Classification of Arrhythmia From ECG Signals Using CSL-Net

Abstract

Cardiovascular disease (CVD) has become one of the main diseases threatening human life and health. As an important tool for doctors to diagnose and analyze cardiovascular diseases, it is necessary to improve the accuracy of Electrocardiogram (ECG) classification. In this paper, we proposed a new network model called CSL-NET that uses a combination of convolutional neural network (CNN), SE block and long short-term memory (LSTM) for ECG signal processing and arrhythmia classification. The algorithm uses wavelet transform to filter the ECG signal, and then input it to CNN to extract ECG features automatically. An SE block is added to the end of CNN layer, in which, the extracted features are recalibrated to selectively emphasize useful features and suppress less relevant features. After that, input the data to the LSTM layer to extract the temporal information from the ECG signal. The experiment was performed on the ECG signal collected in the MIT-BIH database. Ultimately, the accuracy, sensitivity (recall rate), predicted value and F1 score of the CSL-NET model we proposed reached 99.52%, 98.23%, 99.22% and 98.93% respectively. Experimental results indicate that the proposed model has great potential for application in clinical practice, including wearable devices and intensive care units.