Abstract:

Abstract Electrocardiogram (ECG) signal evaluation is routinely used in clinics as a significant diagnostic method for detecting sudden cardiac death. Using automated detection and classification methods in the clinic can assist doctors in making accurate and expeditious diagnoses of diseases. In this study, we developed a classification method for sudden cardiac death based on image 2D with the combination of a convolutional neural network and long short-term memory, which was then used to diagnose a normal sinus rhythm and sudden cardiac death. The ECG data of the experiment were derived from the MIT-BIH SCD Holter database and MIT-BIH Normal Sinus Rhythm. 2D CNN model give the best result with average accuracy 96.67%, average sensitivity 100%, average specificity 92.90%, average precision 92.90% and the average F1 score is 97.10% for 1 minutes, 2 minutes and 3 minutes before VF onset.

Keywords: