Skip to main content

Table 4 LS-SVM models for the prediction of GRADE, STAGE, METASTASIS and RECURRENCE in prostate cancer

From: A kernel-based integration of genome-wide data for clinical decision support

Outcome Model NG* NC AUC (SE) p-value§
GRADE      
   A M 24   0.8304 (0.0623) 0.2727
  G   8 0.7822 (0.0632) 0.0503
   C MG 6 8 0.9006 (0.0413)  
STAGE      
   A M 18   0.6576 (0.0778) 0.0191
  G   32 0.7936 (0.0631) 0.3466
   C MG 42 22 0.8528 (0.0550)  
METASTASIS      
   A M 18   0.9759 (0.0178) 0.4392
  G   12 0.8114 (0.0755) 0.0166
   C MG 18 3 0.9868 (0.0121)  
RECURRENCE      
   A M 24   0.7208 (0.0936) 0.5392
  G   26 0.4481 (0.1433) 0.0354
   C MG 32 2 0.7857 (0.0934)  
  1. *Number of genes selected in each LOO iteration. Number of copy number variations selected in each LOO iteration. Area under the ROC curve (standard error) obtained with leave-one-out. §Comparison of AUC between each model and the best model in bold [46].