Table 2 Unimodal performance for the prediction of OS, 1-year death, PFS, and 6-month progression

From: Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer

Target (number of patients)

OS (n = 79)

1-year death (n = 77)

PFS (n = 80)

6-month progression (n = 75)

Metric

C-index

AUC

C-index

AUC

Clinical

Tree ensembles

0.67 ± 0.01*

0.59 ± 0.05

0.56 ± 0.02

0.58 ± 0.04

Linear

0.60 ± 0.02*

0.73 ± 0.02*

0.53 ± 0.03

0.61 ± 0.03*

Radiomics

Tree ensembles

0.61 ± 0.02*

0.62 ± 0.04

0.57 ± 0.01

0.56 ± 0.05

Linear

0.61 ± 0.02*

0.47 ± 0.03

0.55 ± 0.02

0.48 ± 0.04

Pathomics

Tree ensembles

0.59 ± 0.02

0.54 ± 0.05

0.56 ± 0.02

0.58 ± 0.06*

Linear

0.58 ± 0.02

0.56 ± 0.03

0.51 ± 0.02

0.61 ± 0.03*

RNA

Tree ensembles

0.69 ± 0.02*

0.75 ± 0.04*

0.57 ± 0.02

0.60 ± 0.04*

Linear

0.58 ± 0.02

0.65 ± 0.03

0.59 ± 0.02*

0.61 ± 0.03

  1. *one-sided permutation p-value ≤ 0.05 (exact p-values are reported in Supplementary Table s1).
  2. Unimodal performance of each data modality for the prediction of OS, 1-year death, PFS, and 6-month progression with linear and tree ensemble algorithms (mean ± std over the 100 cross-validation schemes). The best performances for each column are highlighted in bold. Source data are provided as a Source Data file.
Back to article page