171 / 2019-06-20 21:53:29

A New Automatic Approach to Distinguish Myocardial Infarction Based on LSTM

Electrocardiogram, Myocardial Infarction, Recurrent Neural Network

Myocardial Infarction (MI) is an acute disease. Early detection and early treatment are of great significance for improving the health of the people. This paper proposes a new method for MI classification based on LSTM, in order to reduce the misdiagnosis rate of MI diseases. At first, the original electrocardiogram (ECG) signal is preprocessed and then segmented into a heartbeat sequence. After that the heartbeat sequence is sent to the deep neural network training model to learn the classification. Lastly the method is verified on the Physikalisch-Technische Bundesanstalt (PTB) ECG database. The accuracy of the method is 99.91%. The experimental results show that the classification accuracy of the proposed method is superior to the other methods.