QueueCure-AI: Intelligent Hospital Queue Management & Emergency Triage System

Hospitals often rely on traditional First-In-First-Out (FIFO) queue systems where patients are served strictly based on arrival time. This approach does not account for medical urgency, causing critical patients to wait behind routine consultations. Receptionists manually manage queues, patients lack visibility into their waiting status, and doctors receive limited real-time information. These inefficiencies increase waiting-room anxiety, delay treatment for high-priority cases, and reduce overall operational efficiency. QueueCure-AI was developed to create an intelligent, transparent. Process We began by studying common hospital queue workflows and identifying pain points faced by patients, doctors, and reception staff. We designed a role-based system consisting of Patients, Doctors, Receptionists, Hospitals, and Administrators. We built a full-stack architecture using React, Node.js, Express, MongoDB, and Socket.IO to enable real-time updates. An AI-assisted triage engine was introduced to map patient symptoms to appropriate specialties and assign priority levels. We then implemented queue management, appointment booking, emergency fast-track overrides, analytics dashboards, and real-time lobby displays. Synthetic datasets were generated to simulate realistic hospital operations and validate the system under larger workloads. Results QueueCure-AI successfully demonstrates a real-time hospital queue management platform capable of handling patient registration, appointment scheduling, emergency prioritization, and queue synchronization. The system generated and processed datasets containing 1,000 patients, 100 doctors, 25 hospitals, 5,000 appointments, and 2,000 queue entries. Real-time updates ensure that lobby displays, reception dashboards, and doctor consoles remain synchronized. The solution improves transparency, reduces queue uncertainty, and provides a scalable foundation for smarter healthcare operations. Reflection Given additional time, we would integrate real hospital data sources, implement advanced machine learning models for symptom severity prediction, add voice-based triage for kiosk users, and deploy the platform to a cloud infrastructure with production-grade monitoring and security controls. We would also conduct pilot testing with healthcare professionals to gather usability feedback and further optimize patient workflows.