Machine Learning-Based Forecast of Hemorrhagic Stroke Healthcare Service Demand considering Air Pollution
Table 9
Statistics on the performance of warm season models regarding lag effects.
Lag
M-AUC
M-Sens
M-Spec
SD-AUC
SD-Sens
SD-Spec
MaxLag-14
0.7314
0.3524
0.8040
0.0568
0.1631
0.1360
MaxLag-9
0.6961
0.2863
0.8574
0.0369
0.1329
0.0184
MaxLag-6
0.6948
0.3205
0.8584
0.0367
0.1383
0.0215
MaxLag-11
0.6892
0.2902
0.8266
0.0309
0.1096
0.0763
MaxLag-13
0.6876
0.2671
0.8010
0.0455
0.1619
0.1286
MaxLag-10
0.6855
0.2644
0.8534
0.0356
0.1318
0.0170
MaxLag-8
0.6803
0.2399
0.8422
0.0440
0.1273
0.0342
MaxLag-4
0.6790
0.2953
0.8372
0.0310
0.1407
0.0359
MaxLag-3
0.6785
0.2168
0.8231
0.0287
0.1443
0.0548
MaxLag-12
0.6754
0.2643
0.8246
0.0528
0.1056
0.0769
MaxLag-5
0.6742
0.2680
0.8477
0.0530
0.1080
0.0127
MaxLag-7
0.6683
0.3191
0.8289
0.0541
0.1564
0.0767
MaxLag-1
0.6409
0.3038
0.8486
0.0350
0.0882
0.0121
MaxLag-2
0.6396
0.2008
0.8417
0.0371
0.0746
0.0066
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.