Acquisition of electrocardiogram signals and cardiac arrhythmia detection using neural networks

Abstract

Electrocardiography is a frequently used examination technique for heart disease diagnosis. Represented by the test called electrocardiogram (ECG), electrocardiography is essential in the clinical evaluation of athletes, risk patients who need surgery, and also those who have heart disease. Through electrocardiography, doctors can identify whether the cardiac muscle dysfunctions presented by the patient are of inflammatory or degenerative origin and early diagnose serious diseases that primarily affect the blood vessels and the brain. Thus, the objective of this project is to develop a prototype capable of capturing, analyzing, and classifying a patient’s electrocardiogram signals for the detection and prevention of cardiac arrhythmia in clinical patients. Our ECG signal classification model obtained an accuracy of 98.12% and an F1-score of 99.72% in the classification of ventricular ectopic beats (V). Our ECG acquisition board circuit tested gain output is 28.8V/V and the frequency cut is 40Hz.