Skip to main content

Table 6 The results of stepwise logistic regression analysis

From: Histogram analysis of multiple diffusion models for predicting advanced non-small cell lung cancer response to chemoimmunotherapy

Combined model

β Coefficients

Standard error

Wald

OR (95%CI)

P

Model fita

Whole tumor

     

0.789

 Dslowmean

-0.567

0.238

5.678

0.567 (0.356–0.904)

0.017

 

 fmean

1.231

0.402

9.379

3.425 (1.558–7.530)

0.002

 

 f90th

-0.519

0.194

7.137

0.595 (0.407–0.871)

0.008

 

Single slice

     

0.612

 Dslowmean

-2.081

0.670

9.652

0.125 (0.034–0.464)

0.002

 

 Dslow75th

1.130

0.502

5.063

3.095 (1.157–8.280)

0.024

 

 f90th

0.087

0.027

10.564

1.091 (1.035–1.150)

0.001

 
  1. aThe Hosmer–Lemeshow test was performed to explain the goodness-of-fit of the multivariate logistic model. A P > 0.05 was considered well fitted. OR: odds ratio; CI: confidence interval
Back to article page

Cancer Imaging

ISSN: 1470-7330

Contact us