Research Article
Diagnosis of Alzheimer’s Disease Severity with fMRI Images Using Robust Multitask Feature Extraction Method and Convolutional Neural Network (CNN)
Table 4
Comparison of the diagnosis methods used in this paper.
| | Class | KNN | SVM | DT | LDA | RF | Presented CNN |
| Sensitivity | Low | 94.6% | 95.1% | 94.9% | 91.0% | 99.9% | 98.1% | Mild | 51.1% | 57.6% | 94.3% | 50.2% | 54.6% | 95.2% | Moderate | 6.8% | 84.9% | 61.6% | 61.6% | 47.9% | 89.0% | Severe | 0.0% | 100% | 12.5% | 87.5% | 25.0% | 87.5% |
| Precision | Low | 79.0% | 86.5% | 96.9% | 83.4% | 82.5% | 98.1% | Mild | 70.1% | 80.0% | 80.6% | 70.6% | 97.7% | 92.4% | Moderate | 83.3% | 89.9% | 83.3% | 61.6% | 100% | 97.0% | Severe | 0% | 100% | 50.0% | 63.6% | 100% | 100% |
| Accuracy | | 77.5% | 85.8% | 91.7% | 79.5% | 85.1% | 96.7% |
|
|