Optimising Real-Time Patient Data For Heart Disease Prediction Using Deep Neural Networks

Heart disease is a common comorbidity in patients who die with covid-19. The use of wearable medical devices that track heart disease in real time may be able to lower COVID-19 death rates. Nevertheless, three major problems have arisen as a result of technological constraints. First, it's challenging to completely meet the real-time requirements using typical wireless communication technologies for wearable medical equipment. To add insult to injury, the massive amounts of real-time cardiac data are just too much for the existing monitoring technologies to handle. Thirdly, it is difficult to guarantee that there are enough physicians’ online to provide a quick, efficient, and correct diagnosis since the monitoring platform's diagnosis is often manual. In light of these concerns, this study suggests enhancing deep neural networks [DNN-HDP] for Heart Disease Prediction. First, 5G technology facilitates data transmission and reception from wearable medical equipment, enabling real-time monitoring of patient health status. This enables healthcare providers to quickly respond to any changes or emergencies, improving overall patient care and outcomes. The next thing to do is to use the Flink streaming data processing technology to get the ECG data. Finally, this article uses deep neural network models to automate the prediction of cardiovascular health using real-time patient data. Experimental and theoretical findings demonstrate that our concept effectively addresses the problems mentioned above and achieves a 99.29% improvement in the accuracy of cardiovascular disease prediction.