Performance Evaluation of Heart Disease Disorder Diagnosis Using Intelligent Supervised Machine Learning Classifiers

Abstract

AbstractThe heart plays an important character in living things. Diagnosis and prognosis of heart disease needs greater completeness and accuracy because a small mistake can lead to extreme problems or loss of the person, there are many heart-related deaths and the number is expanding rapidly everyday. To solve this problem, a disease awareness prediction system is a key requirement. Machine learning is a type of artificial intelligence (AI). It provides outstanding support for the prediction of all types of events caused by natural disasters. In this article, we calculate the correctness of machine learning algorithms for heart disease prediction, as these algorithms are k-proximal neighbors, decision tree, linear regression, and support vector machine (SVM) in using UCI benchmark data sets for training and testing. The best tool to implement Python programming is the Anaconda (Jupyter) notebook, which contains many kinds of libraries and header files that make the task crisp and efficient.KeywordsSupervisedReinforcedConfusion matrixLinear regressionUnsupervisedPython