Abstract:
Heart disease is the main reason for death in the world in the course of the most recent
decade. As per late study by WHO (World health organization) 17.9 million people die
every year because of these type of diseases and it is expending quickly. With the
expending populace and disease, it is become a challenge to diagnosing sickness and giving
the appropriate therapy at the ideal time. But early prediction of heart disease may save
numerous lives. However utilizing data mining methods can lessen the quantity of test that
are required. In order to diminish number of death from heart disease there must be speedy
and proficient detection procedure. This paper targets analyzing the different data mining
procedures in particular Naive Bayes, Random Forest Classification, Decision tree and
Support Vector Machine by utilizing a certified data set for heart disease prediction which
is comprise of different features like sex, age, chest pain type, blood pressure, glucose and
so forth. The research incorporates finding the correlations between the different features
of the data set by using the standard data mining methods and hence utilizing the features
appropriately to anticipate the possibility of a heart disease. These machine learning
methods take least time for the prediction of the disease with more exactness which will
reduce the dispose of valuable lives all over the world.