Table 3.
Classification report of the classifiers in the “immediate word recall” cognitive assessment task (scenario 3)
| Cross-validation accuracy (%) | Accuracy (on data split) (%) | Precision | f1-score | Sensitivity | Specificity | ||
|---|---|---|---|---|---|---|---|
| Dementia | Normal | ||||||
| A. Scenario 3A: on the sample person’s responses | |||||||
| KNN | 93.00 | 93.00 | 0.77 | 0.94 | 0.92 | 0.36 | 0.99 |
| Decision tree | 93.00 | 93.00 | 0.77 | 0.94 | 0.92 | 0.36 | 0.99 |
| Random forest | 93.00 | 93.00 | 0.77 | 0.94 | 0.92 | 0.36 | 0.99 |
| Artificial neural networks | 92.00 | 93.00 | 0.73 | 0.94 | 0.92 | 0.37 | 0.99 |
| B. Scenario 3B: on the proxy’s responses | |||||||
| KNN | 88.00 | 91.00 | 0.79 | 0.98 | 0.91 | 0.97 | 0.88 |
| Decision tree | 88.00 | 92.00 | 0.80 | 0.99 | 0.92 | 0.98 | 0.89 |
| Random forest | 88.00 | 92.00 | 0.80 | 0.99 | 0.92 | 0.98 | 0.89 |
| Artificial neural networks | 88.00 | 91.00 | 0.83 | 0.95 | 0.91 | 0.89 | 0.92 |
| C. Scenario 3C: on the sample person’s and proxy’s responses | |||||||
| KNN | 95.00 | 94.00 | 0.89 | 1.00 | 0.94 | 1.00 | 0.88 |
| Decision tree | 95.00 | 94.00 | 0.89 | 1.00 | 0.94 | 1.00 | 0.88 |
| Random forest | 95.00 | 94.00 | 0.89 | 1.00 | 0.94 | 1.00 | 0.88 |
| Artificial neural networks | 93.00 | 94.00 | 0.89 | 1.00 | 0.94 | 1.00 | 0.88 |