Optimize the Planning of Ambulance Standby Points by Using Getis-Ord Gi* Based on Historical Emergency Data

In this paper, we first find the hot spots of emergency call events from a large number of historical pre-hospital medical data, and then plan ambulance standby points to shorten the time to the emergency scenes. The Getis-Ord Gi* method for calculating the local spatial autocorrelation index is introduced as a screening tool for ambulance standby locations. First aid call data are selected according to different time granularities, and the results of ambulance standby point planning with annual cycle are obtained by analyzing hot call areas extracted under different time granularities. By adjusting the significance level of hot call areas extracted, different numbers of ambulance standby points and their importance can be obtained. In the case study, we figured out 6 standby points with a significance level of 95%, for 12 ambulances. This method has been applied in the medical emergency service in Minhang District, Shanghai.

[1]  Sean Shao Wei Lam,et al.  Simulation-based decision support framework for dynamic ambulance redeployment in Singapore , 2017, Int. J. Medical Informatics.

[2]  Yulong Bai Application of GPS/GIS technologies in the pre-hospital first aid: Lessons learned from Suzhou municipal hospital case study , 2009, 2009 17th International Conference on Geoinformatics.

[3]  A. Şişman,et al.  A geographic information system-based analysis of ambulance station coverage area in Samsun, Turkey. , 2013, Singapore medical journal.

[4]  J. Jui,et al.  Predicting Ambulance Time of Arrival to the Emergency Department Using Global Positioning System and Google Maps , 2013, Prehospital emergency care : official journal of the National Association of EMS Physicians and the National Association of State EMS Directors.

[5]  Hwei-Jen Lin,et al.  Demand Forecast and Multi-Objective Ambulance Allocation , 2018, Int. J. Pattern Recognit. Artif. Intell..

[6]  Yi-Chun Chang,et al.  Ambulance Dispatching System with Integrated Information and Communication Technologies on Cloud Environment , 2014, Int. J. Grid High Perform. Comput..

[7]  Albert Y. Chen,et al.  Demand Forecast Using Data Analytics for the Preallocation of Ambulances , 2016, IEEE Journal of Biomedical and Health Informatics.

[8]  Alka B. Patel,et al.  A validation of ground ambulance pre-hospital times modeled using geographic information systems , 2012, International Journal of Health Geographics.

[9]  J. Ord,et al.  Local Spatial Autocorrelation Statistics: Distributional Issues and an Application , 2010 .