Predictive queue management in healthcare environments: A systematic review of IoT architectures, edge-based analytics and low-cognitive-load displays

The problem of overcrowding of the healthcare facilities and prolonged waiting time is becoming more frequent, and this negatively impacts patient satisfaction, clinical results, and the hospital's efficiency. Predictive queue management has emerged as the best practice for handling this issue as it combines the use of real-time sensing, smart analytics, and human-centric information delivery. The present review systematically analyzes the past to the future of predictive queue management in healthcare, especially emphasizing Internet of Things (IoT) architectures, edge-based predictive analytics, and low-cognitive-load display mechanisms. We study the various sensing technologies used, the architecture of the system, and the different methods of predicting the patient flow and waiting time in real-time conditions. Furthermore, we study the provision of visualization and the interaction strategies that are intended to reduce the cognitive load on both the patients and healthcare staff. The main problems that are identified include the quality of data, privacy, scalability, and human factors, and the discussion of future research directions for intelligent, deployable queue management systems in smart healthcare settings is provided.