Figure 4.
The prognostic efficiency of the Cox proportional hazards regression model. Heat map of the model genes in (A) training set of the TCGA, (B) test set of GSE16001, (C) test set of Rembrandt; ROC curves of the four genes signature for predicting 12- and 36-months survival of glioblastoma. The 12- and 36-months areas (AUC) under the ROC curves indicate higher predictive value; Kaplan–Meier curves analyze the survival of the high-risk group and the low-risk group, the high-risk group had the worse outcome (P < 0.001).