Skip to main content

Table 6 The performance of CACS, Radscore and radiomics nomogram

From: Non-contrast CT-based radiomics nomogram of pericoronary adipose tissue for predicting haemodynamically significant coronary stenosis in patients with type 2 diabetes

Models

Cohorts

AUC (95% CI)

Accuracy

Sensitivity

Specificity

PPV

NPV

CACS

Training cohort

0.75(0.69–0.80)

69.4%

73.5%

67.5%

52.1%

84.1%

Validation cohort

0.73(0.64–0.82)

71.4%

62.5%

74.6%

46.3%

85.0%

Radscore

Training cohort

0.80(0.75–0.85)

75.8%

71.8%

77.8%

60.9%

85.1%

Validation cohort

0.82(0.75–0.90)

75.3%

75.0%

75.4%

51.7%

89.6%

Radiomics nomogram

Training cohort

0.81(0.76–0.86)

75.0%

76.1%

74.5%

58.9%

86.6%

Validation cohort

0.83(0.76–0.90)

76.0%

75.0%

76.3%

52.6%

89.7%

  1. CACS Coronary artery calcium score, AUC Area under receiver operating characteristic curve, PPV Positive predictive value, NPV Negative predictive value