Skip to main content

Table 2 Diagnostic performance of the clinical factor model, radiomics signature, and radiomics nomogram for detection of intraplaque hemorrhage

From: Radiomics assessment of carotid intraplaque hemorrhage: detecting the vulnerable patients

Set

Model

AUC (95%CI)

Sensitivity (%)

Specificity (%)

Accuracy (%)

Training set

Clinical model

0.631 (0.524–0.738)

61.8 (28/46)

49.0 (29/60)

56.7 (60/106)

Radiomics signature

0.717 (0.620–0.814)

68.9 (32/46)

60.0 (36/60)

65.1 (69/106)

Radiomics nomogram

0.743 (0.650–0.835)

69.1 (32/46)

56.9 (34/60)

63.2 (67/106)

External test set

Clinical model

0.761 (0.596–0.927)

80.0 (14/18)

77.8 (16/20)

78.9 (30/38)

Radiomics signature

0.725 (0.562–0.888)

62.5 (11/18)

69.2 (14/20)

63.2 (24/38)

Radiomics nomogram

0.811 (0.661–0.961)

88.9 (16/18)

80.0 (16/20)

84.2 (32/38)

  1. AUC Area under the curve, CI Confidence interval