Skip to main content

Table 2 Mean accuracies of the CDT and RCFT-copy for the prediction of cognitive impairment

From: Use of the Clock Drawing Test and the Rey–Osterrieth Complex Figure Test-copy with convolutional neural networks to predict cognitive impairment

  No. of images No. of images training: validation dataset Mean accuracy of validation dataset (%)
CDT NC vs CI
(1362:879)
1569:672 77.37 ± 1.77
  NC vs MI (1362:537) 1330:569 78.04 ± 2.75
  NC vs SI
(1362:342)
1193:511 91.45 ± 0.83
  NC vs MI vs SI
(1362:537:342)
1569:672 71.06 ± 0.75
RCFT-copy NC vs CI
(1233:1707))
2058:882 83.52 ± 1.41
  NC vs MI
(1233:1101)
1634:700 NT
  NC vs SI
(1233:606)
1288:551 90.10 ± 1.33
  NC vs MI vs SI
(1233:1101:606)
2058:882 71.50 ± 1.16
  1. CDT, clock drawing test; RCFT, Rey–Osterrieth Complex Figure Test; NC, normal cognition; MI, mild impairment of cognition; SI, severe impairment of cognition; NT, not being trained