Skip to main content
Fig. 4 | BMC Bioinformatics

Fig. 4

From: Machine-learning algorithms based on personalized pathways for a novel predictive model for the diagnosis of hepatocellular carcinoma

Fig. 4

Prognostic values of characteristic genes. A HR statistics of 33 prognostic-related genes. B The Kaplan–Meier survival curve of OS for DYNC1H1. C The Kaplan–Meier survival curve of RFS for DYNC1H1. D Lambda distribution of lasso regression. The left line indicated the optimal values (λ = 0.01988275). E lasso regression coefficient of 12 genes. F Analysis of the correlation between the risk score and survival status. G The Kaplan–Meier survival curve of 12-gene signature in TCGA cohort. H The AUC curve of 12-gene signature in TCGA cohort. *: P ≤ 0.05, **: P ≤ 0.01, ***: P ≤ 0.001, ****: P ≤ 0.0001, *****: P ≤ 0.00001

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us