AI-Augmented Telemedicine Queue Management System for Time-Critical Consultations

Abstract

Telemedicine has now been one of the central components of the contemporary healthcare provision notably in areas of time-sensitive responses like emergency care delivery, stroke expertise, and emergency triage. However, conservative queue management strategies may not have dynamic prioritization of patients basing on clinical emergencies. Therefore, creating delays and poor outcome. The present paper offers an AI-Augmented Queue Management System (AI-QMS), which assimilates two different machine-learning schemes urgency prediction and reinforcement learning-conducted scheduling, to maximize telemedicine queues. The system was simulated in a discrete-event scenario using both synthetic and real-world data sets in order to address the performance measures such as mean waiting time and service level conformance and patient satisfaction index. Findings show that the waiting time under high-priority cases has a huge reduced balance (up to 35%) compared with both first-come, first-served (FCFS) triage and rule-based triage measures. The proposed system is a scalable application that would improve responsiveness and efficiency of telemedicine services.