Skip to main content

Table 2 C-index of the Cox proportional hazards models based on different features

From: Toward the precision breast cancer survival prediction utilizing combined whole genome-wide expression and somatic mutation analysis

Feature type

Features

C-index

P-value

Gene expression

330 significant univariate genes

0.584

0.0011

118 significant univariate genes with hazard ratio > 1.221

0.636

<  0.0001

88 significant univariate genes selected by GA

0.656

<  0.0001

Somatic mutation

25 functional annotations

0.603

0.0012

15 gene ontology terms

0.567

0.0013

14 pathways

0.548

0.0037

54 functional gene sets combining functional annotations, GO terms and pathways

0.591

0.0016

Gene expression & somatic mutation

All 142 features (88 significant univariate genes and 54 functional gene sets)

0.658

<  0.0001