Figure 6.

Establishing a Prognostic Model for LUAD

(A) Identification of the optimal penalization coefficient lambda in the Lasso regression model. (B) ROC curves of the risk score for predicting 1-year, 3-year, and 5-year survival. (C) ROC curves of the risk score combined with clinical factors for predicting 1-year, 3-year, and 5-year survival. (D) Forest plot of the prognostic impact of 27 variables. (E) Forest plot of the prognostic impact of risk score and clinical factors. (F) Heatmap in the top panel shows the gradient of 27 variables. The color in the heatmap represents the normalized values of log₂FPKM, log₂Δbeta, and mutation status (0 for non-mutated and 1 for mutated). The scatterplots in the middle and bottom panels respectively illustrate the distribution of risk score and survival status of LUAD patients. (G) Kaplan-Meier curves show the independent relevance between overall survival time and risk scores.