Ambulance travel times predicted more accurately with ai system
Beyond Heuristics and Commercial Navigation: An AI-Augmented Decision-Support for Ambulance Travel Time Estimation
Machine Learning
Summary
Estimating how long an ambulance will take to reach its destination is important for emergency responses. The authors found that simple assumptions like ambulances always driving a bit faster than regular cars are often wrong. By using real ambulance trip data from Sweden, they showed travel times change depending on the hour, day, and urgency of the trip. They built an AI system that better predicts ambulance travel times and used explanation tools to make sure the system’s decisions make sense to ambulance operators.
What this means in practice
- •For emergency dispatch teams: Improve ambulance routing by using AI-driven travel time estimates that reflect real emergency conditions and trip priorities.
- •For city traffic planners: Incorporate nuanced ambulance travel time predictions to better design traffic controls that prioritize emergency vehicles.
Authors
Muhammad Adil Abid, Johan Holmgren, Fabian Lorig, Jesper Petersson
Abstract
Accurate ambulance travel time estimation is critical for emergency medical dispatch, yet existing decision-support practices often rely on static lookup tables or simplified assumptions regarding how ambulance travel time differs from ordinary passenger-car travel. For instance, they assume ambulances simply travel a fixed percentage (e.g., 5%) faster than ordinary passenger cars. However, such assumptions are rarely validated using real ambulance operational data and may fail to capture the effects of trip priority, temporal context, and origin-destination. We address these limitations using historical ambulance trips from the Skåne region in Sweden. Our analysis reveals that ambulance travel times vary substantially by hour, day, and trip priority, and that commercial navigation systems fail to capture emergency-specific dynamics. We contribute a machine learning system to more accurately estimate ambulance travel time. To make the system interpretable, we explored SHapley Additive exPlanations and permutation importance techniques to ensure that our system captures operationally meaningful patterns.