Weather factors in the short-term forecasting of daily ambulance calls
- 573 Downloads
The daily ambulance demand for Hong Kong is rising, and it has been shown that weather factors (temperature and humidity) play a role in the demand for ambulance services. This study aimed at developing short-term forecasting models of daily ambulance calls using the 7-day weather forecast data as predictors. We employed the autoregressive integrated moving average (ARIMA) method to analyze over 1.3 million cases of emergency attendance in May 2006 through April 2009 and the 7-day weather forecast data for the same period. Our results showed that the ARIMA model could offer reasonably accurate forecasts of daily ambulance calls at 1–7 days ahead of time and with improved accuracy by including weather factors. Specifically, the inclusion of average temperature alone in our ARIMA model improved the predictability of the 1-day forecast when compared to that of a simple ARIMA model (8.8 % decrease in the root mean square error, RMSE = 53 vs 58). The improvement in the 7-day forecast with average temperature as a predictor was more pronounced, with a 10 % drop in prediction error (RMSE = 62 vs 69). These findings suggested that weather forecast data can improve the 1- to 7-day forecasts of daily ambulance demand. As weather forecast data are readily accessible from Hong Kong Observatory’s official website, there is virtually no cost to including them in the ARIMA models, which yield better prediction for forward planning and deployment of ambulance manpower.
KeywordsEmergency ambulance service Time series analysis Autoregressive integrated moving average model Weather
The research is supported in part by (1) Hui-Oi-Chow Trust Fund, the University of Hong Kong, and (2) General Research Fund, Research Grants Council of Hong Kong. We are grateful to the following government departments of the Hong Kong Special Administrative Region for data access: Hong Kong Observatory and Hospital Authority.
None to declare.
Ethical approvals have been obtained from the University of Hong Kong Human Research Ethics Committee for Non-Clinical Faculties.
- Abeku TA, Vias SJ, Borsboom G, Teklehaimanot A, Kebede A, Olana D, Oortmarssen GJ, Habbema JDF (2002) Forecasting malaria incidence from historical morbidity patterns in epidemic-prone areas of Ethiopia: a simple seasonal adjustment method perform best. Trop Med Int Health 7(10):851–857CrossRefGoogle Scholar
- Allard R (1998) Use of time-series analysis in infectious diseases surveillance. Bull World Health Organ 76(4):327–333Google Scholar
- Census and Statistics Department (2012) Hong Kong statistics—population and vital events. http://www.censtatd.gov.hk/hong_kong_statistics/statistics_by_subject/index.jsp?subjectID=1&charsetID=2&displayMode=T. Accessed 10 February 2010
- Cluett C, Gopalakrishna D, Kitchener F, Balke K, Osborne L (2011) Weather information integration in transportation management Center (TMC) operations, Final report FHWA-JPO-11-058, U.S. Department of Transport. http://ntl.bts.gov/lib/38000/38600/38677/TMC%20Final%20Report%20Website%206.13.11/tmc_integration_report_final.pdf. Accessed 10 February 2010
- Einspruch EL (2004) Next steps with SPSS. Sage, Thousand OaksGoogle Scholar
- Fire Services Department (2011) Hong Kong fire services review 2010. http://www.hkfsd.gov.hk/home/eng/review_10.html. Accessed 15 October 2011
- Harvey AC (1989) Forecasting, structural time series models and the Kalman filter. Cambridge University Press, CambridgeGoogle Scholar
- Harvey AC (1993) Time series models, 2nd edn. MIT Press, CambridgeGoogle Scholar
- Hentschel G (1987) A human biometeorology classification of climate for large and local scales. Proceedings WMO/HMO/UNEP Symposium on Climate and Human Health, Leningrad 1986, Vol I, WCPA—No.1, WMOGoogle Scholar
- Hong Kong Observatory (2007) Warm words in wintry weather. Press release, 19 November 2007. http://www.weather.gov.hk/wxinfo/news/2007/pre1119c.htm. Accessed 15 February 2011
- Hong Kong Observatory (2010) Extract of meteorological observations for Hong Kong. http://www.hko.gov.hk/wxinfo/pastwx/extract.htm. Accessed 10 February 2010
- Hong Kong Legislative Council (2005) Discussion paper for panel on security—provision of emergency ambulance service. Legislative Council Paper No. CB(2)1740/04-05(05)Google Scholar
- IBM SPSS (2011a) IBM SPSS forecasting 20. ftp://public.dhe.ibm.com/software/analytics/spss/documentation/statistics/20.0/en/client/Manuals/IBM_SPSS_Forecasting.pdf. Accessed 17 September 2012
- IBM SPSS (2011b) IBM SPSS statistics 20 Algorithms. ftp://public.dhe.ibm.com/software/analytics/spss/documentation/statistics/20.0/en/client/Manuals/IBM_SPSS_Statistics_Algorithms.pdf. Accessed 17 September 2012
- Karlaftis MG, Yannis G (2010) Weather effects on daily traffic accidents and fatalities: time series count data approach, Paper #10-0325, Transportation Research Board 89th Annual Meeting 2010, held in Washington D.C. on 10–14 January 2010Google Scholar
- Lam CC, Yeung KC, Lam H (2005) Use of model ensemble products for weather forecasting in Hong Kong, WMO Training Workshop on Ensemble Prediction System, held in Shanghai, China on 18–23 April 2005Google Scholar
- Leung WM, Leung YK, Mok HY (2008) Impact of weather on human health, Guangdong-Hong Kong-Macau Seminar on Meteorological Science and Technology, held in Zhongshan, China on 22–23 January 2008Google Scholar
- Liao PS, Tzeng YS, Chen TS (2002) Ambulance run volume prediction by back-propagation neural network. Proceedings 4th China-Japan-Korea Joint Symposium on Medical Informatics, CJKMI, Beijing, pp 203–206Google Scholar
- NOAA (2005) Finalizing plans for a global earth observation system of systems. NOAA magazine online—story 159, 14 Jan 2005. http://www.magazine.noaa.gov/stories/mag159.htm. Accessed 15 February 2011
- Saydam CA, Baker JR, Fitzpatrick KE (1986) An interactive forecasting program using Winters’ exponential smoothing model. J Bus Forecast 4:26–29Google Scholar
- Shukla J, Palmer TN, Hagedorn R, Hoskins B, Kinter J, Marotzke J, Miller M, Slingo J (2010) Toward a new generation of world climate research and computing facilities. Bull Am Meteorol Soc 1407–1412Google Scholar
- Williamson RA, Hertzfeld HR, Cordes J (2002) The socio-economic value of improved weather and climate information. Washington, DC: Space Policy Institute, George Washington University. http://www.gwu.edu/∼spi/assets/docs/Socio-EconomicBenefitsFinalREPORT2.pdf. Accessed 15 February 2012
- Wong HT, Lai PC (2009) Time series forecasts of monthly ambulance calls in Hong Kong, 10th Asian Urbanization Conference, held in Hong Kong, China on 16–19 August 2009Google Scholar