Edge AI for Healthcare Operations: From Real-Time Monitoring to Organizational Intelligence

The rapid evolution of Edge Computing and Artificial Intelligence has created unprecedented opportunities for healthcare systems to process data closer to its source, reducing latency and enabling real-time decision-making. The Internet of Medical Things (IoMT) now generates vast amounts of clinical and operational data across hospitals, from patient monitoring devices to energy management systems and staff tracking solutions.Current research on Edge AI in healthcare predominantly focuses on clinical applications: real-time patient monitoring, diagnostic support, and alert systems for critical events. These contributions are valuable, yet they address only one dimension of hospital complexity. Healthcare organizations operate as intricate ecosystems where clinical outcomes are deeply intertwined with operational efficiency, resource allocation, and energy sustainability.A significant gap exists in the literature regarding the application of Edge AI to healthcare operations and management. While centralized Machine Learning approaches have demonstrated effectiveness in optimizing hospital efficiency, staff scheduling, and resource allocation, these solutions typically rely on batch processing and cloud-based architectures that introduce latency and limit responsiveness to dynamic conditions.The convergence of Edge Computing with AI offers a transformative opportunity: enabling distributed organizational intelligence that can support real-time managerial decisions at the point of need. This includes dynamic bed management, predictive staff allocation, energy optimization based on occupancy patterns, and patient flow coordination across departments.Furthermore, the post-pandemic healthcare landscape demands more resilient and adaptive systems capable of responding to sudden changes in demand, resource availability, and operational constraints. Edge AI architectures provide the technical foundation for such adaptability while addressing critical concerns about data privacy, network reliability, and computational efficiency.This Research Topic aims to bridge the gap between clinical Edge AI applications and healthcare operational intelligence. We seek to advance the understanding of how distributed AI architectures can support real-time decision-making in hospital management, resource optimization, and organizational efficiency. The collection will explore novel frameworks, methodologies, and empirical studies that demonstrate how Edge AI can transform healthcare operations beyond patient monitoring, contributing to more sustainable, efficient, and responsive healthcare systems.We welcome original research articles, reviews, and case studies addressing the intersection of Edge AI and healthcare operations. Topics of interest include, but are not limited to:• Edge-based architectures for real-time hospital resource allocation and bed management• Distributed AI models for staff scheduling and workforce optimization• Energy efficiency optimization through Edge AI in healthcare facilities• Patient flow prediction and coordination using edge-deployed algorithms• Federated and privacy-preserving approaches for operational data analysis• Integration frameworks connecting clinical IoMT data with operational decision systems• Explainable AI methods for transparent managerial decision support at the edge• Multi-tier computing architectures balancing edge, fog, and cloud processing for healthcare operations• Case studies from hospital implementations with measurable operational outcomes• Comparative analyses of centralized versus distributed AI approaches in healthcare management Topic editors: Agostino Marengo, Professor Richard Hill Source: https://www.frontiersin.org/research-topics/77562/edge-ai-for-healthcare-operations-from-real-time-monitoring-to-organizational-intelligence