Table 5.
Paper | Dataset | Method | Validation | Results (%) |
---|---|---|---|---|
Cassani and Falk (2019) | 20 HC, 34 AD | Spectral feature extraction, ANOVA, SVM | LOSO CV | Acc: 88.1, F1 86.2 |
Vecchio et al. (2020) | 120 HC, 175 AD | Exact low-resolution brain electromagnetic tomography, SVM | Hold-out CV (80:20) |
Acc: 95.0, Sen: 95.0, Spe: 96.0 |
Alves et al. (2022) | 24 HC, 24 AD | Pearson’s correlation, custom-designed CNN, hyperparameter optimization | tenfold CV |
Acc: 100, Pre: 100, Rec: 100 |
Dogan et al. (2022) | 11 HC, 12 AD | Primate brain pattern, INCA, kNN | tenfold CV |
Acc: 100, Pre: 100, Rec: 100 |
Our model | 8 HC, 1 AD | Lattice123, MDWT, INCA, kNN, IHMV, greedy algorithm | tenfold CV |
Experiment 1: • Acc:98.37, GM:96.74 |
Experiment 2: • Acc:99.62, GM:99.45 | ||||
Experiment 3: • Acc:98.74, GM:97.52 | ||||
Alternative dataset 11 HC, 12 AD |
Acc: 100, Pre: 100, Rec: 100 |