Deep Learning Approach for Automatic Cardiovascular Disease Prediction Employing ECG Signals

Abstract

Cardiovascular problems have become the predominant cause of death worldwide and a rise in the number of patients has been observed lately. Currently, electrocardiogram (ECG) data is analyzed by medical experts to determine the cardiac abnormality, which is time-consuming. In addition, the diagnosis requires experienced medical experts and is error-prone. However, automated identification of cardiovascular disease using ECGs is a challenging problem and state-of-the-art performance has been attained by complex deep learning architectures. This study proposes a simple multilayer perceptron (MLP) model for heart disease prediction to reduce computational complexity. ECG dataset containing averaged signals with window size 10 is used as an input. Several competing deep learning and machine learning models are used for comparison. K-fold cross-validation is used to validate the results. Experimental outcomes reveal that the MLP-based architecture can produce better outcomes than existing approaches with a 94.40% accuracy score. The findings of this study show that the proposed system achieves high performance indicating that it has the potential for deployment in a real-world, practical medical environment.