Real-Time Intelligent Healthcare Ambulance Monitoring and Emergency Prediction System Using Machine Learning and Computer Vision

Emergency situations require timely assessment of patient conditions and effective coordination between the people who report a case, the clinicians who prioritise it and the ambulances that respond. This paper presents a web-based prototype that brings these activities together in a single application. The proposed system combines machine learning, computer vision and a monitoring dashboard. Patient vitals and reported symptoms are entered through a web interface, and a machine-learning model estimates the patient's emergency (triage) category together with class probabilities. A computer-vision module demonstrates preliminary analysis of uploaded scene images or video frames. An ambulance-monitoring dashboard displays active emergencies, ambulance availability, a city map with unit positions and an operations log, and a dispatch workflow demonstrates the assignment of an ambulance to a registered case. The backend is implemented in Python using the Flask framework, and the front end uses HTML, CSS and JavaScript. The current prototype uses simulated ambulance information rather than live GPS tracking, and the computer-vision output is not a clinically validated diagnosis. The system is intended to support decision-making and to serve as a foundation for future research; it is not a substitute for professional medical assessment.