Skip to main content

Table 1 Study population and characteristics

From: Enhancing magnetic resonance imaging-driven Alzheimer’s disease classification performance using generative adversarial learning

  ADNI 1.5 T ADNI 3 T NACC AIBL
Diagnosis NC MCI AD NC MCI AD NC AD NC AD
Number of cases 229 69 188 47 69 35 356 209 93 14
Age (median + range) 76 [60, 90] 76 [55, 88] 76 [55, 91] 75 [70–86] 76 [55, 88] 72 [57, 89] 74 [56, 94] 77 [55, 95] 71 [61, 86] 73 [58, 82]
Gender, male (percentage) 119 (51.96%) 39 (56.52%) 101 (53.72%) 18 (38.29%) 39 (56.52%) 12 (34.29%) 126 (35.39%) 95 (45.45%) 48 (51.61%) 6 (42.86%)
Education (median + range) 16 [6, 20] 16 [6, 20] 16 [4, 20] 16 [7, 20] 16 [6, 20] 14 [7, 20] 16 [0, 22] 14.5 [2, 24] N.A. N.A.
APOE+ (percentage) 61 (26.64%) 33 (47.83%) 124 (65.96%) 13 (27.66%) 33 (47.83%) 24 (68.75%) 102 (28.65%) 112 (53.59%) 1 (1.01%) 1 (7.17%)
MMSE (median + range) 29 [25, 30] 26 [24, 30] 23.5 [18, 28] 30 [26, 30] 26 [24, 30] 23 [20, 27] 29 [20, 30] 22 [0, 30] 29 [25, 30] 18 [6, 22]
  1. Three independent datasets including (a) the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset, (b) the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL), and (c) the National Alzheimer’s Coordinating Center (NACC) were used for this study