A Taxonomy on Machine Learning Based Techniques to Identify the Heart Disease

Abstract

Every year average death of human being is 17.7 million caused by Heart Disease or Cardiovascular diseases (CVDs), which is 31% of all global deaths reflected in Survey of World Heart Day 2017 [33]. In September 2016, many countries have taken the various Global Hearts Initiative in prediction and diagnosis of heart Diseases at earlier stages so that it can be cure perfectly [5]. Many authors have studied in this filed to optimize the performance of various ML techniques using various approaches. In latest studies, many groups have uncovered that many optimization algorithm like Differential Evolution, Genetic Variants, and Particle Swarm optimization are associated with prediction algorithm like K-Nearest neighbor, Decision Tree, Neural Network, Support Vector machine, Logistic Regression etc. to make efficient medical system for CVDs. The Objective of our current study is to analyze the comparatively study of the ML techniques in terms of performance measure of different ML techniques that have been used by various authors in their research work in earlier studies of heart disease prediction and diagnosis process.