Predictive Analysis of Heart Disease Using Machine Learning Algorithms

Abstract

Early prediction of cardiac arrest is one of the most challenging jobs in medical science. It takes a long time to figure out the exact causes behind it. Approximately one human dies per minute because of heart disease. Data analysis plays a vital part in handling huge amounts of healthcare data. In order to decrease the number of deaths from heart diseases, efficient detection techniques have to be used. This chapter describes the chances of heart disease and classifies a patient's risk level by implementing different classification algorithms such as K-Nearest neighbour, support vector machine, Naïve Bayes, random forest and a multilayer perception. Artificial neural network optimized by particle swarm optimization (PSO) are combined with ant colony optimization (ACO) approaches. Thus, this chapter presents a comparative study by analysing the performance of different machine learning algorithms. The trial results verify that random forest algorithm has achieved the highest accuracy of 90.16% compared to other ML algorithms implemented.