Using Personal Key Indicators and Machine Learning-based Classifiers for the Prediction of Heart Disease

This paper explores different machine learning algorithms and data splits to measure each model's accuracy, precision, and recall. The models use personal key indicators to predict heart disease. Heart disease, according to the center for disease control, is the leading cause of death in the United States, and about 32% of all global deaths are due to heart diseases such as heart attacks and strokes. Therefore, it is of the utmost importance to integrate machine learning into heart disease prediction and hopefully alert people of the dangers that lie ahead using personal key indicators. Multiple models are recommended in this paper and produced different but relatively high accuracies, the highest accuracy being 99% using Random Forest Classification and a data split based on race.