Skip to main content

Table 5 Hazard ratios and C-indexes of longitudinal and ensemble models trained for endpoint PFS6 to predict PFS and OS in the independent test set

From: Integration of longitudinal deep-radiomics and clinical data improves the prediction of durable benefits to anti-PD-1/PD-L1 immunotherapy in advanced NSCLC patients

  

PFS

OS

Model

Features

HR

[95% CI]

p-value

C-index

HR

[95% CI]

p-value

C-index

RF-longitudinal

Clinical data

1.63

[-1.00,4.25]

0.224

0.615

3.49

[0.28,6.69]

0.033

0.656

RF-longitudinal

DF-imm

3.30

[1.02,5.59]

0.005

0.687

4.31

[1.43,7.12]

0.003

0.709

Ensemble

RF-longitudinal

DF-imm

Clinical data

4.68

[1.52,7.84]

0.004

0.723

6.00

[2.27,9.73]

0.002

0.768

  1. The highest value for each metric is highlighted in bold