Table 3 Four-way classification by participant group (controls vs. svPPA vs. lvPPA vs. nfvPPA) with TRF beta weights as input.

From: Application of machine learning and temporal response function modeling of EEG data for differential diagnosis in primary progressive aphasia

Feature

Frequency band

Algorithm

Participant group

Precision

Recall

F1

Accuracy

Semantic dissimilarity

Delta

Logistic regression

Healthy controls

0.41

0.39

0.34

0.34

svPPA

0.40

0.35

lvPPA

0.30

0.36

nfvPPA

0.28

0.28

  1. F1 refers to the macro average of all class’ F1 scores.
Back to article page