Prediction and Classification of Heart Disease Using Different Classifier Algorithms

Abstract

One of the leading causes of death all over the world is cardiovascular disease, making early detection of the condition crucial. Predicting and diagnosing cardiac illness is made easier with the use of computer-aided technologies. Data mining is a method used on huge databases to discover previously unseen connections or correlations using a hybrid approach to statistical analysis, machine learning, and database technology. Furthermore, the growth of diverse applications in the thriving healthcare industry makes medical data mining an incredibly significant study subject. This study's overarching objective is to create a cardiovascular disease prediction system that makes use of key risk indicators and employs many classifier methods, including Naive Bayes, Support Vector Machine, and K-Nearest Neighbors. This study employs the heart illness dataset housed in the UCI Machine Repository in an effort to better diagnose cardiovascular conditions. Based on the findings, it appears that the suggested unique optimized algorithm can serve as the basis for a reliable healthcare monitoring system capable of detecting and preventing cardiac disease at an early stage.