Dynamic Emergency Medical Service Dispatch: Role of Spatiotemporal Machine Learning

  • Sunghwan Cho
  • Dohyeong KimEmail author
Part of the Global Perspectives on Health Geography book series (GPHG)


Previous research has suggested that providing prompt access to emergency medical services (EMS) may greatly improve the health outcomes of patients with urgent conditions. However, there has not been enough research on ways in which planning resources for ambulance dispatch may enhance the response time of EMS. GIS has been used to manage and visualize the spatial distribution of EMS demand, but there is still a need for more empirical evidence from spatiotemporal demand-based prediction techniques, such as machine learning. We applied the long short-term memory (LSTM) method to forecast EMS demands based on past records and reallocated service locations using a dynamic maximal covering location model. The training of the prediction models and validation were conducted with 323,993 emergency calls in the Gyeongnam Province in Korea in 2014. We found that conventional hotspot-based emergency dispatch systems, ignoring temporal variations of service demands, could fail to fulfill a desired coverage standard. This study shows an evidence that demand-based spatiotemporal demand prediction and dynamic dispatch protocol based on machine learning algorithm have the potential to support more efficient allocation of resources, especially when resources are limited.


EMS Machine learning GIS Spatiotemporal Response time Korea 



Emergency medical services


Geographic information systems


Long short-term memory


Multilayer perceptrons


Mean squared error


Response time


Safety center


Maximal covering location model


Ordinary least squares


  1. Abadi, M., Barham, P., Chen, J., Chen, Z., & Davis, A. (2016). Tensorflow: A system for large-scale machine learning. OSDI, Savannah, GA, USENIX.Google Scholar
  2. Bassil, K., Cole, D. C., Moineddin, R., Craig, A. M., Lou, W. Y., Schwartz, B., & Rea, E. (2009). Temporal and spatial variation of heat-related illness using 911 medical dispatch data. Environmental Research, 109(5), 600–606.CrossRefGoogle Scholar
  3. Blackwell, T. H., & Kaufman, J. S. (2008). Response time effectiveness: Comparison of response time and survival in an urban emergency medical services system. Academic Emergency Medicine, 9(4), 288–295.CrossRefGoogle Scholar
  4. Chen, A., & Lu T. (2014). A GIS-based demand forecast using machine learning for emergency medical services. 2014 international conference on computing in civil and building engineering. Orlando, FL, USA.Google Scholar
  5. Chen, A. Y., Lu, T., Ma, M. H., & Sun, W. (2016). Demand forecast using data analytics for the preallocation of ambulances. IEEE Journal of Biomedical and Health Informatics, 20(4), 1178–1187.CrossRefGoogle Scholar
  6. Cho, J., You, M., & Yoon, Y. (2017). Characterizing the influence of transportation infrastructure on emergency medical services (EMS) in urban area—A case study of Seoul, South Korea. PLoS One, 12(8), e0183241.CrossRefGoogle Scholar
  7. Church, R., & ReVelle, C. (1974). The maximal covering location problem. Papers of the Regional Science Association, 32, 101–118.CrossRefGoogle Scholar
  8. Dean, S. F. (2008). Why the closest ambulance cannot be dispatched in an urban emergency medical services system. Prehospital and Disaster Medicine, 23(2), 161–165.CrossRefGoogle Scholar
  9. Getis, A., & Ord, J. K. (1992). The analysis of spatial association by use of distance statistics. Geographical Analysis, 24, 188–205.Google Scholar
  10. Haghani, A., Hu, H., & Tian, Q. (2003). An optimization model for real-time emergency vehicle dispatching and routing. Washington, DC: Transportation Research Board.Google Scholar
  11. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.CrossRefGoogle Scholar
  12. Hong, K. H., Lee, K. J., Kim, J. T., & Lee, D. H. (2008). Severity-based analysis of prehospital transportation time using the geographic information system (GIS). Journal of the Korean Society of Emergency Medicine, 19(2), 153–160.Google Scholar
  13. Kim, D., Sarker, M., & Vyas, P. (2016). Role of spatial tools in public health policymaking of Bangladesh: Opportunities and challenges. Journal of Health, Population and Nutrition, 35(8), 1–5.Google Scholar
