Ambulance Demand Forecasting: A Systematic Review of Existing Models
ABSTRACT
Forecasting ambulance demand is essential for improving Emergency Medical Services systems, guaranteeing prompt responses, and effectively allocating resources. With an emphasis on identifying important factors and their effects on demand, this systematic review offers an overview of the literature on forecasting ambulance demand. The goal of this study is to help increase the effectiveness and efficiency of ambulance services. The results highlight the importance of some factors in call center case volume, such as the day of the week, national holidays, and local disease incidence rates. Increased call volumes on weekdays highlight the necessity of accurate forecasting models that consider daily and weekly changes. In addition to temperature and relative humidity, weather factors such as wind speed and season also have a big impact. Additionally, seasonal patterns show that demand is higher in the winter, emphasizing the significance of seasonal adjustment in forecasting models. This review highlights the diversity of effective forecasting methods, with Artificial Neural Networks consistently emerging as the most effective approach. Tailoring forecasting models to local demographics and incorporating additional factors such as weather, air quality, and traffic patterns could enhance forecasting accuracy. This systematic review sheds light on the complex dynamics of ambulance demand forecasting, emphasizing the need for multifaceted models that adapt to diverse contexts. Accurate forecasts are crucial for optimizing emergency service resources, ultimately leading to improved patient care and more efficient healthcare systems. Future research should continue to explore these intricate relationships to advance the field and contribute to more effective ambulance services.
AUTHOR(S)
Elif ERBAY
