A Dynamic Redeployment System for Mobile Ambulances in Qatar, Empowered by Deep Reinforcement Learning

Efficiently managing ambulance deployment is crucial for the success of emergency medical services, ensuring timely responses and life-saving care delivery. The initial ambulance location problem poses a challenge, demanding optimal deployment strategies to minimize response times and maximize coverage. Traditional approaches rely on heuristics and predetermined rules, struggling to adapt to the dynamic nature of emergencies. In response, this study proposes a dynamic ambulance redeployment system to reduce ambulance response time, increasing the chances of saving lives. The system identifies available ambulances finishing patient transports and strategically redistributes them to designated spokes, enhancing readiness for future emergencies. Addressing the inherent complexity, the study introduces a deep score network, utilizing Deep Reinforcement Learning (DRL) to train the network effectively. Our proposed approach achieved approximately 75% reduction in delays in Average Response Times (AvRT), utilizing real data from Qatar in a realistic deployment scenario. The outcome is a dynamic ambulance redeployment algorithm for real-world application, supported by experimental results using real-world data.