Heart Disease Prediction System

Heart diseases are the one of the primary reasons of human death today. There are many recent technologies are used to assist the medical professionals and doctors in the prediction of heart disease in the early stage. Prediction of heart disease is a critical challenge in the area of clinical data analysis. This paper introduces a technique to detect arrhythmia, which is a representative type of cardio vascular diseases. Arrhythmia refers to any irregular change from the normal heart rhythms, means that your heart beats too quickly, too slowly, or with an irregular pattern. The Electro Cardiogram (ECG) is used as an input for the arrhythmia detection. It displays the rhythm and status of the heart. This paper propose an effective ECG arrhythmia classification approach based on a deep convolutional neural network (CNN), which has lately demonstrated remarkable performance in the field of machine learning. It perform the classification without any manual pre-processing of the ECG signals such as noise filtering, feature extraction, and feature reduction. Keywords: Arrhythmia, ECG, deep learning, CNN, ResNet