Skip to main content

Predicting ambulance demand using singular spectrum analysis

Abstract

This paper demonstrates techniques to generate accurate predictions of demand exerted upon the Emergency Medical Services (EMS) using data provided by the Welsh Ambulance Service Trust (WAST). The aim is to explore new methods to produce accurate forecasts that can be subsequently embedded into current OR methodologies to optimise resource allocation of vehicles and staff, and allow rapid response to potentially life-threatening emergencies. Our analysis explores a relatively new non-parametric technique for time series analysis known as Singular Spectrum Analysis (SSA). We explain the theory of SSA and evaluate the performance of this approach by comparing the results with those produced by conventional time series methods. We show that in addition to being more flexible in approach, SSA produces superior longer-term forecasts (which are especially helpful for EMS planning), and comparable shorter-term forecasts to well established methods.

This is a preview of subscription content, access via your institution.

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8

Notes

  1. 1.

    Category A calls are immediately life-threatening calls.

  2. 2.

    Categories B and C calls represent all other emergency calls.

References

  1. Aldrich C, Hisserich J and Lave L (1971). An analysis of the demand for emergency ambulance service in an urban area. American Journal of Public Health 61: 1156–1169.

    Article  Google Scholar 

  2. Baker J and Fitzpatrick K (1986). Determination of an optimal forecast model for ambulance demand using goal programming. Journal of the Operational Research Society 37 (11): 1047–1059.

    Article  Google Scholar 

  3. Box G and Jenkins G (1970). Time Series Analysis, Forecasting and Control. Holden-Day Incorporated: San Francisco.

    Google Scholar 

  4. Brockwell P and Davis R (2002). Introduction to Time Series and Forecasting, 2nd edn. Springer-Verlag: New York.

    Book  Google Scholar 

  5. Broomhead D and King G (1986). Extracting qualitative dynamics from experimental data. Physica D: Nonlinear Phenomena 20 (2–3): 217–236.

    Article  Google Scholar 

  6. Broomhead D, Jones R, King G and Pike E (1987). Singular System Analysis with Application to Dynamical Systems. CRC Press: Bristol.

    Google Scholar 

  7. Brotcorne L, Laporte G and Semet F (2003). Ambulance location and relocation models. European Journal of Operational Research 147: 451–463.

    Article  Google Scholar 

  8. Channouf N, L'Ecuyer P, Ingolfsson A and Avramidis A (2007). The application of forecasting techniques to modelling emergency medical system calls in Calgary, Alberta. Health Care Management Science 10 (1): 25–45.

    Article  Google Scholar 

  9. Chatfield C (2001). Time Series Forecasting. CRC Press: Florida.

    Google Scholar 

  10. Colebrook J (1978). Continuous plankton records—Zooplankton and environment, Northeast Atlantic and North Sea, 1948–1975. Oceanologica Acta 1: 9–23.

    Google Scholar 

  11. Efron B and Tibshirani R (1993). An Introduction to the Bootstrap. Chapman & Hall/CRC: New York, London.

    Book  Google Scholar 

  12. Fildes R, Nikolopoulos K, Crone S and Syntetos A (2008). Forecasting and operational research: A review. Journal of the Operational Research Society 59 (9): 1150–1172.

    Article  Google Scholar 

  13. Gardner E (1985). Exponential smoothing: The state of the art. Journal of Forecasting 4 (1): 1–28.

    Article  Google Scholar 

  14. Ghil M, Allen M, Dettinger M, Ide K, Kondrashov D, Mann M, Robertson A, Saunders A, Tian Y, Varadi F and Yiou P (2001). Advanced spectral methods for climatic time series. Reviews of Geophysics 40 (1): 3.1–3.41.

    Google Scholar 

  15. Goldberg J (2004). Operations research models for the deployment of emergency service vehicles. EMS Management Journal 1 (1): 20–39.

    Google Scholar 

  16. Golyandina N, Nekrutkin V and Zhigljavsky A (2001). Analysis of Time Series Structure: SSA and Related Techniques. Chapman & Hall/CRC: New York, London.

    Book  Google Scholar 

  17. Green L and Kolesar P (2004). Improving emergency responsiveness with management science. Management Science 50 (8): 1001–1014.

    Article  Google Scholar 

  18. Green L, Kolesar P and Whitt W (2007). Coping with time-varying demand when setting staffing requirements for a service system. Production and Operations Management 16 (1): 13–39.

    Article  Google Scholar 

  19. Hall W (1971). Management science approaches to the determination of urban ambulance requirements. Socio-economic Planning Sciences 5 (5): 491–499.

    Article  Google Scholar 

  20. Hassani H (2007). Singular spectrum analysis: Methodology and comparison. Journal of Data Science 5: 239–257.

    Google Scholar 

  21. Hassani H, Soofi A and Zhigljavsky A (2010). Predicting daily exchange rate with singular spectrum analysis. Nonlinear Analysis: Real World Applications 11: 2023–2034.

