Table 3.

RMSE and MAE values for univariate models in five different forecasting horizons.

Models	Forecasting Horizon (in Days)
	1		7		14		21		30
	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE	RMSE	MAE
SARIMA	33.57	26.58	32.73	26.03	28.81	22.28	47.59	39.97	96.20	89.92
FP	43.82	34.74	45.94	41.62	54.50	51.15	60.67	57.27	53.75	49.99
HW	28.42	21.29	28.19	21.32	30.20	23.07	38.47	32.34	89.74	84.09
LSTM	29.92	23.64	29.94	23.65	30.70	23.92	30.43	23.97	31.32	24.52

Note: Green highlights the model with the best results. Interpretation: The LTSM model with a 30-day horizon had the lowest RMSE of 31.32 and lowest MAE of 24.52 of all four models, suggesting that the prediction of daily patients on a 30-day horizon was best accomplished with the LTSM model. MAE, mean absolute error; RMSE, root mean square error (units = patients).