Skip to main content

Table 5 Experiment 2: Classification Accuracy with K-Nearest Neighbor

From: Supervised Regularized Canonical Correlation Analysis: integrating histologic and proteomic measurements for predicting biochemical recurrence following prostate surgery

Dataset (ϕP, ϕJ) PCA PLSR SRCCA TT SRCCA WRST SRCCA WLT
(ϕP, ϕM) 68% 57% 80% 79% 79%
(ϕP, ϕA) 63% 47% 74% 68% 74%
(ϕP, ϕH) 53% 53% 74% 74% 74%
  1. Classification accuracies obtained for fusing (ϕP, ϕM), (ϕP, ϕA), and (ϕP, ϕH), with CCA, RCCA, SRCCA TT , SRCCA WRST , and SRCCA WLT using the top d = 3 components, using ϕKNNwith K = 1 neighbor and leave-one-out validation to identify patients at the risk of biochemical recurrence from those who are not.