Cardiac Disorder Classification by Electrocardiogram Sensing Using Deep Neural Network

Cardiac disease is the leading cause of death worldwide. Cardiovascular diseases can be prevented if an effective diagnostic made at initial stages. The ECG test referred to as assistant tool for screening cardiac disorder. research purposes a disorder detection system from 12-lead-based Images. healthcare institutes used various equipment that present results in nonuniform formats images. study proposes generalized methodology process all ECG. Single Shoot Detection (SSD) MobileNet v2-based Deep Neural Network architecture was detect cardiovascular detection. focused on detecting four major abnormalities (i.e., myocardial infarction, abnormal heartbeat, previous history MI, and normal class) with 98% accuracy were calculated. work relatively rare based their dataset; collection 11,148 standard images this manually collected health care annotated by domain experts. achieved high differentiate abnormalities. Several cardiologists verified proposed system’s result recommended screen