Skip to main content

Table 3 Comparison of the performance of the three methods for healthy and unhealthy discrimination

From: paraFaceTest: an ensemble of regression tree-based facial features extraction for efficient facial paralysis classification

 

LAC-based

LAC-based

ERT-based GRFE

 

KPFE

GRFE

(our approach)

Sensitivity

89.12%

95.01%

98.12%

Specificity

90.01%

88.12%

94.06%

AUC

93.40%

95.56%

98.34%