Abstract
BACKGROUND: Forecasting models for intensive care occupancy of coronavirus disease 2019 (COVID-19) patients are important in the current pandemic for strategic planning of patient allocation and avoidance of regional overcrowding. They are often trained entirely on retrospective infection and occupancy data, which can cause forecast uncertainty to grow exponentially with the forecast horizon. METHODOLOGY: We propose an alternative modeling approach in which the model is created largely independent of the occupancy data being simulated. The distribution of bed occupancies for patient cohorts is calculated directly from occupancy data from "sentinel clinics". By coupling with infection scenarios, the prediction error is constrained by the error of the infection dynamics scenarios. The model allows systematic simulation of arbitrary infection scenarios, calculation of bed occupancy corridors, and sensitivity analyses with respect to protective measures. RESULTS: The model was based on hospital data and by adjusting only two parameters of data in the Aachen city region and Germany as a whole. Using the example of the simulation of the respective bed occupancy rates for Germany as a whole, the loading model for the calculation of occupancy corridors is demonstrated. The occupancy corridors form barriers for bed occupancy in the event that infection rates do not exceed specific thresholds. In addition, lockdown scenarios are simulated based on retrospective events. DISCUSSION: Our model demonstrates that a significant reduction in forecast uncertainty in occupancy forecasts is possible by selectively combining data from different sources. It allows arbitrary combination with infection dynamics models and scenarios, and thus can be used both for load forecasting and for sensitivity analyses for expected novel spreading and lockdown scenarios.