Remote Cardiac System Monitoring Using 6G-IoT Communication and Deep Learning

Remote patient monitoring has recently been popularised due to advanced technological innovations. The advent of the Sixth Generation Internet of Things (6G-IoT) communication technology, combined with deep learning algorithms, presents a groundbreaking opportunity for enhancing remote cardiac system monitoring. This paper proposes an innovative framework leveraging the ultra-reliable, low-latency communication capabilities of 6G-IoT to transmit real-time cardiac data from wearable devices directly to healthcare providers. Integrating deep learning models facilitates the accurate analysis and prediction of cardiac anomalies, significantly improving traditional monitoring systems. Our methodology involves the deployment of cutting-edge wearable sensors capable of capturing high-fidelity cardiac signals. These signals are transmitted via 6G-IoT networks, ensuring minimal delay and maximum reliability. Upon receiving the data, a densely connected deep neural network with an optimised swish activation function—designed explicitly for cardiac anomaly detection is employed to analyse the data in real-time. These algorithms are trained on vast datasets to recognise patterns indicative of potential cardiac issues, allowing immediate intervention when necessary. The proposed system’s efficacy is validated through extensive testing in simulated environments, demonstrating its ability to accurately detect and swiftly predict a wide range of cardiac conditions. Moreover, implementing 6G-IoT communication ensures the system's scalability and adaptability to future technological advancements.