TABLE 2.

Correlations between age‐matching cross‐sectional subsamples’ ages and brain age estimates.

Matched subject	Field strength	N subjects	Pearson's r [95% CI] *	Mean age	SD age	Mean prediction	SD prediction	Mean BAG	SD BAG	MAE	RMSE
BBSC1	3T	279	0.56 [0.47, 0.64]	30.64	2.74	28.34	4.10	−2.30	3.42	3.33	4.12
BBSC2	3T	269	0.62 [0.54, 0.69]	28.81	2.83	26.75	3.96	−2.05	3.13	3.02	3.74
BBSC3	3T	248	0.44 [0.34, 0.54]	40.71	2.95	37.86	5.21	−2.85	4.71	4.52	5.50
FTHP1	3T	113	0.71 [0.60, 0.79]	48.60	3.04	44.68	5.93	−3.91	4.34	4.59	5.84
FTHP1	1.5T	49	0.79 [0.65, 0.88]	49.61	3.22	51.98	4.40	2.38	2.71	2.91	3.58

Matched subject refers to the longitudinally sample subjects presented in Table 1. Mean ages for the respective subjects with an interval of five years were used to sample from the cross‐sectional validation set consisting of 3T and 1.5T data from TOP and NCNG samples. BAG, brain age gap; MAE, mean absolute error; RMSE, root mean squared error. BAG is calculated as the difference between predicted age and age.

^*All p < .001.