Hybrid CNN-LSTM model for automatic prediction of cardiac arrhythmias from ECG big data

Abstract

Automatic and accurate prognosis of cardiac arrhythmias from ECG big data is a very challenging task for the diagnosis and treatment of heart diseases. Hence, we have proposed a hybrid CNN-LSTM deep learning model for accurate and automatic prediction of cardiac arrhythmias using the ECG big dataset. The total 123,998 ECG beats from combined benchmark datasets “MIT-BIH arrhythmias database” and “PTB diagnostic database” are employed for validation of the model performance. The ECG beat time interval and its gradient value is directly considered as the feature and given as the input to the proposed model. The Model performance was verified using six types of evaluation metrics and compared the result with the state-of-art method. The overall and average accuracy percentage obtained using the proposed model is 99% and 99.7%.