  14. Kingma, D., & Jimmy B. (2014). Adam: A method for stochastic optimization. arXiv Preprint arXiv 1412(6980).Google Scholar
  15. Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. International Joint Conference on Artificial Intelligence. Montreal, QB, Canada.Google Scholar
  16. Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems 25 (NIPS Proceedings 2012), pp. 1097–1105.Google Scholar
  17. Levi, K., Kharkar, R., Kiang, M., & Hartmann, C. (2017). Using machine learning to improve emergency medical dispatch decisions. 23rd ACM SIGKDD conference on knowledge discovery and data mining. Halifax, NS, Canada.Google Scholar
  18. Li, X., Zhao, Z., Zhu, X., & Wyatt, T. (2011). Covering models and optimization techniques for emergency response facility location and planning: A review. Mathematical Methods of Operations Research, 74(3), 281–310.CrossRefGoogle Scholar
  19. Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the future—Big data, machine learning, and clinical medicine. New England Journal of Medicine, 375(13), 1216–1219.CrossRefGoogle Scholar
  20. Ong, M. E., Ng, F. S., Overton, J., Yap, S., Anderson, D., Yong, D. K., Lim, S. H., & Anantharaman, V. (2009). Geographic-time distribution of ambulance calls in Singapore: Utility of geographic information system in ambulance deployment (CARE 3). Annals Academy of Medicine, 38(3), 184–191.Google Scholar
  21. Orbach, J. (1962). Principles of neurodynamics. Perceptrons and the theory of brain mechanisms. Archives of General Psychiatry, 7(3), 218–219.CrossRefGoogle Scholar
  22. Peleg, K., & Pliskin, J. S. (2004). A geographic information system simulation model of EMS: Reducing ambulance response time. The American Journal of Emergency Medicine, 22(3), 164–170.CrossRefGoogle Scholar
  23. Pell, J. P., Sirel, J. M., Marsden, A. K., Ford, I., & Cobbe, S. M. (2001). Effect of reducing ambulance response times on deaths from out of hospital cardiac arrest: Cohort study. BMJ, 322, 1385–1388.CrossRefGoogle Scholar
  24. Peters, J., & Hall, G. B. (1999). Assessment of ambulance response performance using a geographic information system. Social Science & Medicine, 49(11), 1551–1556.CrossRefGoogle Scholar
  25. Pons, P. T., Haukoos, J. S., Bludworth, W., Cribley, T., Pons, K. A., & Markovchick, V. J. (2005). Paramedic response time: Does it affect patient survival? Academic Emergency Medicine, 12(7), 594–598.CrossRefGoogle Scholar
  26. Revelle, C., Bigman, D., Schilling, D., Cohon, J., & Church, R. (1977). Facility location: A review of context-free and EMS models. Health Services Research, 12(2), 129–146.Google Scholar
  27. Rogers, F. B., Rittenhouse, K., & Gross, B. W. (2015). The golden hour in trauma: Dogma or medical folklore? Injury, 46, 525–527.CrossRefGoogle Scholar
  28. Roudsari, B. S., Nathens, A. B., Arreola-Risa, C., Cameron, P., Civil, I., Grigoriou, G., Gruen, R. L., Koepsell, T. D., Lecky, F. E., Lefering, R. L., Liberman, M., Mock, C. N., Oestern, H. J., Petridou, E., Schildhauer, T. A., Waydhas, C., Zargar, M., & Rivara, F. P. (2007). Emergency medical service (EMS) systems in developed and developing countries. Injury, 38(9), 1001–1013.CrossRefGoogle Scholar
  29. Savas, E. S. (1969). Simulation and cost-effectiveness analysis of New York’s emergency ambulance service. Management Science, 15(12), 608–627.CrossRefGoogle Scholar
  30. Washington D.C. Fire and EMS Department. (2018). EMS response time. Retrieved 20 May 2018, from
  31. Zarandi, M., Davari, S., & Sisakht, S. (2013). The large-scale dynamic maximal covering location problem. Mathematical and Computer Modeling, 57, 710–719.CrossRefGoogle Scholar
  32. Zhou, Z. (2016). Predicting ambulance demand: Challenges and methods. 2016 ICML workshop. New York, NY.Google Scholar
  33. Zhou, Z., Matteson, D. S., Woodard, D. B., Henderson, S. G., & Micheas, A. C. (2013). A spatio-temporal point process model for ambulance demand. Journal of the American Statistical Association, 110(509), 6–15.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Korea Land and Geospatial Informatrix CorporationDeokjin-gu, Jeonju-siSouth Korea
  2. 2.University of Texas at DallasRichardsonUSA

Personalised recommendations