Research Paper Volume 12, Issue 13 pp 13318—13337

Subtype-specific risk models for accurately predicting the prognosis of breast cancer using differentially expressed autophagy-related genes

Figure 4. Construction and Validation of the prognostic risk model in Luminal BRCA patients. (A) Lasso regression analyses of DEARGs using the OS model. The Lasso regression was performed using prognosis-significant DEARGs in the training dataset of Luminal BRCA. (B) Kaplan-Meier plot represents that patients in the high-risk group had a significantly shorter overall survival time than those in the low-risk group. left, training dataset, right, testing dataset. (C) Time-dependent ROC curve analyses showing AUC values for OS in BRCA patients. Left, training dataset, right, testing dataset. (D) Dot plots showing the survival time and risk score in training set and testing set. (E) The heatmap of the 4 key genes expression profiles in the training dataset and testing dataset. (F) Forest plot showing the multivariable Cox regression analysis of 4 key genes in risk-model.