Journal article
Predicting emergency department admissions
Emergency Medicine Journal, Vol.29(5), pp.358-365
05/2012
PMID: 21705374
Metrics
12 Record Views
UN Sustainable Development Goals (SDGs)
This output has contributed to the advancement of the following goals:
Source: InCites
Abstract
ObjectiveTo develop and validate models to predict emergency department (ED) presentations and hospital admissions for time and day of the year.MethodsInitial model development and validation was based on 5 years of historical data from two dissimilar hospitals, followed by subsequent validation on 27 hospitals representing 95% of the ED presentations across the state. Forecast accuracy was assessed using the mean average percentage error (MAPE) between forecasts and observed data. The study also determined a daily sample size threshold for forecasting subgroups within the data.ResultsPresentations to the ED and subsequent admissions to hospital beds are not random and can be predicted. Forecast accuracy worsened as the forecast time intervals became smaller: when forecasting monthly admissions, the best MAPE was approximately 2%, for daily admissions, 11%; for 4-hourly admissions, 38%; and for hourly admissions, 50%. Presentations were more easily forecast than admissions (daily MAPE ∼7%). When validating accuracy at additional hospitals, forecasts for urban facilities were generally more accurate than regional forecasts (accuracy is related to sample size). Subgroups within the data with more than 10 admissions or presentations per day had forecast errors statistically similar to the entire dataset. The study also included a software implementation of the models, resulting in a data dashboard for bed managers.ConclusionsValid ED prediction tools can be generated from access to de-identified historic data, which may be used to assist elective surgery scheduling and bed management. The paper provides forecasting performance levels to guide similar studies.
Details
- Title
- Predicting emergency department admissions
- Creators
- Justin Boyle - CSIRO Information and Communication Technologies Centre, Level , UQ Health Sciences Building, Royal Brisbane and Women's Hospital, Herston, Queensland, AustraliaMelanie Jessup - Gold Coast Hospital Emergency Department, Queensland Health, Gold Coast Hospital, Southport, Queensland, AustraliaJulia Crilly - Gold Coast Hospital Emergency Department, Queensland Health, Gold Coast Hospital, Southport, Queensland, AustraliaDavid Green - Gold Coast Hospital Emergency Department, Queensland Health, Gold Coast Hospital, Southport, Queensland, AustraliaJames Lind - Gold Coast Hospital Emergency Department, Queensland Health, Gold Coast Hospital, Southport, Queensland, AustraliaMarianne Wallis - Gold Coast Hospital Emergency Department, Queensland Health, Gold Coast Hospital, Southport, Queensland, AustraliaPeter Miller - Toowoomba Hospital Emergency Department, Queensland Health, Toowoomba, Queensland, AustraliaGerard Fitzgerald - Faculty of Health, Queensland University of Technology, Brisbane, Queensland, Australia
- Publication Details
- Emergency Medicine Journal, Vol.29(5), pp.358-365
- Publisher
- B M J Group
- Identifiers
- 991012927100002368
- Academic Unit
- Nursing; Faculty of Health
- Language
- English
- Resource Type
- Journal article