An Efficient Healthcare Monitoring System for Cardiovascular Diseases using Deep Modified Neural Networks

Abstract

Doctors check medical records to figure out the chances of someone getting heart disease (Myocardial infarction). Major focus will be on blood pressure, how old the person is, if he is a man or a woman, if they feel pain in their chest, how much is their cholesterol level, and how much sugar is in their blood. However, manual illustrations may lead to incorrect predictions. The expectation of heart malady may be a key issue within the investigation of clinical dataset. The point of the proposed examination is to recognize the key characteristics of heart infection expectation utilizing profound learning methods. Numerous ponders have centered on heart infection conclusion, but the execution of the discoveries is moo. In this manner, to progress forecast precision, an profound learning system for the determination of heart illness utilizing adjusted Deep Neural Networks (DNN) is proposed by using Cleveland database by adjusting its learning parameters. The proposed method used has a score of 90.7, with a higher precision of 91.5 compared to other methods.