Heart Disease Prediction using Supervised Learning Classifiers

Heart disease is the leading factor of death around the world. Heart and blood vessels together, incorporate our cardiovascular system. A set of conditions can affect our cardiovascular system which can be fatal if it is not properly diagnosed. Hence, it is very crucial to identify and impede any sort of cardiovascular system abnormality as early as possible. The venture of this paper is to anticipate heart disease by comparing various reliable machine learning techniques and analyzing their coherence and accuracy. The result of our research shows that a wide range of parameters are involved in the creation of heart disease. Cleveland dataset on heart disease is used with four machine learning methods i.e., Support Vector Classifier, Random Forest Classifier, Multi-Layer Perceptron Classifier and Ridge Classifier to predict heart disease. Among the above-mentioned classifiers, Ridge Classifier shows maximum accuracy which is 89.19% and 0.92 F1-score. In a nutshell, Ridge Classifier can be considered as a dependable way to identify heart disease and to prevent immature death.