Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network
Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic E...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/23/1/119 |
| _version_ | 1797410155873173504 |
|---|---|
| author | Tao Wang Changhua Lu Yining Sun Mei Yang Chun Liu Chunsheng Ou |
| author_facet | Tao Wang Changhua Lu Yining Sun Mei Yang Chun Liu Chunsheng Ou |
| author_sort | Tao Wang |
| collection | DOAJ |
| description | Early detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75%, 67.47%, 68.76%, and 98.74% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75~16.85%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool. |
| first_indexed | 2024-03-09T04:25:50Z |
| format | Article |
| id | doaj.art-6a318724dd2244f4b5a4f5836dab8a29 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-09T04:25:50Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-6a318724dd2244f4b5a4f5836dab8a292023-12-03T13:40:31ZengMDPI AGEntropy1099-43002021-01-0123111910.3390/e23010119Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural NetworkTao Wang0Changhua Lu1Yining Sun2Mei Yang3Chun Liu4Chunsheng Ou5School of Computer and Information, Hefei University of Technology, Hefei 230009, ChinaSchool of Computer and Information, Hefei University of Technology, Hefei 230009, ChinaInstitute of Intelligent Machines, Chinese Academy of Sciences, Hefei 230031, ChinaBeijing Huaru Technology Co., Ltd., Hefei Branch, Hefei 230088, ChinaSchool of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009, ChinaSchool of Computer and Information, Hefei University of Technology, Hefei 230009, ChinaEarly detection of arrhythmia and effective treatment can prevent deaths caused by cardiovascular disease (CVD). In clinical practice, the diagnosis is made by checking the electrocardiogram (ECG) beat-by-beat, but this is usually time-consuming and laborious. In the paper, we propose an automatic ECG classification method based on Continuous Wavelet Transform (CWT) and Convolutional Neural Network (CNN). CWT is used to decompose ECG signals to obtain different time-frequency components, and CNN is used to extract features from the 2D-scalogram composed of the above time-frequency components. Considering the surrounding R peak interval (also called RR interval) is also useful for the diagnosis of arrhythmia, four RR interval features are extracted and combined with the CNN features to input into a fully connected layer for ECG classification. By testing in the MIT-BIH arrhythmia database, our method achieves an overall performance of 70.75%, 67.47%, 68.76%, and 98.74% for positive predictive value, sensitivity, F1-score, and accuracy, respectively. Compared with existing methods, the overall F1-score of our method is increased by 4.75~16.85%. Because our method is simple and highly accurate, it can potentially be used as a clinical auxiliary diagnostic tool.https://www.mdpi.com/1099-4300/23/1/119arrhythmiacontinuous wavelet transformconvolutional neural networkdeep learningECG classificationheartbeat classification |
| spellingShingle | Tao Wang Changhua Lu Yining Sun Mei Yang Chun Liu Chunsheng Ou Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network Entropy arrhythmia continuous wavelet transform convolutional neural network deep learning ECG classification heartbeat classification |
| title | Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network |
| title_full | Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network |
| title_fullStr | Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network |
| title_full_unstemmed | Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network |
| title_short | Automatic ECG Classification Using Continuous Wavelet Transform and Convolutional Neural Network |
| title_sort | automatic ecg classification using continuous wavelet transform and convolutional neural network |
| topic | arrhythmia continuous wavelet transform convolutional neural network deep learning ECG classification heartbeat classification |
| url | https://www.mdpi.com/1099-4300/23/1/119 |
| work_keys_str_mv | AT taowang automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork AT changhualu automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork AT yiningsun automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork AT meiyang automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork AT chunliu automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork AT chunshengou automaticecgclassificationusingcontinuouswavelettransformandconvolutionalneuralnetwork |