Forecasting Emergency Department Attendances
Author Information
Author(s): Sun Yan, Heng Bee Hoon, Seow Yian Tay, Seow Eillyne
Primary Institution: National Healthcare Group, Singapore
Hypothesis
Can daily attendances at an emergency department be accurately predicted using time series analysis?
Conclusion
Time series analysis is an effective tool for predicting emergency department workload, aiding in staff and resource planning.
Supporting Evidence
- P1 attendances were predicted by ambient air quality of PSI > 50.
- P2 and total attendances showed weekly periodicities and were significantly predicted by public holidays.
- P3 attendances were significantly correlated with day of the week, month of the year, and ambient air quality.
Takeaway
This study shows that we can guess how many people will visit the emergency room each day, which helps hospitals plan better.
Methodology
The study used time series analysis with ARIMA models to forecast daily patient attendances based on historical data and various predictors.
Potential Biases
Potential bias due to reliance on historical data and specific local conditions that may not generalize.
Limitations
The study may not account for all factors affecting ED attendances, such as the availability of primary care facilities.
Participant Demographics
Patients attending the emergency department, categorized by acuity levels (P1, P2, P3).
Statistical Information
P-Value
p<0.05
Confidence Interval
95% confidence interval for mean daily attendances
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website