Skip to main content
Fig. 6 | BMC Cancer

Fig. 6

From: Prognosis of lasso-like penalized Cox models with tumor profiling improves prediction over clinical data alone and benefits from bi-dimensional pre-screening

Fig. 6

C-index obtained with the lasso without pre-screening (gray), with the lasso after the bi-dimensional pre-screening (blue), and with independent sure independence screening (ISIS, red). We computed the C-indices by 10 repetitions of a K-fold-validation (K=5). As an indication, the p-values obtained after a Wilcoxon test between ISIS and the bi-dimensional pre-screening (stars above the graphics) are provided. The 16 p-values are corrected with Benjamini-Hochberg method. Blue stars: the median C-index is lower for the bi-dimensional pre-screening. Blue numbers: number of genes selected by the lasso after bi-dimensional pre-screening. Red numbers: number of genes retained by ISIS. ***: \(p \le 0.001\), **: \(p \le 0.01\), *: \(p \le 0.05\), +: \(p \le 0.1\), n.s. : \(p > 0.1\)

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us