“…The predictive strength of the different risk models at follow‐up compared with baseline is shown in Figure 2 . 19 , 20 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 Overall, the C‐statistic at follow‐up was higher than at baseline. At follow‐up, it ranged from 0.66 to 0.91, with a median of 0.73 (IQR, 0.71–0.78), whereas at baseline, it ranged from 0.57 to 0.77, with a median of 0.67 (IQR, 0.65–0.69).…”