Table 2 AD-DLB classification result comparison for EC and EC-EO classification using 10-fold cross-validation, with comparisons across 3 separate machine learning models: k-nearest neighbour, logistic regression and support vector machine
From: Investigating the power of eyes open resting state EEG for assisting in dementia diagnosis
AD-DLB classification accuracies | ||||
|---|---|---|---|---|
Classifier | Accuracy | Specificity (± CI) | Sensitivity (± CI) | Weighted Average AUC |
EC + EO data | ||||
Cosine KNN | 0.82 ± 0.13 | 0.75 ± 0.19 | 0.81 ± 0.17 | 0.74 |
Logistic Regression | 0.76 ± 0.15 | 0.67 ± 0.20 | 0.86 ± 0.15 | 0.84 |
Quadratic SVM | 0.82 ± 0.13 | 0.58 ± 0.21 | 0.95 ± 0.09 | 0.82 |
EC data only | ||||
Cosine KNN | 0.67 ± 0.16 | 0.5 ± 0.21 | 0.76 ± 0.18 | 0.63 |
Logistic Regression | 0.73 ± 0.15 | 0.58 ± 0.21 | 0.81 ± 0.17 | 0.77 |
Quadratic SVM | 0.73 ± 0.15 | 0.58 ± 0.21 | 0.81 ± 0.17 | 0.72 |