Enhanced and Effective Model for Heart Disease Prediction Using Hybridization of Random Forest and AdaBoost (HRFAB)

Coronary artery disease or heart disease is the leading cause of death worldwide. In the field of data analysis and clinical decision making, one of the challenging tasks is the prediction of heart disease. In today's era, large amount of data is getting generated and Machine learning is able to analyse, predict this data. We have studied ML techniques which are mostly used in medical field. In this view, various research techniques have been conducted by researchers using ML classifiers. In this paper, we have implemented a good ensemble & bagging and boosting techniques i.e. Random Forest and AdaBoost respectively to predict the heart disease. To generate prediction model, data preprocessing techniques are applied on well-known dataset extended Z Alizadeh Sani. We achieved 95% prediction accuracy for hybrid of Random Forest and AdaBoost model (HRFAB). It gave us better accuracy for heart disease forecast.