HEART DISEASE IDENTIFICATION METHOD USING MACHINE LEARNING CLASSIFICATION IN E-HEALTHCARE

Abstract

In this publication, we conducted a study on cardiovascular disease using data
analytics. Predicting the occurrence of cardiovascular disease is an emerging field of
study, especially as more data becomes accessible. A number of researchers have
looked at it using different methods. In order to identify and anticipate illness victims,
we used data analytics. We started by doing some preliminary processing on data sets
of varying sizes utilising three data analytics methods (Choice tree, Random forest,
SVM, and KNN) to identify the most important attributes according to the connection
matrix. Because of this, we were able to evaluate the consistency and accuracy of
each method. Using clinical criteria, the datasets are classified. Our method use a data
mining category approach to examine such factors. The optimal design showed the
greatest degree of accuracy for heart disease when the datasets were examined in
Python using machine learning methods.