Predicting hospital emergency department visits with deep learning approaches

Overcrowding in emergency department (ED) causes lengthy waiting times, reduces ade-quate emergency care and increases rate of mortality. Accurate prediction of daily ED visits and allocating resources in advance is one of the solutions to ED overcrowding problem. In this paper, a deep stacked architecture is being proposed and applied to the daily ED visits prediction problem with deep components such as Long Short Term Memory (LSTM), Gated Recurrent Units (GRU) and simple Recurrent Neural Network (RNN). The proposed architec-ture achieves very high mean accuracy level (94.28-94.59%) in daily ED visits predictions. We have also compared the performance of this architecture with non-stacked deep mod-els and traditional prediction models. The results indicate that deep stacked models out-perform (4-7%) the traditional prediction models and other non-stacked deep learning models (1-2%) in our prediction tasks. The application of deep neural network in ED visits prediction is novel as this is one of the first studies to apply a deep stacked architecture in this field. Importantly, our models have achieved better prediction accuracy (in one case comparable) than the state-of-the-art in the literature.(c) 2022 Published by Elsevier B.V. on behalf of Nalecz Institute of Biocybernetics and Bio-medical Engineering of the Polish Academy of Sciences.