Table 2 Classification results using discriminant RBM, PCA with SVM, and LDA (Bold font denotes the best performance on certain metric of the 4 patients)
From: PATTERN: Pain Assessment for paTients who can’t TEll using Restricted Boltzmann machiNe
Patient ID | Model | AUC | Sensitivity | Specificity | Accuracy |
|---|---|---|---|---|---|
7137 | RBM | 0.73255 | 0.7143 | 0.6286 | 0.6714 |
PCA + SVM | 0.65541 | 0.8143 | 0.4714 | 0.6429 | |
LDA | 0.65316 | 0.8 | 0.4858 | 0.6429 | |
4822 | RBM | 0.76017 | 0.7037 | 0.6885 | 0.6932 |
PCA + SVM | 0.67729 | 0.6667 | 0.6557 | 0.625 | |
LDA | 0.67122 | 0.7037 | 0.5902 | 0.6591 | |
1245 | RBM | 0.8813 | 0.8667 | 0.8049 | 0.8214 |
PCA + SVM | 0.76504 | 0.8667 | 0.7317 | 0.7679 | |
LDA | 0.82033 | 0.8 | 0.7561 | 0.7679 | |
6563 | RBM | 0.78594 | 0.7692 | 0.6721 | 0.7011 |
PCA + SVM | 0.71721 | 0.5769 | 0.6885 | 0.6552 | |
LDA | 0.69893 | 0.7308 | 0.6393 | 0.6667 |