Advanced recurrent neural network with tensorflow for heart disease prediction

Abstract

Heart disease has become one of the most critical disease that cause highest mortality rate. Deep learning is a subfield of machine learning that is based on learning multiple levels of representation and abstraction. In this paper we aim to present our proposed model on the heart disease prediction. This model aims to perform an advanced Recurrent Neural Network (RNN) model of deep learning to increase the accuracy of the existing model of predictions, which should be more than 98.23%. This paper discusses about the deep learning methods, draw comparison of performance among the existing systems and propose an enhanced RNN model to provide a better in terms of accuracy and feasibility. The presence of multiple Gated Recurrent Unit (GRU) have improvised the RNN model performance with 98.4% of accuracy. The Cleveland data for this study are obtained from UCI Repository. The further research and advancement possibilities are also mentioned in the paper.