Scalable Cloud-Edge Collaborative Framework for Real-Time Clinical Decision Support Systems

Abstract

Clinical Decision Support Systems (CDSS) are becoming a necessity to support and enhance patient outcomes through the timely and information-driven medical decisions. Nevertheless, the classic cloud-based CDSS design usually has a high latency, bandwidth, and scalability, and is not applicable to real-time healthcare use cases like remote monitoring and critical care. In the effort to overcome these challenges, the proposed study suggests scaling cloud-edge collaborative framework as a method of delivering real-time clinical decision-making support. In the proposed system, edge computing is used to provide low latency data processing and cloud infrastructure to provide advanced analytics and storage, which can be used to efficiently allocate tasks and respond with shorter reaction times. The framework is executed with the help of multi-layer architecture that includes data acquisition, edge processing and cloud coordination modules. An exhaustive experimental analysis is also done under different workloads in order to measure system performance. Key metrics, such as latency, throughput, scalability, and resource utilization are examined. The findings indicate that the end-to-end latency is reduced significantly and the throughput is improved in comparison with the traditional cloud-only solutions. The system is also highly scalable and the performance does not change with the number of attached devices. In general, the suggested framework will increase the responsiveness and efficiency of the CDSS, which is why it can be used in real-time healthcare settings. The work can be used to further develop intelligent healthcare systems by offering a scalable and powerful next-generation clinical decision support system.