-23T22:42:47ZengMDPI AGApplied Sciences2076-34172022-10-0112201032210.3390/app122010322Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff SoundHuanyu Zhang0Ruwei Wang1Hong Zhou2Shudong Xia3Sixiang Jia4Yiteng Wu5College of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310013, ChinaCollege of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310013, ChinaCollege of Biomedical Engineering & Instrument Science, Zhejiang University, Hangzhou 310013, ChinaThe Fourth Affiliated Hospital of Zhejiang University School of Medicine, Yiwu 322000, ChinaThe Fourth Affiliated Hospital of Zhejiang University School of Medicine, Yiwu 322000, ChinaThe Fourth Affiliated Hospital of Zhejiang University School of Medicine, Yiwu 322000, ChinaHeart failure (HF) is a devastating condition that impairs people’s lives and health. Because of the high morbidity and mortality associated with HF, early detection is becoming increasingly critical. Many studies have focused on the field of heart disease diagnosis based on heart sound (HS), demonstrating the feasibility of sound signals in heart disease diagnosis. In this paper, we propose a non-invasive early diagnosis method for HF based on a deep learning (DL) network and the Korotkoff sound (KS). The accuracy of the KS-based HF prediagnosis was investigated utilizing continuous wavelet transform (CWT) features, Mel frequency cepstrum coefficient (MFCC) features, and signal segmentation. Fivefold cross-validation was applied to the four DL models: AlexNet, VGG19, ResNet50, and Xception, and the performance of each model was evaluated using accuracy (Acc), specificity (Sp), sensitivity (Se), area under curve (AUC), and time consumption (Tc). The results reveal that the performance of the four models on MFCC datasets is significantly improved when compared to CWT datasets, and each model performed considerably better on the non-segmented dataset than on the segmented dataset, indicating that KS signal segmentation and feature extraction had a significant impact on the KS-based CHF prediagnosis performance. Our method eventually achieves the prediagnosis results of Acc (96.0%), Se (97.5%), and Sp (93.8%) based on a comparative study of the model and the data set. The research demonstrates that the KS-based prediagnosis method proposed in this paper could accomplish accurate HF prediagnosis, which will offer new research approaches and a more convenient way to achieve early HF prevention.https://www.mdpi.com/2076-3417/12/20/10322heart failureKorotkoff sounddeep learningMFCCneural networksprediagnosis |
spellingShingle | Huanyu Zhang Ruwei Wang Hong Zhou Shudong Xia Sixiang Jia Yiteng Wu Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound Applied Sciences heart failure Korotkoff sound deep learning MFCC neural networks prediagnosis |
title | Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound |
title_full | Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound |
title_fullStr | Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound |
title_full_unstemmed | Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound |
title_short | Prediagnosis of Heart Failure (HF) Using Deep Learning and the Korotkoff Sound |
title_sort | prediagnosis of heart failure hf using deep learning and the korotkoff sound |
topic | heart failure Korotkoff sound deep learning MFCC neural networks prediagnosis |
url | https://www.mdpi.com/2076-3417/12/20/10322 |
work_keys_str_mv | AT huanyuzhang prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound AT ruweiwang prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound AT hongzhou prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound AT shudongxia prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound AT sixiangjia prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound AT yitengwu prediagnosisofheartfailurehfusingdeeplearningandthekorotkoffsound |