Skip to main content

Table 2 Risk predictors for IAC in the univariate and multivariate logistic regression analysis

From: An artificial intelligence algorithm for the detection of pulmonary ground-glass nodules on spectral detector CT: performance on virtual monochromatic images

Variable

 

Univariate analysis

  

Multivariate analysis

 
 

OR (95% CI)

 

P value

OR (95% CI)

 

P value

Total volume (mm3)

1.005(1.002—1.008)

 

0.001

—

 

—

Total mass(mg)

1.017(1.009—1.026)

 

0.000

1.02(1.002—1.038)

 

0.029

Maximum CT value (HU)

1.004(1.002—1.006)

 

0.000

—

 

—

Mean CT value (HU)

1.008(1.003—1.012)

 

0.002

—

 

—

Maximum section area (mm2)

1.052(1.026—1.079)

 

0.000

1.014(0.957—1.074)

 

0.635

Superficial area (mm2)

1.01(1.005—1.016)

 

0.000

—

 

—

3D long diameter (mm)

1.53(1.261—1.857)

 

0.000

1.004(0.617—1.633)

 

0.988

Kurtosis

1.005(0.965—1.046)

 

0.826

—

 

—

Skewness

0.897(0.661—1.216)

 

0.483

—

 

—

Entropy

5.058(2.375—10.772)

 

0.000

0.527(0.097—2.845)

 

0.456

  1. IAC Invasive adenocarcinoma, CT Computed tomography, 3D Three-dimensional, OR Odds ratio, CI Confidence interval