Table 5.

Decision tree based cross-modal model performances on forecasting hospitalization rates 7 days ahead. Models were evaluated on 68 testing windows using the MAE and MAPE. Here the mean MAE and mean MAPE are displayed in percent with the corresponding 95% confidence interval. Models were trained cross-modal, i.e. Wastewater viral load was used as sole predictor for hospitalization rates

Model	MAE	MAPE in %
Random Forest - Cross-Modal	0.44; (0.28, 0.61)	6.66; (5.33, 8.00)
XGBoost - Cross-Modal	0.49; (0.31, 0.66)	7.23; (5.85, 8.62)