Developing a Deep Learning Model Using a Combination of CNN and RCNN for Cardiovascular Disease Classification

Cardiovascular diseases have become a major cause of death due to factors such as underlying health conditions, perceived medical costs, and lack of timely treatment. The Electrocardiogram (ECG) is a tool widely used to record electrical heart signals for evaluating and treating these diseases. Many research studies have utilized machine learning and deep learning to detect and classify cardiovascular diseases (CVDs). This study proposed a new method that combines Convolutional Neural Networks (CNN) and Recurrent Convolutional Neural Networks (RCNN) for the detection and classification of five types of CVDs, using PhysioNet's MIT-BIH Arrhythmia Database. CNN helps extract significant features from the data, while RCNN aids in preventing overfitting. This method has achieved a macro accuracy of approximately 93 % and an average accuracy of approximately 99%.