DRNN: Deep Residual Neural Network for Heart Disease Prediction

Abstract

Heart disease is one of the major diseases threatening human health. This paper proposed a novel deep neural network model to predict heart disease based on routine clinical data. We adapt the deep residual structure to discover a novel Deep Residual Neural Network (DRNN). In order to verify the effectiveness of DRNN, we performed experiments on Heart Disease UCI. The accuracy reached 95%, which is better than the traditional machine learning methods among Random Forest 83%, Decision Tree 68%, Logistic Regression 87%, KNN 60%, Native Bayes 80%.

Improving the Prediction of Heart Disease Using Ensemble Learning and Feature Selection

“…The optimizer used was adam and batch normalization was applied. In [13] Xiao et al (2020), have proposed a deep residual neural network (DRNN). The accuracy approached 95%, better than the various machine learning algorithms like decision tree 68%, logistic regression 87%, naive bayes 80%, knearest neighbors (KNN) 60%, and random forest 83%.…”