Heart Disease Prediction using Hybrid Technique in Data Mining

Abstract

Data mining techniques have been widely used in clinical decision supporting system for
prediction and diagnosis of various disease with good accuracy. These techniques have been very effective in
designing clinical support systems because of their ability to discover hidden patterns and relationships in
medical data. One of the most important applications of such systems is in diagnosis of heart diseases
because it is one of the leading causes of deaths all over the world. Heart disease prediction is treated as a
most complicated task in the field of medical science. Thus there is a need to develop a decision support
system for detecting heart disease of a patient. In this system we work on a hybrid approach for heart
disease data analysis using k-means algorithm and Support Vector Machine. We propose an efficient hybrid
algorithmic approach for heart disease prediction. It serves an efficient prediction technique to determine
and extract the unknown knowledge of heart disease using hybrid combination of K-means clustering
algorithm and SVM. To perform grouping of various attributes it uses K-means algorithm and for prediction
it uses SVM. It is developed in RStudio. We get 94% accuracy.
We have seen that making cluster earlier than prediction is very useful in increasing the accuracy of
prediction. We improve the accuracy as shown in result.