Heart Disease Diagnosis System using Machine Learning with Principal Component Analysis: A Review

Abstract

Health is not everything, however, everything else is nothing without health. Then and now, people are trying out ways which can increase the longevity of life. Still, technology is far away from achieving this goal of reducing the mortality rate. However, for a start, the beginning steps have been done. Advancing technology and its influence on peoples’ life is already leading to healthy lifestyles. Healthy living habits, routines, proactive health monitoring, and early detection of diseases lead to increased expectancy of life. Today, the world is adopting Internet of Things in its daily uses. There are various wearable technological devices that have been developed to monitor/measure different health attributes. The criticality of health diseases are more crucial and can even lead to vulnerable consequences if it is not detected at an earlier stage. The techniques such as electronic health records, body area networks are emerged to continuously monitor and diagnose patient’s health conditions through the projection of medical sensors and wearable devices across human bodies. Since the data generated from the body area networks are continuous and tremendous in volume, the machine learning techniques are used for efficient health data classification processes. However, health data classification is the most challenging process as it needs to be executed accurately with an earlier prediction of heart diseases.