Table 5 Predictive values of each classifier for AD progression.

From: Atrophy of amygdala and abnormal memory-related alpha oscillations over posterior cingulate predict conversion to Alzheimer’s disease

Classifier

AUC (CI)

ACC%

SE%

SP%

R amygdala

0.75 (0.52–0.89)*

77.5*

74.4

79.2

αERDE L PCC

0.80 (0.60–0.92)*

81.3*

58.3

92.6*

αERDR L cuneus

0.77 (0.57–0.90)*

79.6*

75.4

71.7

R amygdala + αERDE L PCC

0.82 (0.63–0.93)*

80.9*

77.7*

82.2*

R amygdala + αERDR L cuneus

0.78 (0.56–0.90)*

80.0*

63.6

6.1*

  1. AUC = area under the curve; CI = confidence interval; ACC = accuracy; SE = sensitivity; SP = specificity; αERDE = alpha event-related desynchronization during encoding; αERDR = alpha event-related desynchronization during retrieval; PCC = posterior cingulate cortex; L = left; R = right; *significant after permutation testing (p < 0.05). Bold type indicates the best fit model.