Integrating Machine Learning-Based Ambulance Travel Time Estimation into an Emergency Medical Services Simulation Modeling Framework

Travel time estimation is an integral component of emergency medical services (EMS) simulations due to the need to calculate ambulance transport times for patients. We present a study where we integrated a machine learning (ML) based ambulance travel time estimation module into an EMS simulation modeling framework, aiming to explore the potential benefits of using ML-based travel time estimations in emergency simulations. To illustrate the effectiveness of the proposed approach, we used the framework to construct an EMS simulation model for stroke patients and applied it in a scenario study covering Skåne County, Sweden. The result of the simulation shows differences in ambulance driving times when using the ML-based module compared to existing routing engines designed for passenger cars. The observed differences emphasize the impacts of integrating ML-based estimations into EMS simulations.