Skip to main content
Fig. 3 | BMC Cancer

Fig. 3

From: Four-gene signature predicting overall survival and immune infiltration in hepatocellular carcinoma by bioinformatics analysis with RT‒qPCR validation

Fig. 3

Construction of a prognostic model of four DEGs in the training cohort (TCGA cohort) and validation of that in the validation cohort (ICGC cohort). Cross-validation to find the optimal lambda value in the LASSO regression (A). LASSO regression analysis was performed to select radiomic features for prognostic model-building for HCC patients. Feature coefficients were plotted against the shrinkage parameter (Lambda) (B). Risk score analysis of the four-gene-based signature. Risk score distributions (top), survival overviews (middle), and heatmaps (bottom) for patients assigned to high-and low-risk groups based on the risk scores in the TCGA cohort (C) and ICGC cohort (D). Kaplan‒Meier estimates of the overall survival (OS) using the prognostic model for patients in the TCGA cohort (E) and ICGC cohort (F) Time-dependent receiver operating characteristic (ROC) curves for the survival of high- and low-risk groups in the TCGA cohort (G) and ICGC cohort (H). Different colors represent different years

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us