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
  • [21] Heart Sound Feature Reduction Approach for Improving the Heart Valve Diseases Identification
    Salama, Mostafa A.
    Hassanien, Aboul Ella
    Fahmy, Aly A.
    Kim, Tai-hoon
    SIGNAL PROCESSING, IMAGE PROCESSING AND PATTERN RECOGNITION, 2011, 260 : 280 - +
  • [22] Evaluation of Algorithms for Automatic Classification of Heart Sound Signals
    Enrique Perez-Guzman, Ricardo
    Garcia-Bermudez, Rodolfo
    Rojas-Ruiz, Fernando
    Cespedes-Perez, Ariel
    Ojeda-Riquenes, Yudelkis
    BIOINFORMATICS AND BIOMEDICAL ENGINEERING, IWBBIO 2017, PT I, 2017, 10208 : 536 - 545
  • [23] Heart Sound Signals Classification with Image Conversion Employed
    Deng, Erqiang
    Jia, Yibei
    Zhu, Guobin
    Zhou, Erqiang
    ELECTRONICS, 2024, 13 (07)
  • [24] An expert system for diagnosis of the heart valve diseases
    Turkoglu, I
    Arslan, A
    Ilkay, E
    EXPERT SYSTEMS WITH APPLICATIONS, 2002, 23 (03) : 229 - 236
  • [25] Heart Sound Classification via Sparse Coding
    Whitaker, Bradley M.
    Anderson, David V.
    2016 COMPUTING IN CARDIOLOGY CONFERENCE (CINC), VOL 43, 2016, 43 : 805 - 808
  • [26] Heart sound reproduction based on neural network classification of cardiac valve disorders using wavelet transforms of PCG signals
    Babaei, Sepideh
    Geranmayeh, Amir
    COMPUTERS IN BIOLOGY AND MEDICINE, 2009, 39 (01) : 8 - 15
  • [27] Robust classification of heart valve sound based on adaptive EMD and feature fusion
    Wang, Weibo
    Yuan, Jin
    Wang, Bingrong
    Fang, Yu
    Zheng, Yongkang
    Hu, Xingping
    PLOS ONE, 2022, 17 (12):
  • [28] Classification of Heart Valve Diseases using Correlation Analysis
    Suboh, Mohd Zubir
    Mashor, M. Y.
    Saad, A. R. Mohd
    Mohamed, M. S.
    2008 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, COMPUTING SCIENCE AND AUTOMATIC CONTROL (CCE 2008), 2008, : 216 - +
  • [29] Analysis of heart sound signals based on LabVIEW
    Information School, Yunnan University, Kunming 650091, China
    Yi Qi Yi Biao Xue Bao, 2007, SUPPL. 5 (78-81):
  • [30] The importance of handling multivariate attributes in the identification of heart valve diseases using heart signals
    Hamdy, Ahmed
    Hefny, Hesham
    Salama, Mostafa A.
    Hassanien, Aboul Ella
    Kim, Tai-hoon
    2012 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS (FEDCSIS), 2012, : 75 - 79