Table 5 AUC, sensitivity, specificity, and overall accuracy of SVM prediction models for the training and test sets for the two sketching methods.

From: Machine learning-based CT radiomics model to discriminate the primary and secondary intracranial hemorrhage

Sketch method

Training set (n = 166)

Test set (n = 72)

 

AUC [95%CI]

Sensitivity

Specificity

Accuracy

AUC [95%CI]

Sensitivity

Specificity

Accuracy

VOI sketching images

0.91 [0.84,0.98]

0.98

0.64

0.87

0.90 [0.80,1]

0.95

0.65

0.86

Three-layer sketching images

0.91 [0.83,0.99]

0.98

0.74

0.90

0.81 [0.66,0.98]

0.92

0.61

0.82

  1. AUC=area under the receiver operating characteristic curve.
Back to article page