English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There were 25.6 million attendances at Emergency Departments (EDs) in Englandin 2019 corresponding to an increase of 12 million attendances over the pastten years. The steadily rising demand at EDs creates a constant challenge toprovide adequate quality of care while maintaining standards and productivity.Managing hospital demand effectively requires an adequate knowledge of thefuture rate of admission. Using 8 years of electronic admissions data from twomajor acute care hospitals in London, we develop a novel ensemble methodologythat combines the outcomes of the best performing time series and machinelearning approaches in order to make highly accurate forecasts of demand, 1, 3and 7 days in the future. Both hospitals face an average daily demand of 208and 106 attendances respectively and experience considerable volatility aroundthis mean. However, our approach is able to predict attendances at theseemergency departments one day in advance up to a mean absolute error of +/- 14and +/- 10 patients corresponding to a mean absolute percentage error of 6.8%and 8.6% respectively. Our analysis compares machine learning algorithms tomore traditional linear models. We find that linear models often outperformmachine learning methods and that the quality of our predictions for any of theforecasting horizons of 1, 3 or 7 days are comparable as measured in MAE. Inaddition to comparing and combining state-of-the-art forecasting methods topredict hospital demand, we consider two different hyperparameter tuningmethods, enabling a faster deployment of our models without compromisingperformance. We believe our framework can readily be used to forecast a widerange of policy relevant indicators.

A unified machine learning approach to time series forecasting applied to demand at emergency departments