An Efficient Association Rule Mining from Distributed Medical Database for Predicting Heart Disease

Abstract

Naïve Bayes classification categorization in machine learning is employed to check the patient's entire heart illness in this proposed work. As a result, the percentage of patients that contract disease as both positive and negative data is used. Most database management systems and desktop analytics and visualization applications make working with big data difficult. As a result of this machine learning can be employed from the standpoint of data mining, and the proposal displays a machine learning methodology. The classifiers are used to process heart percentages, and the results are given as a confusion matrix. In the presence of a training dataset, a unique classification strategy is introduced that can effectively increase classification performance. Heart disease stent diagnostic In addition, the generated method has a high identification of rates, making It's a useful tool for junior cardiologists to check the cardio vascular patients with a high risk for certain diseases and refer them to expert cardiologists for further evaluation.