    Article  Google Scholar 

  22. Holcomb J and Sharpe N (2007). Forecasting police calls during peak times for the city of Cleveland. CS-BIGS 1 (1): 47–53.

    Google Scholar 

  23. Hyndman R and Khandakar Y (2008). Automatic time series forecasting: the forecast package for R. Journal of Statistical Software 27 (3): 1–22.

    Article  Google Scholar 

  24. Ingolfsson A, Akhmetshina E, Budge S and Li Y (2007). A survey and experimental comparison of service-level-approximation methods for nonstationary M(t)/M/s(t) queueing systems with exhaustive discipline. INFORMS Journal of Computing 19 (2): 201–214.

    Article  Google Scholar 

  25. Jolliffe I (2008). Principal Component Analysis, 2nd edn. Springer-Verlag: New York.

    Google Scholar 

  26. Kamentzky R, Shuman L and Wolfe H (1982). Estimating need and demand for prehospital care. Operations Research 30 (6): 1148–1167.

    Article  Google Scholar 

  27. Kvålseth T and Deems J (1979). Statistical models of the demand for emergency medical services in an urban area. American Journal of Public Health 69 (3): 250–255.

    Article  Google Scholar 

  28. Li Y and Kozan E (2009). Rostering ambulance services. Asia Pacific Industrial Engineering and Management Systems Conference, Kitakyushu International Conference Center, Kitakyushu, Japan.

    Google Scholar 

  29. Lightfoot Solutions (2009). Efficiency review of the Welsh Ambulance Services NHS Trust, http://www.ambulance.wales.nhs.uk/assets/documents/e7b60166-639f-440f-b715-8922e6b032ef633959717392816442.pdf, accessed 2 June 2010.

  30. Matteson D, McLean M, Woodard D and Henderson S (2011). Forecasting emergency medical service call arrival rates. The Annals of Applied Statistics 5 (2B): 1379–1406.

    Article  Google Scholar 

  31. McConnel C and Wilson R (1998). The demand for prehospital emergency services in an aging society. Social Science and Medicine 46 (8): 1027–1031.

    Article  Google Scholar 

  32. Rodó X, Pascual M, Fuchs G and Faruque A (2002). ENSO and cholera: A nonstationary link related to climate change? PNAS 99 (20): 12901–12906.

    Article  Google Scholar 

  33. Setzler H, Park S and Saydam C (2005). Developing accurate forecasts for ambulance demand via artificial neural networks: a framework. 35th International Conference on Computers and Industrial Engineering, Istanbul, Turkey.

  34. Setzler H, Park S and Saydam C (2009). EMS call volume predictions: A comparative study. Computers & Operations Research 36: 1843–1851.

    Article  Google Scholar 

  35. Siler K (1975). Predicting demand for publicly dispatched ambulances in a metropolitan area. Health Services Research 10 (3): 254–263.

    Google Scholar 

  36. Thomakos D, Wang T and Wille L (2002). Modeling daily realized futures volatility with singular spectrum analysis. Physica A: Statistical Mechanics and its Applications 312 (3–4): 505–519.

    Article  Google Scholar 

  37. Vautard R and Ghil M (1989). Singular spectrum analysis in nonlinear dynamics, with applications to paleoclimatic time series. Physica D: Nonlinear Phenomena 35 (3): 395–424.

    Article  Google Scholar 

  38. Weare B and Nasstrom J (1982). Examples of extended empirical orthogonal function analyses. Monthly Weather Review 110: 481–485.

    Article  Google Scholar 

  39. Welsh Ambulance Services NHS Trust (2007). Time to make a difference: Transforming ambulance services in Wales. A modernisation plan for ambulance services and NHS Direct Wales Final Report, http://www.ambulance.wales.nhs.uk/assets/documents/c4cc0416-9fab-4dea-8753-247a9431c4c7633446359123733750.pdf, accessed 2 June 2010.

  40. Yiou P, Baert E and Loutre M (1996). Spectral analysis of climate data. Surveys in Geophysics 17: 619–663.

    Article  Google Scholar 

Download references

Acknowledgements

This research is being funded by EPSRC grant EP/F033338/1 as part of the LANGS initiative. The authors thank the Welsh Ambulance Service Trust for the cooperation in providing the data and particularly Andrew Rees, Senior Information Analyst at the Health Informatics Department, for his helpful comments and advice.

Author information

Affiliations

Authors

Corresponding author

Correspondence to P R Harper.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Vile, J., Gillard, J., Harper, P. et al. Predicting ambulance demand using singular spectrum analysis. J Oper Res Soc 63, 1556–1565 (2012). https://doi.org/10.1057/jors.2011.160

Download citation

Keywords

  • health service
  • emergency medical services
  • forecasting
  • singular spectrum analysis