Tharun N E

Queue Cure '26 – Real-Time Hospital Queue Management with AI Voice Announcements

Hospital OPD queues still rely on manual token systems that provide no real-time visibility to patients. Patients do not know their live position or accurate waiting time, leading to repeated inquiries at reception counters, crowding, and frustration. The core issue is not queue length, but the information delay between actual queue movement and patient awareness. Only receptionists have full visibility, creating an unfair information gap that slows down communication and reduces overall efficiency in patient flow. Process I analyzed OPD queue systems and identified that the main issue was information delay, not queue size. I broke the problem into three core needs: Visibility: Live queue position for patients Predictability: Accurate estimated waiting time Communication: Instant updates without manual interaction I evaluated multiple solutions: Manual token system → inefficient and non-transparent SMS-based updates → delayed and not real-time Static digital display → lacks personalization Real-time synchronized system → selected approach I iterated towards a real-time system using Socket.IO that ensures instant updates across all connected users. I also added dynamic wait time estimation based on queue position and consultation duration, and automated alerts to reduce receptionist workload. Results ⚡ 0-delay real-time queue synchronization across users ⏱ Dynamic wait time estimation updated continuously 📢 Automated alerts reduced manual receptionist communication 📱 Improved transparency between patients and staff 🔄 Reduced repeated queue inquiries and crowding at counters Reflection Next, I would integrate historical OPD data to improve prediction accuracy and introduce doctor-side scheduling optimization to reduce queue buildup at the source. I would also conduct real-world testing in clinic environments to validate system performance under high patient load and refine usability based on feedback.