Early Heart Disease Prediction Using Hybrid Machine Learning Techniques

Abstract

In the contemporary era, cardiovascular disease is one in all the most causes of death within the world. Estimating Heart problems i.e cardiopathy is a crucial challenge within the area of clinical data analysis. Large volumes of data produced by the healthcare sector have been proved to be useful for helping with decision-making and speculation, thanks to machine learning (ML).. Various studies help us to review and supply glimpse into predict the centre disease with Machine Learning modules. In this paper, we propose a Hybrid approach that aims to improve the predictability of cardiac disease by identifying key features using machine learning approaches. A combination of several features and classification techniques makes up the hybrid model. The author develops a novel technique called Hybrid Machine Learning to achieve the highest accuracy of heart rate estimates by combining two separate algorithms, such as Linear Model and Random Forest. The Hybrid algorithm will be developed using the Vote Separator, the Internal Voting Phase will grow using the Line and Random Forest Model and while the phased voting algorithm will check the accuracy of your prediction for both algorithms and vote for that algorithm that provides better accuracy. So, by implementing a hybrid model fetches us better accuracy and helps better prediction of heart disease.