An Adaptive Technique to Predict Heart Disease Using Hybrid Machine Learning Approach

Abstract

cardiovascular disease is amongby far prevalent fatalities in today's society. Cardiovascular disease is extremely hard to predict using clinical data analysis. Machine learning (ML) hasproved to be useful for helping in judgement and predictions with the enormous amount data produced by the healthcare sectorbusiness. Furthermore, latest events in other IoT sectors have demonstrated that machine learning is used (IOT). Several studies have examined the use of MLa heart disease prediction. In this research, we describe a novel method that, by highlighting essential traits, can improvethe precision of heart disease prognosis. Numerous data combinations and well-known categorization algorithms are used to create the forecasting models. Using a decent accuracy of 88.7%, we raise the level of playusing a heart disease forecasting approach that incorporates a88.7% absolute certainty in a combination random forest and linear model. (HRFLM).