Heart Disease Prediction Using Data Mining

Abstract

CVDs(Cardiovascular disorders) are the primary health problem, with 17.9 million deaths every year (World Health Organization). Heart disease has been the primary cause of death on a global scale for the last 20 years. It has become more difficult to diagnose illness and have adequate care at the right time as the population and disease have grown. However, medical research has advanced to the point that we can see a glimpse of hope. We primarily address it in this article. We looked at various data mining approaches, including Decision Tree Classification, Random Forest Classification, and K-Nearest Neighbor Classification, and we used a good data set of random attributes and values to achieve the highest accuracy. We are only attempting to forecast the progression of heart disease in this article. These Data Mining techniques require less time and have higher accuracy. It is used to monitor and examine the outcome of heart disease patients, with a current diagnosis ranging from in decent form to good shape. Using various data mining methods, the proposed study forecasts the likelihood of Heart Disease and classifies patients' risk levels. As a result, this report provides a comparative analysis of the success of various Data mining algorithms. As opposed to other data mining algorithms, the trial results suggest that the Random Forest and Decision tree algorithms have the best accuracy.