Performance Evaluation of Artificial Neural Network Models for the Prediction of the Risk of Heart Disease

According to world health organization, cardiovascular diseases are the number one cause of death globally and most of them can be prevented by addressing risk factors such as tobacco use, unhealthy diet and obesity, physical inactivity, high blood pressure, diabetes and raised lipids. Hence early and correct diagnosis and administering the appropriate and effective treatment is important. Physicians often make decisions based on current clinical tests and previous experience of diagnosing patients with similar symptoms but it is a difficult task since a lot of factors are contributing to the prediction. In this paper, a clinical decision support system is designed and implemented that can help the doctors in predicting the risk of heart disease. This system is based on the optimal artificial neural network model identified among the different models evaluated using accuracy measures on standard heart disease database. An interface is also developed based on the optimal model to facilitate the doctors in predicting the risk of heart diseas