Emerging Scholars

ABSTRACT

Cardiovascular diseases are highly prevalent around the world, making heart attacks one of the leading causes of death. Being able to accurately predict heart attacks before they happen could help decrease the fatality rate of heart attacks, as well as decrease the number of heart attacks that occur. Because of the limitations of human time and focus, machine learning has been utilized to attempt to find new ways of prediction. This study uses two machine learning techniques, logistic regression and an artificial neural network, in order to build a model to predict the probability someone has of experiencing a heart attack. The dataset contained 13 different features, each a different piece of medical information about a certain patient. These features were then used to predict the probability of the patient getting a heart attack. In addition to building a model for prediction, this study also attempts to evaluate the different features of the dataset and compare the importance of each feature to the overall prediction. The correlation between each feature and the overall prediction was examined. Moreover, each feature was also compared with the rest to find the difference in influence the features had on the overall prediction of the model. The results of this study show that the logistic regression model and artificial neural network model share a similar accuracy, with both models reaching an overall accuracy of 84%.