Table 2.
Task | No. of minority class | No. of majority class | Method | Accuracy (%) | Sensitivity (%) | Specificity (%) | AUC |
---|---|---|---|---|---|---|---|
aMCI vs. CN | aMCI = 42 | CN = 115 | Baseline | 0.64 | 0.42 | 0.71 | 0.68 |
Wave-2 | 0.81* | 0.68 | 0.85 | 0.74 | |||
Longitudinal | 0.73 | 0.53 | 0.80 | 0.75 | |||
naMCI vs. CN | naMCI = 27 | CN = 115 | Baseline | 0.67 | 0.37 | 0.75 | 0.57 |
Wave-2 | 0.65 | 0.30 | 0.74 | 0.58 | |||
Longitudinal | 0.70 | 0.23 | 0.82 | 0.60 | |||
naMCI vs. aMCI | naMCI = 27 | aMCI = 42 | Baseline | 0.77* | 0.70* | 0.82 | 0.84* |
Wave-2 | 0.71 | 0.57 | 0.82 | 0.70 | |||
Longitudinal | 0.61 | 0.40 | 0.78 | 0.71 |
wave-2, 2-year follow-up; MCI, mild cognitive impairment; CN cognitively normal; aMCI, amnestic MCI; naMCI, non-amnestic MCI; AUC, area under the receiver operating characteristic curve.
Significantly different from the method using longitudinal features; results are from t-test (p < 0.05).