Fig. 4

A1. Curve of risk(training set): Distribution of risk scores in the training set, ordered by increasing risk scores. Patients were categorized into high-risk and low-risk groups based on the optimal risk-score cutoff. Red dots represent patients in the high-risk group, whereas blue dots represent those in the low-risk group. A2. survival status(training set): Red points are dead samples, blue points are survival samples, and dashed lines are the best cutoff value of risk score. B1. Curve of risk(validation set).B2. survival status(validation set). C. Train KM: Kaplan-Meier survival curves for the training dataset, The unit of time is days; Red represents the high-risk group, blue represents the low-risk group, and the bottom number represents the number of samples that survived at this time. D. Verify KM. E. Train ROC: Receiver Operating Characteristic (ROC) curves for the training dataset at 1, 3, and 5 years. The area under the curve (AUC) values were all > 0.6. F. Verify ROC. G. Train Heatmap: The heatmap displays the expression patterns of the selected genes in the training dataset. Each row represents a gene, and each column represents a patient. The color scale indicates the expression level. H. Verify Heatmap.