Skip to main content

Table 2 Univariate and multivariable regression analyses of the Radscore with primary clinical features for the histological subtype prediction of NSCLC in the training cohort

From: Elaboration of a multimodal MRI-based radiomics signature for the preoperative prediction of the histological subtype in patients with non-small-cell lung cancer

Indicators

Univariate analysis

Multivariable analysis

ORa

95% CI

p value

OR

95% CI

p value

Lower

Upper

Lower

Upper

Age

2.481

1.368

4.499

< 0.05

3.994

1.421

11.228

< 0.05

Sex

0.068

0.015

0.313

≪ 0.05

0.413

0.015

10.889

0.59

Smoking

0.148

0.053

0.409

≪ 0.05

0.104

0.012

0.947

< 0.05

Side

0.353

0.127

0.981

0.051

–

–

–

–

Location

2.191

0.954

5.028

0.06

–

–

–

–

LDa

1.991

1.061

3.734

< 0.05

0.048

0.005

0.511

< 0.05

LPDa

3.246

1.651

6.379

≪ 0.05

9.807

1.420

67.719

< 0.05

CEAa

0.784

0.635

0.968

< 0.05

0.661

0.488

1.129

0.062

Radscore

11.128

4.100

30.198

≪ 0.01

74.937

9.339

601.32

≪ 0.01

  1. The underlined values indicate statistical significance with p value < 0.05 after the univariate analysis
  2. The italics underlined values indicate statistical significance with p value < 0.05 after the multivariable analysis
  3. aLD, LPD, CEA and OR indicate the longest diameter, the longest perpendicular diameter, carcinoembryonic antigen, and odds ratio, respectively
Back to article page

BioMedical Engineering OnLine

ISSN: 1475-925X

Contact us