AN ENSEMBLE LEARNING FRAMEWORK FOR PREDICTING THE RISK OF HEART DISEASES

Coronary heart disease is a major cause of morbidity and mortality in the modern society. Many risk factors for coronary heart disease have been discussed and identified by medical fraternity, but the magnitudes of risk factors, particularly in predicting the disease are remained unknown and inconclusive. The early prognosis of cardiovascular diseases can aid in making decisions to lifestyle changes in high risk patients and intum reduce their complications. Data mining is an iterative and interactive process of discovering valid, useful, comprehensive and understandable patterns and models in enormous data sources. The challenge faced by healthcare industry with regard to the massive data- rich but information-poor collection is to extraction of valuable information. Research has attempted to pinpoint most influential factors of heart diseases as well as accurately predict the overall risk using homogenous data mining techniques. We propose a rule based model to find the accuracy of applying rules to the logistic regression on the Cleveland heart disease database in order to predict heart diseases.