Smart Sensor Based Prognostication of Cardiac Disease Prediction Using Machine Learning Techniques

Abstract

Healthcare sectors are more predominantly growing in the modern decade. People are concerned about their health status because of unhealthy foods and imbalanced diet. People are switching to gymnasium, yoga, and other required healthy life activities. Despite the fact that many healthcare companies collect large quantities of data that contain some hidden information which are used for decision making. In this work we concentrate on predicting cardiovascular disease which is a leading cause of global death. The death rate is low in lower income counties than high income countries. It is mainly due to people’s lifestyle in the modern era changing factors such as obesity, diabetes, and others. Early detection of heart disease in the healthcare sector is difficult because it depends on clinical and pathological data. The purpose of this work is to use machine learning (ML) algorithms to implement a solution for earlier prediction of cardiovascular disease. The work comprises various sensors to get the user’s medical parameter like resting blood pressure (RBS), serum cholesterol (chol), fasting blood sugar (FBS), max heart rate, etc., and the data are processed with various ML algorithms like random forest, k-nearest neighbor (k-NN), decision tree (DT), and extreme gradient boost (XGBoost) method. Through these 64various methods, we have analyzed and compared the accuracy of the disease prediction.