Empirical Analysis of Heart Disease Prediction Using Deep Learning
Arunima Jaiswal, Monika Singh, Nitin Sachdeva
Abstract
In this current world, we keep hearing about heart disease problems every day and about the deaths due to them. and heart disease is also the reason for the crucial mortality rate around the world. According to the WHO, according to estimates, 17.9 million individuals die from cardiovascular diseases (CVD) each year. Detecting cardiovascular conditions, such as cardiac arrest and coronary heart disease, using regular clinical data analysis is a vital challenge. If cardiac disease is identified early, many lives can be spared. The use of machine learning (ML) algorithms enables intelligent decisions and exact predictions. In this study, a number of patient-provided factors decide whether or not heart disease exists. Our goal is to improve diagnostic precision and safeguard human resources in the medical industry. Some of the approaches used in this study to identify cardiac disease include the Long-Term Memory Network Model (LSTM), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Densenet, and Bi- LSTM. Of all the techniques utilized, CNN has the highest accuracy rate of 94.5%.