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

Table 6

The values of the t-test between different machine learning methods regarding AUC.

	LR	XGBTree	XGBLinear	KNN	SVMLinear	RF
LR	1	<0.0001	<0.0001	0.0001	<0.0001	<0.0001
XGBTree	<0.0001	1	0.9878	0.5949	0.1579	0.1265
XGBLinear	<0.0001	0.9878	1	0.5846	0.2964	0.0326
KNN	0.0001	0.5949	0.5846	1	0.6933	0.4353
SVMLinear	<0.0001	0.1579	0.2964	0.6933	1	0.5933
RF	<0.0001	0.1265	0.0326	0.4353	0.5933	1

0.001, 0.01, and 0.05. 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.