Machine Learning-Based Forecast of Hemorrhagic Stroke Healthcare Service Demand considering Air Pollution

Table 10

Performance of warm season models with AUC >0.75

Lag	Models	M-AUC	M-Sens	M-Spec	SD-AUC	SD-Sens	SD-Spec
MaxLag-14	LR	0.7971	0.6252	0.8929	0.1158	0.2802	0.0429
MaxLag-14	SVMLinear	0.7741	0.2266	0.5293	0.0829	0.2942	0.4593
MaxLag-13	LR	0.7588	0.5483	0.8963	0.1289	0.2789	0.0541
MaxLag-14	RF	0.7567	0.3500	0.8489	0.1116	0.4191	0.0307
MaxLag-9	LR	0.7549	0.4617	0.8707	0.0668	0.2632	0.0347

M-AUC, M-Sens, and M-Spec denote the average area under the curve (AUC), sensitivity, and specificity, respectively; SD-AUC, SD-Sens, and SD-Spec denote the standard deviation of the AUC, sensitivity, and specificity, respectively. MaxLag-N refers to the risk factor sets that considered the air quality variables of the recent N days. LR, logistic regression; RF, random forest; SVMLinear, support-vector machines with linear kernel; KNN, k-nearest neighbor algorithm; XGBTree, extreme gradient boosting decision tree; XGBLinear, extreme gradient boosting linear model.