Detecting temporal lobe seizures in ultra long-term subcutaneous EEG using algorithm-based data reduction

• Published in: Clinical neurophysiology Vol. 142; pp. 86 - 93
• Main Authors: Remvig, Line S., Duun-Henriksen, Jonas, Fürbass, Franz, Hartmann, Manfred, Viana, Pedro F., Kappel Overby, Anne Mette, Weisdorf, Sigge, Richardson, Mark P., Beniczky, Sándor, Kjaer, Troels W.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.10.2022
• Subjects: Algorithms; Electroencephalography - methods; Epilepsy; Epilepsy - diagnosis; Epilepsy, Temporal Lobe - diagnosis; Humans; Long-term monitoring; Neurology; Outpatient monitoring; Seizure detection; Seizures - diagnosis; Subcutaneous EEG; Temporal Lobe; Long-term monitoring; sqEEG; Seizure detection; Epilepsy; Subcutaneous EEG; Outpatient monitoring; PWE; epilepsy; subcutaneous encephalography; seizure detection; people with epilepsy; long-term monitoring; subcutaneous EEG; outpatient monitoring
• ISSN: 1388-2457; 1872-8952; 1872-8952
• DOI: 10.1016/j.clinph.2022.07.504

•Ultra long-term subcutaneous EEG offers a novel option for the recording of electrographic epileptic seizures in everyday life.•A semi-automatic seizure detection process is proposed to limit the time spent on review to periods of potential seizure activity.•The algorithm of the semi-automatic detection process had a sensitivity of 86% and a false detection rate of 2.4 per 24 hours. Ultra long-term monitoring with subcutaneous EEG (sqEEG) offers objective outpatient recording of electrographic seizures as an alternative to self-reported epileptic seizure diaries. This methodology requires an algorithm-based automatic seizure detection to indicate periods of potential seizure activity to reduce the time spent on visual review. The objective of this study was to evaluate the performance of a sqEEG-based automatic seizure detection algorithm. A multicenter cohort of subjects using sqEEG were analyzed, including nine people with epilepsy (PWE) and 12 healthy subjects, recording a total of 965 days. The automatic seizure detections of a deep-neural-network algorithm were compared to annotations from three human experts. Data reduction ratios were 99.6% in PWE and 99.9% in the control group. The cross-PWE sensitivity was 86% (median 80%, range 69–100% when PWE were evaluated individually), and the corresponding median false detection rate was 2.4 detections per 24 hours (range: 2.0–13.0). Our findings demonstrated that step one in a sqEEG-based semi-automatic seizure detection/review process can be performed with high sensitivity and clinically applicable specificity. Ultra long-term sqEEG bears the potential of improving objective seizure quantification.