Skip to main content

Table 3 Recognition ability of all models for patients with CAD

From: Diagnosis of coronary artery disease in patients with type 2 diabetes mellitus based on computed tomography and pericoronary adipose tissue radiomics: a retrospective cross-sectional study

Model

Training set

Test set

 

AUC (95%CI)

SEN

SPE

ACC

PPV

NPV

AUC (95%CI)

SEN

SPE

ACC

PPV

NPV

Model 1

0.811(0.741–0.881)

0.784

0.772

0.780

0.667

0.860

0.691(0.564–0.817)

0.577

0.659

0.629

0.500

0.725

Model 2

0.960(0.934–0.987)

0.951

0.877

0.925

0.909

0.933

0.930(0.871–0.989)

0.885

0.773

0.814

0.697

0.919

Model 3

0.812(0.742–0.882)

0.784

0.772

0.780

0.667

0.860

0.693(0.567–0.819)

0.577

0.659

0.629

0.500

0.725

Model 4

0.961(0.934–0.988)

0.951

0.877

0.925

0.909

0.933

0.929(0.869–0.989)

0.885

0.773

0.814

0.697

0.919

  1. AUC area under curve, 95%CI 95% confidence interval, SEN sensitivity, SPE specificity, ACC accuracy, PPV positive predictive value, NPV negative predictive value
  2. Model 1 clinical factors model
  3. Model 2 clinical factors and imaging indexes model
  4. Model 3 clinical factors and Radscore model
  5. Model 4 combined model
Back to article page

Cardiovascular Diabetology

ISSN: 1475-2840