Heart disease is the main reason for death in the world over the last decade. The World Health Organization reported that heart disease is the first leading cause of death in high and low income countries. Clinical diagnosis is done by doctor’s expertise but still some cases are reported of wrong prediction and diagnosis. Today, numerous doctors manage healthcare data utilizing medicinal services data framework it contains huge measure of information, used to extract hidden information for prediction of cardiovascular disease. The main objective of this research is to develop a Heart Disease Prediction System to predict the presence of heart disease using machine learning algorithms. Extreme Learning Machine (ELM) is a new class of Single-Hidden Layer Feed Forward Neural Network (SLFN), which is simple in theory and fast in implementation and it reported that it suffer from over fitting. It can be overcome by incorpoted a structural risk minimization principle into the (weighted) ELM and proposed a Modified Weighted Extreme Learning Machine (MWELM). The experimental results shows that proposed method outperforms well and provides better classification accuracy to predict the presence of cardiovascular disease.
