Skip to main content

Table 4 Univariate and multivariate cox regression analysis of ESCC-PS and clinicopathological characteristics for overall survival in validation cohort

From: From pixels to patient care: deep learning-enabled pathomics signature offers precise outcome predictions for immunotherapy in esophageal squamous cell cancer

Patient characteristics

Univariate Cox analysis

Multivariate Cox analysis

HR (95%CI)

P value

HR (95% CI)

P value

Age

    

  ≤ 60

1

0.495

  

  > 60

1.309 (0.604–2.838)

   

Gender

    

 Male

1

0.906

  

 Female

0.947 (0.379–2.365)

   

Smoking history

    

 No

1

0.660

  

 Yes

1.192 (0.546–2.602)

   

Drinking history

    

 No

1

0.214

  

 Yes

1.641 (0.751–3.583)

   

T stage

    

 T1-T2

1

0.644

  

 T3-T4

1.328 (0.398–4.434)

   

N stage

    

 N0-N1

1

0.482

  

 N2-N3

0.755 (0.345–1.653)

   

Stage

    

 III

1

0.673

  

 IV

1.205 (0.507–2.862)

   

Lung metastasis

    

 No

1

0.172

  

 Yes

1.834 (0.768–4.382)

   

Bone metastasis

    

 No

1

0.494

  

 Yes

1.666 (0.386–7.198)

   

Liver metastasis

    

 No

1

0.460

  

 Yes

1.497 (0.513–4.362)

   

Radiotherapy

    

 No

1

0.025*

  

 Yes

0.386 (0.168–0.888)

   

Chemotherapy

    

 No

1

0.981

  

 Yes

1.011 (0.423–2.16)

   

PD-L1

    

  < 57.5%

1

0.037*

1

0.041*

  ≥ 57.5%

0.214 (0. 050–0.909)

 

0.213 (0.048–0.942)

 

ESCC-PS

    

 ESCC-PS 1

1

 < 0.001*

1

 < 0.001*

 ESCC-PS 2

0.167 (0.056–0.496)

 

0.168 (0.055–0.516)

 

 ESCC-PS 3

0.040 (0.009–0.171)

 

0.034 (0.007–0.160)

 
  1. *Statistcal significance