Table 2 Discriminant analysis for lung cancer (diagnostic model).

From: A miRNA-based diagnostic model predicts resectable lung cancer in humans with high accuracy

Model

Number of miRNAs

Sensitivity (%)

Specificity (%)

Accuracy (%)

PPV (%)

NPV(%)

AUC

model 1

1

93.3

88.5

90.9

89.0

92.9

0.935a

model 2

2

99.0

99.0

99.0

99.0

99.0

0.993b

model 3

3

99.0

99.0

99.0

99.0

99.0

0.995

  1. model1: (0.491213) × miR-17-3p − 2.49845.
  2. model2: (−3.56049) × miR-1268b + (1.99039) × miR-6075 + 16.7999.
  3. model3: (−3.87517) × miR-1268b + (2.28137) × miR-6075 + (−0.81776) × miR-6858-5p + 23.5615.
  4. aDeLong’s test for two correlated ROC curves to assess whether the model 2 gives a significantly greater AUC compared with model 1, P < 0.0001
  5. bDeLong’s test for two correlated ROC curves to assess whether the model 3 gives a significantly greater AUC compared with model 2, P = 0.342
Back to article page