Table 2 Multivariate Cox regression analysis in the training cohort.

From: Development of machine learning prognostic models for overall survival of prostate cancer patients with lymph node-positive

Variables

Multivariate analyses

p value

HR (95%CI)

Age

 ≤ 60

Reference

 

 61–69

1.236 (0.992–1.541)

0.059

 ≥ 70

1.707 (1.388–2.100)

 < 0.001

Race

 White

Reference

 

 Black

0.928 (0.717–1.203)

0.574

 Other

0.647 (0.437–0.959)

0.030

Marital status

 Married

Reference

 

 Unmarried

1.640 (1.365–1.969)

 < 0.001

Clinical T stage

 T1–T3a

Reference

 

 T3b

1.230 (0.946–1.599)

0.122

 T4

1.740 (1.285–2.358)

 < 0.001

PSA level (ng/ml)

1.001 (0.998–1.004)

0.501

GS

 ≤ 3 + 4

Reference

 

 4 + 3

1.358 (0.936–1.971)

0.108

 8

1.866 (1.339–2.600)

 < 0.001

 ≥ 9

3.087 (2.273–4.192)

 < 0.001

Number of positive lymph nodes

 1

Reference

 

 2

1.284 (0.944–1.746)

0.111

 ≥ 3

1.631 (1.247–2.133)

 < 0.001

No nodes were examined

RP

 Yes

Reference

 

 No

1.517 (1.037–2.219)

0.032

RT

 Yes

Reference

 

 No/unknown

1.538 (1.276–1.854)

 < 0.001

  1. HR hazard ratio, CI confidence interval.