A modular approach to forecasting COVID-19 hospital bed occupancy

Monitoring the number of COVID-19 patients in hospital beds was a critical component of Australia’s real-time surveillance strategy for the disease. From 2021–2023, we produced short-term forecasts of bed occupancy to support public health decision making. In this work, we present a model for forecasting the number of ward and intensive care unit (ICU) beds occupied by COVID-19 cases. The model simulates the stochastic progression of COVID-19 patients through the hospital system and is fit to reported occupancy counts using an approximate Bayesian method. We do not directly model infection dynamics — instead taking independently produced forecasts of case incidence as an input — enabling the independent development of our model from that of the underlying case forecast(s). We evaluate the performance of 21-day forecasts of ward and ICU occupancy across Australia’s eight states and territories between March and September 2022, when major waves of the Omicron variant of SARS-CoV-2 were occurring throughout the country. Forecasts were on average biased downwards immediately prior to epidemic peaks and biased upwards post-peak. Forecast performance was best in jurisdictions with the largest population sizes. Our forecasts of COVID-19 hospital burden were reported weekly to national decision-making committees to support Australia’s public health response.