Assisting Heart Valve Diseases Diagnosis via Transformer-Based Classification of Heart Sound Signals

被引:7
|
作者
Yang, Dongru [1 ,2 ,3 ]
Lin, Yi [1 ,2 ,4 ]
Wei, Jianwen [1 ,2 ,4 ]
Lin, Xiongwei [5 ]
Zhao, Xiaobo [1 ,2 ,4 ]
Yao, Yingbang [1 ,2 ,4 ]
Tao, Tao [1 ,2 ,3 ]
Liang, Bo [1 ,2 ,3 ]
Lu, Sheng-Guo [1 ,2 ,3 ,4 ]
机构
[1] Guangdong Prov Res Ctr Smart Mat & Energy Convers, Guangzhou 510006, Peoples R China
[2] Guangdong Prov Key Lab Funct Soft Condensed Matter, Guangzhou 510006, Peoples R China
[3] Guangdong Univ Technol, Sch Integrated Circuits, Guangzhou 510006, Peoples R China
[4] Guangdong Univ Technol, Sch Mat & Energy, Guangzhou 510006, Peoples R China
[5] Shenzhen Inst Informat Technol, Sch Microelect, Shenzhen 518000, Peoples R China
关键词
heart sound signal; multi-classification; audio spectrogram; attention mechanism; transformer; NETWORK;
D O I
10.3390/electronics12102221
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Background: In computer-aided medical diagnosis or prognosis, the automatic classification of heart valve diseases based on heart sound signals is of great importance since the heart sound signal contains a wealth of information that can reflect the heart status. Traditional binary classification algorithms (normal and abnormal) currently cannot comprehensively assess the heart valve diseases based on analyzing various heart sounds. The differences between heart sound signals are relatively subtle, but the reflected heart conditions differ significantly. Consequently, from a clinical point of view, it is of utmost importance to assist in the diagnosis of heart valve disease through the multiple classification of heart sound signals. Methods: We utilized a Transformer model for the multi-classification of heart sound signals. It has achieved results from four abnormal heart sound signals and the typical type. Results: According to 5-fold cross-validation strategy as well as 10-fold cross-validation strategy, e.g., in 5-fold cross-validation, the proposed method achieved a highest accuracy of 98.74% and a mean AUC of 0.99. Furthermore, the classification accuracy for Aortic Stenosis, Mitral Regurgitation, Mitral Stenosis, Mitral Valve Prolapse, and standard heart sound signals is 98.72%, 98.50%, 98.30%, 98.56%, and 99.61%, respectively. In 10-fold cross-validation, our model obtained the highest accuracy, sensitivity, specificity, precision, and F1 score all at 100%. Conclusion: The results indicate that the framework can precisely classify five classes of heart sound signals. Our method provides an effective tool for the ancillary detection of heart valve diseases in the clinical setting.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Recognition of Pediatric Congenital Heart Diseases by Using Phonocardiogram Signals and Transformer-Based Neural Networks
    Hassanuzzaman, Md
    Hasan, Nurul Akhtar
    Al Mamun, Mohammad Abdullah
    Alkhodari, Mohanad
    Ahmed, Khawza, I
    Khandoker, Ahsan H.
    Mostafa, Raqibul
    2023 45TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE & BIOLOGY SOCIETY, EMBC, 2023,
  • [2] Heart Sound Classification Network Based on Convolution and Transformer
    Cheng, Jiawen
    Sun, Kexue
    SENSORS, 2023, 23 (19)
  • [3] Diagnosis of Heart Diseases Using Heart Sound Signals with the Developed Interpolation, CNN, and Relief Based Model
    Yildirim, Muhammed
    TRAITEMENT DU SIGNAL, 2022, 39 (03) : 907 - 914
  • [4] Detection of Mitral Valve Diseases by Bicoherence Analysis of Heart Sound Signals
    OAkgun
    HSVarol
    光谱学与光谱分析, 2017, 37 (10) : 3270 - 3273
  • [5] Detection of Mitral Valve Diseases by Bicoherence Analysis of Heart Sound Signals
    Akgun, O.
    Varol, H. S.
    SPECTROSCOPY AND SPECTRAL ANALYSIS, 2017, 37 (10) : 3270 - 3273
  • [6] Classification of Heart Sound Signals Based on AR Model
    He, Runnan
    Zhang, Henggui
    Wang, Kuanquan
    Li, Qince
    Sheng, Zhiqiang
    Zhao, Na
    2016 COMPUTING IN CARDIOLOGY CONFERENCE (CINC), VOL 43, 2016, 43 : 605 - 608
  • [7] Detection method of early heart valve diseases based on heart sound features
    Sun C.
    Wang X.
    Liu C.
    Shengwu Yixue Gongchengxue Zazhi/Journal of Biomedical Engineering, 2023, 40 (06): : 1160 - 1167
  • [8] A Vision Transformer-Based Approach to Bearing Fault Classification via Vibration Signals
    Zim, Abid Hasan
    Ashraf, Aeyan
    Iqbal, Aquib
    Malik, Asad
    Kuribayashi, Minoru
    PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, : 1321 - 1326
  • [9] Segmentation and Classification of Cardiac Sound Signals and Their Use in the Diagnosis of Heart Disease
    Rebiai, Mohamed
    Bengherbia, Billel
    Benkhaoua, Nadjet
    Douik, Nadjet
    Hentabli, Hamza
    Toumi, Yassine
    2022 INTERNATIONAL CONFERENCE ON THEORETICAL AND APPLIED COMPUTER SCIENCE AND ENGINEERING (ICTASCE), 2022, : 105 - 109
  • [10] Spectral analysis of heart valve sound for detection of prosthetic heart valve diseases
    Kim, SH
    Lee, HJ
    Huh, JM
    Chang, BC
    YONSEI MEDICAL JOURNAL, 1998, 39 (04) : 302 - 308