Evaluation of a pragmatic approach to predicting COVID-19-positive hospital bed occupancy.

Abstract

Study objectives: This study evaluates the feasibility and accuracy of a pragmatic approach to predicting hospital bed occupancy for COVID-19-positive patients, using only simple methods accessible to typical health system teams.

Methods: We used an observational forecasting design for the study period 1st June 2021 to -21st January 2022. Evaluation data covered individuals registered with a general practitioner in North West London, through the Whole Systems Integrated Care deidentified dataset. We extracted data on COVID-19-positive tests, vaccination records and admissions to hospitals with confirmed COVID-19 within the study period. We used linear regression models to predict bed occupancy, using lagged, smoothed numbers of COVID-19 cases among unvaccinated individuals in the community as the predictor. We used mean absolute percentage error (MAPE) to assess model accuracy.

Results: Model accuracy varied throughout the study period, with a MAPE of 10.8% from 12 July 2021 to 18 October 2021, rising to 20.0% over the subsequent period to 15 December 2021. After that, model accuracy deteriorated considerably, with MAPE 110.4% from December 2021 to 21 January 2022. Model outputs were used by senior healthcare system leaders to aid the planning, organisation and provision of healthcare services to meet demand for hospital beds.

Conclusions: The model produced useful predictions of COVID-19-positive bed occupancy prior to the emergence of the Omicron variant, but accuracy deteriorated after this. In practice, the model offers a pragmatic approach to predicting bed occupancy within a pandemic wave. However, this approach requires continual monitoring of errors to ensure that the periods of poor performance are identified quickly.