Enhancing offloading with cybersecurity in edge computing for digital twin-driven patient monitoring

Abstract

In healthcare, the use of digital twin (DT) technology has been recognised as essential for enhancing patient care through real-time remote monitoring. However, concerns regarding risk prediction, task offloading, and data security have been raised due to the integration of the Internet of Things (IoT) in remote healthcare. In this study, a new method was introduced, combines edge computing with sophisticated cybersecurity solutions. A vast amount of environmental and physiological data has been gathered, allowing for thorough understanding of patients. The system included hybrid encryption, threat prediction, Merkle Tree verification, certificate-based authentication, and secure communication. The feasibility of the proposal was evaluated by using an ESP32-Azure IoT Kit and Azure Cloud to evaluate the system's capacity to securely send patient data to healthcare institutions and stakeholders, while simultaneously upholding data confidentiality. The system demonstrated a notable improvement in encryption speed, with 27.18%, represented as the improved efficiency and achieved storage efficiency ratio 0.673. Furthermore, the evidence from the simulations showed that the system's performance was not affected by encryption since encryption times continuously remained within a narrow range. Moreover, proactive alert of probable security risks would be detected from the predictive analytics, hence strong data integrity assurance. The results suggest the proposed system provided a proactive, personalised care approach for cybersecurity-protected DT healthcare (DTH) high-level modelling and simulation, enabled via IoT and cloud computing under improved threat prediction.