Research Article
An Efficient Combination among sMRI, CSF, Cognitive Score, and APOE ε4 Biomarkers for Classification of AD and MCI Using Extreme Learning Machine
Table 4
10-fold cross-validated classification performance for AD vs. MCI.
| Features measure | ELM | SVM-RBF | SVM-linear | ACC% | SEN% | SPE% | AUC | ACC% | SEN% | SPE% | ACC% | SEN% | SPE% |
| Cortical thickness | 70.10 | 81.30 | 66.10 | 0.71 | 64.01 | 83.83 | 62.33 | 65.03 | 78.80 | 73.30 | Surface area | 61.60 | 66.70 | 84.30 | 0.63 | 63.45 | 68.10 | 80.11 | 60.67 | 71.23 | 62.85 | Volume | 67.80 | 82.10 | 67.10 | 0.69 | 58.20 | 77.92 | 68.56 | 60.05 | 73.37 | 63.73 | CSF | 64.70 | 66.00 | 81.40 | 0.73 | 56.07 | 62.75 | 75.73 | 61.23 | 68.71 | 79.37 | APOE + MMSE | 81.45 | 84.40 | 87.70 | 0.82 | 76.81 | 67.81 | 85.48 | 76.20 | 66.94 | 87.48 | Concatenation (all_features_set) | 87.91 | 92.00 | 97.33 | 0.89 | 83.50 | 88.64 | 76.72 | 78.31 | 74.45 | 82.62 |
|
|