Skip to main content

Table 3 AUC value of the best two models established by Xgboost with test dataset analysis

From: Establishment of early diagnosis models for cervical precancerous lesions using large-scale cervical cancer screening datasets

Data sets

Accuracy

ASCUShigher

ASC-Hhigher

LSILhigher

HSILhigher

P value (ACD vs. POS)

ACD

xgboost-AUC

0.8200

0.9385

0.9413

0.9293

0.00050

Sensitivity

0.5020

0.6476

0.6484

0.6000

 

Specificity

0.9547

0.9561

0.9577

0.9568

 

Accuracy

0.9274

0.9484

0.951

0.9556

 

POS

xgboost-AUC

0.7176

0.7285

0.7210

0.7336

 

Sensitivity

0.5747

0.6596

0.5750

0.6429

 

Specificity

0.7466

0.6907

0.7199

0.7228

 

Accuracy

0.6909

0.6853

0.6983

0.7207