Figure 3.
Figure 3. Separation of patients by SVM based on their expression of the 35 prognosis-associated genes. (A) Patients are ordered according to their values calculated by SVM, when PP and GP patients were used as training samples and set as 1 and –1, respectively (lower panel). Patients with values greater than 0 were classified as the high-risk group (indicated by red bar), and the remaining patients were classified as the low-risk group (indicated by blue bar). Expression of the 35 genes in these patients is also shown (upper panel). Each column represents a patient, and each row represents a gene. (B) Kaplan-Meier plots of EFS of patients divided into the high-risk and low-risk groups by SVM based on the 35 prognosis-associated genes (PP and GP patients were excluded). EFS differed significantly between the 2 groups (P = .03 in log-rank test).

Separation of patients by SVM based on their expression of the 35 prognosis-associated genes. (A) Patients are ordered according to their values calculated by SVM, when PP and GP patients were used as training samples and set as 1 and –1, respectively (lower panel). Patients with values greater than 0 were classified as the high-risk group (indicated by red bar), and the remaining patients were classified as the low-risk group (indicated by blue bar). Expression of the 35 genes in these patients is also shown (upper panel). Each column represents a patient, and each row represents a gene. (B) Kaplan-Meier plots of EFS of patients divided into the high-risk and low-risk groups by SVM based on the 35 prognosis-associated genes (PP and GP patients were excluded). EFS differed significantly between the 2 groups (P = .03 in log-rank test).

Close Modal

or Create an Account

Close Modal
Close Modal