Table 2 Performance comparisons of our model with those of other studies reported in the literature for AD vs. LMCI vs. EMCI vs. NC, EMCI vs. LMCI, and EMCI vs. NC.
Train | Test | Tasks | Method | ACC (%) | SEN (%) | SPE (%) | AUC |
|---|---|---|---|---|---|---|---|
AD vs. LMCI vs. EMCI vs. NC | STNet33 | 60.67 | - | - | - | ||
Adaptive sparse learning34 | 64.97 | - | - | - | |||
ADNI | ADNI | Our study | 78.70 | - | - | 0.95 | |
EMCI vs. LMCI | Graph CNN35 | 60.90 | 52.50 | 67.80 | - | ||
MFCC-MK-SVM36 | 73.87 | 90.55 | 49.52 | 0.70 | |||
STNet33 | 79.36 | 80.95 | 77.00 | 0.83 | |||
SWRLS dFC37 | 83.80 | 87.20 | 82.00 | 0.85 | |||
ADNI | ADNI | Our study | 84.67 | 77.56 | 96.97 | 0.96 | |
EMCI vs. NC | Forouzannezhad38 | 61.10 | 66.50 | 58.70 | - | ||
MB-CNN-ALL12 | 73.85 | 73.91 | 73.69 | 0.81 | |||
Temporal embedding network39 | 74.42 | 75.72 | 73.06 | 0.74 | |||
GDCA40 | 79.25 | 79.31 | 79.17 | 0.80 | |||
ADNI | ADNI | Our study | 82.00 | 100.00 | 69.40 | 0.82 |
