On Machine Learning Models for Heart Disease Diagnosis

Convolutional Neural Networks (CNNs) have different architecture than regular Neural Networks (NNs) and are both applied extensively in many application fields. In this article, we used both of the two machine learning models in the heart disease diagnosis problems. We implemented the algorithms, tuned the parameters, and conducted a series of experiments. We aim to compare the prediction accuracy of the two models under different parameters settings. We used the Cleveland database which is took from UCI learning dataset repository for diagnosis heart disease. From the experimental results, we found that NNs outperform CNNs in prediction accuracy in most of the cases.