A New Deep Learning Method for Accurate Cardiac Heart Failure Prediction from RR Interval Measurements

Abstract

cardiovascular diseases are the major cause of death worldwide. Early detection of heart failure will assist patients and medical professionals in taking better precautions to reduce risks. The objective of this study is to find a technique that can reliably forecast the risk of cardiovascular illnesses. With the help of the training data we offer, deep learning algorithms like Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) make these predictions. Prediction accuracy will be reduced by a lack of medical data. As a part of our study, we examined DNN architectures to forecast cardiac failure. Over the training data, existing deep learning methods were employed. A new deep learning method that can predict heart failure using RR interval measurements is developed by comparing the accuracy performance of the proposed and existing models. The Physiobank NSR-RR and CHF-RR databases were used to compile the findings. The new model, which was based on experimental findings using these two free RR interval databases, attained a 94% accuracy rate compared to the existing model's 93.1% accuracy rate.