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.

Impact of the COVID-19 pandemic on a tertiary care public hospital in Singapore: resources and economic costs.

BACKGROUND: The COVID-19 pandemic has prompted hospitals to respond with stringent measures. Accurate estimates of costs and resources used in outbreaks can guide evaluations of responses. We report on the financial expenditure associated with COVID-19, the bed-days used for COVID-19 patients and hospital services displaced due to COVID-19 in a Singapore tertiary hospital. METHODS: We conducted a retrospective cost analysis from January to December 2020 in the largest public hospital in Singapore. Costs were estimated from the hospital perspective. We examined financial expenditures made in direct response to COVID-19; hospital admissions data related to COVID-19 inpatients; and the number of outpatient and emergency department visits, non-emergency surgeries, inpatient days in 2020, compared with preceding years of 2018 and 2019. Bayesian time-series was used to estimate the magnitude of displaced services. RESULTS: USD $41.96 million was incurred in the hospital for COVID-19-related expenses. Facilities set-up and capital assets accounted for 51.6% of the expenditure; patient-care supplies comprised 35.1%. Of the 19,611 inpatients tested for COVID-19 in 2020, 727 (3.7%) had COVID-19. The total inpatient- and intensive care unit (ICU)-days for COVID-19 patients in 2020 were 8009 and 8 days, respectively. A decline in all hospital services was observed from February following a raised disease outbreak alert level; most services quickly resumed when the lockdown was lifted in June. CONCLUSION: COVID-19 led to an increase in healthcare expenses and a displacement in hospital services. Our findings are useful for informing economic evaluations of COVID-19 response and provide some information about the expected costs of future outbreaks.