Hybrid Classification Method for the Heart Disease Prediction

Abstract

Data mining is a method for separating crucial information from erratic data. In PA, future outcomes are predicted using current data. To evaluate heart failure, this study is being conducted. This strategy involves pre-processing the data, feature extraction, and classification to forecast cardiac disease. Over the years, several machine learning based strategies have been put forth. Heart disease detection cannot be done with great accuracy using current methods. This study suggests a hybrid model that combines RF and LR to evaluate heart failure with good accuracy. The disease is classified using LR after features are extracted using an RF classifier. In this study, many metrics are used to evaluate the effectiveness of the suggested approach. Using a hybrid strategy, heart failure can be predicted with 95% accuracy.