The Power of ECG in Semi-Automated Seizure Detection in Addition to Two-Channel behind-the-Ear EEG

Figure 1. Graphical representation of the multimodal automated multimodal seizure detection framework based on bte-EEG and ECG.

Figure 2. Presentation setup for the two visual experiments: (a) setup for visual annotation of the bte-EEG data; (b) setup for visual annotation of the bte-EEG and ECG data. In (a,b), the black time-series corresponds to the ipsilateral (top) and cross-head (bottom) bte-EEG channel. In (b), the top red signal corresponds to the heart rate derived from ECG, and the bottom red signal shows the raw ECG data. The heart rate data are presented in a 10 min window, and the other signals in a 10 s window. The green vertical lines indicate the start and end of the detected seizure, and the purple shaded area on the heart rate plot depicts the 10 s window presented in the bte-EEG and ECG plot.

Figure 3. Diagram representing the gain in sensitivity, inter-rater agreement, and reduction of false alarms by reviewing the data with the semi-automated multimodal framework (bte-EEG and ECG) compared with the unimodal framework (bte-EEG). The reduction in the time to review is compared with the reported time to review 24 h of bte-EEG recordings without automated assistance.

Figure 4. Number of detected (correctly annotated) and missed (mislabeled) seizures of the two readers in the two experimental setups readers, discriminated by the location of the seizure onset (Temp—Temporal, Fronto-temp—Fronto-temporal, Occ-temp—Occipital-temporal, Front—Frontal, Fronto-par—Fronto-parietal, Par—Parietal, or NC—Not Clear).

Figure 5. (a) Number of true positives (TP, correctly annotated seizures) and false negatives (FN, mislabeled seizure segments) and (b) number of false positives (FP, detections incorrectly classified as seizures) of the two readers in the two experimental setups readers discriminated by the type of patient (responder, non-responder, or intermediate response) according to the presence of ictal ECG changes.

Figure 6. Example of a detected seizure segment mislabeled as a non-seizure on the bte-EEG experimental setup but corrected on the bte-EEG and ECG and heart rate setup (change from FN to TP). The top plot contains the heart rate data in red within a 10 min window, and the bottom contains the bte-EEG channels (in black) and ECG data (in red) within a 10 s window. The shaded section of the heart rate plot corresponds to the plotted area of the bottom one. The green vertical lines indicate the automated algorithm’s time events.

Figure 7. Example of a detected seizure segment correctly labeled by the readers on the bte-EEG experimental setup but mislabeled on the bte-EEG and ECG and heart rate setup (change from TP to FN). The top plot contains the heart rate data in red within a 10 min window, and the bottom contains the bte-EEG channels (in black) and ECG data (in red) within a 10 s window. The shaded section of the heart rate plot corresponds to the plotted area of the bottom one. The green vertical lines indicate the automated algorithm’s time events.

Figure 8. Example of a detected segment incorrectly labeled as a seizure by the algorithm and by the readers on both the bte-EEG setup and the bte-EEG and ECG and heart rate setups(FP). The top plot contains the heart rate data in red within a 10 min window, and the bottom contains the bte-EEG channels (in black) and ECG data (in red) within a 10 s window. The shaded section of the heart rate plot corresponds to the plotted area of the bottom one. The green vertical lines indicate the automated algorithm’s time events.