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

Table 8 Experiment 3: Median ϕ^KNNand ϕ^RFof DF schemes across d ∈ {1, 2, ..10}

Classifier	PCA	PLS	CCA	RCCA	SRCCA_TT	SRCCA_WRST	SRCCA_WLT
ϕ ^KNN	52.63%	57.89%	57.89%	47.37%	68.42%	68.42%	68.42%
ϕ ^RF	51.58%	62.37%	58.42%	37.37%	72.89%	69.47%	74.21%

Median classification accuracies obtained for fusing (ϕ^P, ϕ^M), (ϕ^P, ϕ^A), and (ϕ^P, ϕ^H), with PCA, PLSR, CCA, RCCA, SRCCA_TT, SRCCA_WRST, and SRCCA_WLT across d ∈ {1, 2, ...10} components, using two classifiers, ϕ^KNN, with K = 1, and ϕ^RF, with 50 trees, and leave-one-out validation to identify patients at the risk of biochemical recurrence from those who are not.

ISSN: 1471-2105