Fig. 3.

Brain age prediction results with real data from UK Biobank (N=19000). A,B) The first two scatterplots show the clear bias (age-dependence) in ${\delta }_1$ being corrected in ${\delta }_2$ (each point is one subject). C) shows relative strengths of correlations of ${\delta }_1$ and ${\delta }_2$ with (fully deconfounded) non-imaging variables, with the latter showing consistently stronger associations (each point relates to the association of a single non-imaging variable to brain age delta). P-values are uncorrected for multiple comparisons. D) shows the change in associations with ${\delta }_1$, without (x axis) vs. with (y axis) age-deconfounding of the non-imaging variables; this illustrates the danger of looking for associations between biased brain age delta and non-imaging variables that have not been corrected for age dependence. E) shows a similar story, when using ${\delta }_2$ on the y axis; bias can cause (probably unwanted and misleading) associations (points under the y = x line), while applying the corrections described here can raise sensitivity to finding (what are hopefully valid) associations in other cases (points above the line).