Ambulance allocation considering the spatial randomness of demand

Abstract

To guarantee that emergency calls can be responded to in time, the government is obliged to implement an effective ambulance location plan. In practice, emergency medical service (EMS) systems work in an uncertain environment with stochastic demand, response time, and travel time. The uncertainty of these factors significantly affects ambulance location planning. However, most recent studies in this field fail to adequately consider the effect of the spatial uncertainty of demand since it is difficult to describe quantitatively. As a result, most allocation plans are not efficient. In this study, Gaussian mixture model clustering is innovatively utilized to quantitatively describe spatially uncertain demand. Accordingly, the chance constraint programming model for ambulance allocation planning is developed. The objective is to minimize the sum of the cost of patient lives lost and the operational cost of the emergency facilities. Two years of data from the Shanghai Songjiang District are used to validate the proposed method. The data from 2013 are utilized to fit the spatial distribution of demand. The data from 2014 are used to test and verify the obtained models. The experimental results demonstrate that the delay time can be significantly decreased with the proposed methods. Furthermore, compared with other classic assumptions for the spatial randomness of demand in this field, better service performance and lower cost are obtained with the proposed methods.