Table 3 Results of the classification between healthy patients and those who are diagnosed either with mild cognitive impairment or dementia obtained with various ML algorithms.
Classifier | ACC | AUC | F1-Score | Precision | Recall | MCC |
|---|---|---|---|---|---|---|
MLP | 0.53 | 0.60 | 0.40 | 0.38 | 0.51 | 0.06 |
SVM | 0.61 | 0.62 | 0.57 | 0.65 | 0.53 | 0.22 |
KNN | 0.66 | 0.71 | 0.54 | 0.83 | 0.41 | 0.37 |
Non–linear SVM | 0.75 | 0.85 | 0.79 | 0.69 | 0.93 | 0.54 |
Naive Bayes | 0.56 | 0.62 | 0.47 | 0.59 | 0.42 | 0.13 |
QDA | 0.54 | 0.60 | 0.42 | 0.57 | 0.34 | 0.10 |
LDA | 0.57 | 0.60 | 0.55 | 0.59 | 0.55 | 0.14 |
Random Forest | 0.70 | 0.79 | 0.67 | 0.75 | 0.62 | 0.41 |
AdaBoost | 0.60 | 0.65 | 0.59 | 0.62 | 0.58 | 0.21 |
Gaussian Process Classifier | 0.71 | 0.76 | 0.70 | 0.75 | 0.66 | 0.44 |
