Integrating nowcasts into an ensemble of data-driven forecasting models for SARI hospitalizations in Germany

Predictive epidemic modeling can enhance situational awareness during emerging and seasonal outbreaks and has received increasing interest in recent years. A common distinction is between nowcasting, which corrects recent incidence data for reporting delays, and forecasting, which predicts future trends. This paper presents an integrated system for nowcasting and short-term forecasting of hospitalizations from severe acute respiratory infections (SARI) in Germany (November 2023–September 2024). Motivated by facilitating multi-model forecasting collaborations, we propose a modular approach in which a statistical nowcasting model is run centrally, and its output is provided as input to various data-driven forecasting methods. We apply this approach to a seasonal time series model, a gradient boosting approach, and a neural network. These are moreover combined into an ensemble approach, which achieves the best average performance. The resulting forecasts are overall well-calibrated up to four weeks ahead, but struggled to capture the unusual double peak that occurred during the test season. The presented retrospective results are key developments for ongoing and future collaborative real-time forecasting of respiratory diseases in Germany.