Table 6.

Robustness analysis.

SD			Forecasting model
			GLMa		ANNb		SVMc		ARIMAXd		LSTMe		RFf		ELMg
Patient arrivals + traditional variables
	SD of MAPEh (%)	2.5		1.0		1.0		1.7		1.7		1.2		1.0
	SD of RMSEi	15.638		4.385		5.158		5.843		7.409		5.371		4.099
Patient arrivals + traditional variables + internet search index
	SD of MAPE (%)	2.4		0.8		0.7		0.9		1.3		0.8		0.7
	SD of RMSE	15.212		3.577		4.008		5.681		5.797		3.985		3.370

^aGLM: generalized linear model.

^bANN: artificial neural network.

^cSVM: support vector machine.

^dARIMAX: ARIMA with explanatory variables.

^eLSTM: long short-term memory.

^fRF: random forest.

^gELM: extreme learning machine.

^hMAPE: average mean absolute percentage error.

ⁱRMSE: root mean square error.