Bindu Mogilicherla

Queue Cure '26 – AI-Powered Real-Time Hospital Queue Management System

Hospitals often face long patient waiting times and overcrowded reception areas due to manual queue management. Patients have little visibility into their queue position, expected waiting time, or token status, leading to frustration and poor user experience. Receptionists also spend significant time managing queues manually, updating patient status, and answering repetitive inquiries. The absence of a digital queue system reduces operational efficiency and makes it difficult to provide a smooth healthcare experience. Queue Cure was developed to address these challenges by creating a centraliz Process I began by studying common problems faced in hospital waiting areas and identifying key pain points for patients and receptionists. After defining the requirements, I designed two separate user flows: one for receptionists who manage the queue and another for patients who track their token status. The frontend was built using React and Vite to create a fast and responsive user experience. For the backend, I selected Spring Boot because of its scalability and strong REST API support. MySQL was chosen to store patient and queue information. I designed APIs for patient registration, token generation, queue tracking, and waiting list management. During development, I faced challenges while deploying the backend and cloud database. Initially, I attempted to deploy the backend using Render. Results Queue Cure successfully demonstrates a digital hospital queue management workflow that improves transparency and reduces manual queue handling. The platform provides token generation, queue visualization, patient tracking, and receptionist management capabilities through an intuitive interface. The frontend has been successfully deployed and is accessible online, allowing stakeholders to evaluate the solution. The project establishes a scalable foundation for future AI-powered waiting-time prediction and advanced hospital analytics features. Reflection I successfully implemented AI-based waiting-time prediction using historical queue and consultation patterns to provide patients with estimated waiting times. If given additional time, I would complete full cloud deployment of the backend infrastructure and implement real-time synchronization using WebSockets so patients receive instant queue updates. I would also enhance the prediction model with larger datasets and improve its accuracy, while developing role-based authentication for hospital staff. Further user testing with healthcare professionals would help validate assumptions and improve