CARDIOVASCULAR DISEASES DETECTION IN ECG IMAGES USING DEEP LEARNING METHODS

Abstract

Heart diseases are the leading cause of death world- wide. So,detecting and identifying them earlier can save many lives.Electrocardiogram (ECG) is a common and inexpensive tool for measuring the electrical activity of the heart and is used to detect cardiovascular disease.In this paper, the power of deep learning techniques was used to predict the four major cardiac abnormalities: abnormal heartbeat, myocardial infarction, his- tory of myocardial infarction, and normal person classes using the public ECG images dataset of cardiac patients. First, the preatrained models, namely SqueezeNet, AlexNet, proposed CNN and Xception were proposed for abnormality prediction.Second, these models were used as feature extraction tools for traditional machine learning algorithms, namely support vector machine, K- nearest neighbors, decision tree, random forest, and Na¨ıve Bayes. According to the experimental results, the performance metrics of the Xception model outperform the exciting works; it achieves 99.5% accuracy, 99.5% recall, 99.5% precision, and 99.5% F1 score. Moreover, when the Xception model is used for feature extraction, it achieves the best score of 99.8% using the RF and DT algorithms. Index Terms—Cardiovascular, deep learning, electrocardio- gram (ECG) images, feature extraction, machine learning, trans- fer learning.