Predicting Cardiovascular Disease by Integrating the Dataset and DNN with Asynchronous Learning Technique

Abstract

Predicting cardiovascular illness via the integration of datasets and deep neural networks using an asynchronous learning methodology. Healthcare experts see the prediction of cardiac disease as a critical endeavour, while deep learning has shown considerable potential in accomplishing this objective. This research study presents a unique methodology termed the Asynchronous Federated Deep Learning Approach aimed at Cardiac Predictions (AFLCP), which integrates a heart disease dataset along with DNN through an asynchronous learning strategy. Suggested method utilises an asynchronous parameter update mechanism for deep neural networks and integrates a temporally weighted aggregate strategy to improve the convergence and accuracy of core model. The efficacy of the proposed AFLCP technique is assessed using two datasets across several DNN architectures, revealing that proposed AFLCP method surpasses baseline technique for communication expenses and model correctness.