Weather factors in the short-term forecasting of daily ambulance calls

Abstract

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.

Big data as a new approach in emergency medicine research

“…Finally, high-risk groups-such as women, low-income groups, and the elderly-were identified to be more sensitive to extreme weather conditions. In their second published paper, Wong and Lai used the same big data to develop a short-term daily ambulancedemand forecast system [6] . In addition to the daily ambulance-demand data series, the HKO seven-day weather forecast report was used to predict the next seven days' daily ambulance demand through the Autoregressive Integrated Moving Average model, available at IBM SPSS Forecasting [8,9] .…”

“…In this connection, a showcase is particularly useful for encouraging clinical practitioners to conduct research using big data. Wong and Lai used big data containing over 6 million emergency department records to conduct research related to ambulance demand and weather [5][6][7] . They obtained the data set from the Hong Kong Hospital Authority, which contains patients' age, gender, triage level, and other information.…”

The Need for a Definition of Big Data for Nursing Science: A Case Study of Disaster Preparedness

“…Although disaster preparedness is considered to be the most critical phase in the disaster management continuum, none of the publications related to disaster preparedness in nursing can be identified in the PubMed Nursing Journals as having used Big Data. Disaster preparedness research using Big Data has, however, been found in the publications of health geographers [5,29], an indication that health geographers are among the first to use Big Data in such research.…”

“…The model validation results showed that it is feasible to use a weather forecast report to forecast the future daily demand for ambulances [30]. The accuracy of the forecast was further improved by introducing the seven-day average temperature forecast into the emergency ambulance demand forecast model [29]. …”

Modelling Vulnerability to Severe Weather

“…However including meteorological data apparently failed to improve model performance (Wargon et al 2009). Findings of more recent studies however do find that weather factors such 5 as temperature and humidity play a role in the demand for ambulance services and demonstrate that including weather forecast data can in fact improve forecasts of daily ambulance demand (Wong and Lai (2014)). …”