Skip to main content

Table 3 Metrics for assessing the quality of the estimated model in test and validation samples

From: Early biomarkers of extracapsular extension of prostate cancer using MRI-derived semantic features

Measure

Value (95% CI)

Test Sample

 Area Under the Curve (AUC)*

90.8 (85.3, 94.5)

 Sensitivity

86.4 (80.4, 90.7)

 Specificity

78.4 (71.6, 83.9)

Hosmer and Lemeshow test**

4.964 (0.761)

Validation Sample

 Area Under the Curve (AUC)*

85.0 (74.0, 95.8)

 Sensitivity

84.2 (72.9, 91.4)

 Specificity

82.5 (70.9, 90.1)

  1. Data are given in percentages, with 95% confidence intervals in parenthesis
  2. * Confidence interval was obtained from 2000 stratified bootstrap replicates
  3. ** Test statistic; and p-value in parenthesis