Early Prediction of Heart Disease Using PCA and Hybrid Genetic Algorithm with k-Means

TL;DR

This paper proposes a novel approach combining PCA and a hybrid genetic algorithm with k-means clustering to predict heart disease early, achieving an accuracy of 94.06% on the UCI dataset.

Contribution

It introduces a hybrid genetic algorithm with k-means for improved clustering in heart disease prediction, addressing local optima issues in traditional methods.

Findings

Achieved 94.06% accuracy in early heart disease prediction.

Reduced data attributes using PCA for better model performance.

Hybrid genetic algorithm improves clustering over standard k-means.

Abstract

Worldwide research shows that millions of lives lost per year because of heart disease. The healthcare sector produces massive volumes of data on heart disease that are sadly not used to locate secret knowledge for successful decision making. One of the most important aspects at this moment is detecting heart disease at an early stage. Researchers have applied distinct techniques to the UCI Machine Learning heart disease dataset. Many researchers have tried to apply some complex techniques to this dataset, where detailed studies are still missing. In this paper, Principal Component Analysis (PCA) has been used to reduce attributes. Apart from a Hybrid genetic algorithm (HGA) with k-means used for final clustering. Typically, the k-means method is using for clustering the data. This type of clustering can get stuck in the local optima because this method is heuristic. We used the Hybrid Genetic Algorithm (HGA) for data clustering to avoid this problem. Our proposed method can predict early heart disease with an accuracy of 94.06%.