Implementation of Different Machine Learning Approaches for Heart Disease Diagnosis

Cardiovascular disease is a deadly ailment that can strike unexpectedly and without warning. Despite generating copious amounts of patient and illness data, the healthcare sector often fails to effectively harness this information for precise diagnosis and decision-making. To unlock the wealth of information available, researchers and practitioners can utilize data mining and machine learning approaches. This paper implements a proposed system consisting of data collection, preprocessing, feature selection, model selection, model training, and model evaluation. The study compares different machine learning models for predicting heart disease such as KNN classifier, Support vector machine learning classifier (SVM), Random Forest and Decision tree, where KNN is giving best output of 87.05% with 8 neighbor. An analytical review of existing research on the prediction of heart disease is given in this article and drawing insightful conclusions for future study.