| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 11.08 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Emergency Department (ED) overcrowding has been negatively affecting both public and private
hospitals all around the globe. A more efficient planning of ED resources can help to mitigate this
phenomenon. Thus, a Machine Learning multi-step-ahead predictive tool was developed to forecast
weekly ED arrivals. Hence, ED managers can make decisions based on these predictions, allowing
for a smooth ED functioning where the resources provided match current ED demand. First, the
predictive tool was used to forecast ED demand in a bigger unit of a private Portuguese healthcare
provider, CUF, and then, the same tool was used in a smaller unit.
Descrição
Palavras-chave
Healthcare Emergency department Machine learning Time series Multi-step-ahead forecasting
