Feature Whitening

How it works

Preparation

Evidence quality

Highlighted claims

• The approach mapped coefficients learned in whitened space back to original ROI feature space. — Improving clinical interpretability of linear neuroimaging models through feature whitening
• Whitening matrices were fit only on training folds and applied to test folds to avoid leakage. — Improving clinical interpretability of linear neuroimaging models through feature whitening
• Whitening was applied to left-right homologous regions and GM-CSF volumes within the same brain region. — Improving clinical interpretability of linear neuroimaging models through feature whitening
• The method used ZCA-cor whitening matrices computed from standardized two-feature data matrices. — Improving clinical interpretability of linear neuroimaging models through feature whitening
• The article proposes whitening anatomically meaningful pairs of correlated neuroimaging features to separate overlapping information while retaining predictive performance. — Improving clinical interpretability of linear neuroimaging models through feature whitening
• Regularized ZCA-cor whitening allowed partial decorrelation when original correlations might contain disease-relevant information. — Improving clinical interpretability of linear neuroimaging models through feature whitening