Figure 3 | Scientific Reports

Figure 3

From: Using spectral and temporal filters with EEG signal to predict the temporal lobe epilepsy outcome after antiseizure medication via machine learning

Figure 3

(A) Average performance (AUC) for all feature groups with each EEG window length on the optimal frequency band. Asterisks indicate that the p value is lower than 0.05 compared with the AUC at 270 s. (B) Performance (AUC) of Feature 2 on the optimal frequency band at each EEG window length. Asterisks indicate that the p value is lower than 0.05 compared with the AUC at 150 s. (C) Performance (AUC) of Feature 2 at the optimal EEG window length for each frequency band. The frequency range of each band is as follows: delta band, 0.1–4 Hz; theta band, 4–8 Hz; alpha band, 8–12 Hz; beta1 (low beta) band, 12–16 Hz; beta2 (beta) band, 16–20 Hz; beta3 (high beta) band, 20–30 Hz; and low gamma band, 30–50 Hz. The asterisk indicates the frequency band with the highest performance.

Back to article page