Table 2 Cut-point sensitivity, specificity, area under curve (AUC).

From: Development of PancRISK, a urine biomarker-based risk score for stratified screening of pancreatic cancer patients

Method

Logistic regression

Neural network

Neuro-fuzzy technology

SVM

Random forest

Specificity

0.9

0.9

0.9

0.89

0.82

Sensitivity (95% CI)

0.81 (0.7–0.89)

0.81 (0.63–0.95)

0.87 (0.72–0.95)

0.82

0.86

p value

 

1

0.077

1

0.18

AUC (95% CI)

0.94 (0.91–0.97)

0.93 (0.9–0.97)

0.94 (0.91–0.97)