Accurate detection of typical absence seizures in adults and children using a two-channel electroencephalographic wearable behind the ears

Lauren Swinnen, Christos Chatzichristos, Katrien Jansen, Lieven Lagae, Chantal Depondt, Laura Seynaeve, Evelien Vancaester, Annelies Van Dycke, Jaiver Macea, Kaat Vandecasteele, Victoria Broux, Maarten De Vos, Wim Van Paesschen, Lauren Swinnen, Christos Chatzichristos, Katrien Jansen, Lieven Lagae, Chantal Depondt, Laura Seynaeve, Evelien Vancaester, Annelies Van Dycke, Jaiver Macea, Kaat Vandecasteele, Victoria Broux, Maarten De Vos, Wim Van Paesschen

Abstract

Objective: Patients with absence epilepsy sensitivity <10% of their absences. The clinical gold standard to assess absence epilepsy is a 24-h electroencephalographic (EEG) recording, which is expensive, obtrusive, and time-consuming to review. We aimed to (1) investigate the performance of an unobtrusive, two-channel behind-the-ear EEG-based wearable, the Sensor Dot (SD), to detect typical absences in adults and children; and (2) develop a sensitive patient-specific absence seizure detection algorithm to reduce the review time of the recordings.

Methods: We recruited 12 patients (median age = 21 years, range = 8-50; seven female) who were admitted to the epilepsy monitoring units of University Hospitals Leuven for a 24-h 25-channel video-EEG recording to assess their refractory typical absences. Four additional behind-the-ear electrodes were attached for concomitant recording with the SD. Typical absences were defined as 3-Hz spike-and-wave discharges on EEG, lasting 3 s or longer. Seizures on SD were blindly annotated on the full recording and on the algorithm-labeled file and consequently compared to 25-channel EEG annotations. Patients or caregivers were asked to keep a seizure diary. Performance of the SD and seizure diary were measured using the F1 score.

Results: We concomitantly recorded 284 absences on video-EEG and SD. Our absence detection algorithm had a sensitivity of .983 and false positives per hour rate of .9138. Blind reading of full SD data resulted in sensitivity of .81, precision of .89, and F1 score of .73, whereas review of the algorithm-labeled files resulted in scores of .83, .89, and .87, respectively. Patient self-reporting gave sensitivity of .08, precision of 1.00, and F1 score of .15.

Significance: Using the wearable SD, epileptologists were able to reliably detect typical absence seizures. Our automated absence detection algorithm reduced the review time of a 24-h recording from 1-2 h to around 5-10 min.

Keywords: epilepsy; seizure detection algorithm; seizure underreporting; typical absence seizures; wearable seizure detection.

Conflict of interest statement

L.L. has received speaker honoraria from and is participating on advisory boards for Zogenix, Livanova, UCB, Eisai, Novartis, NEL, and Epihunter. None of the other authors has any conflict of interest to disclose. We confirm that we have read the Journal’s position on issues involved in ethical publication and affirm that this report is consistent with those guidelines.

© 2021 The Authors. Epilepsia published by Wiley Periodicals LLC on behalf of International League Against Epilepsy.

Figures

FIGURE 1
FIGURE 1
Concept of the Sensor Dot (SD) used as a wearable to detect absence seizures. (1) Four electrodes (in orange) are placed behind the ears of the patient and connected to the mobile electroencephalographic (EEG) device, the SD, which is attached to the upper back via an adhesive (in blue). An enlarged image of the SD is given in the circle. (2) After 24 h of recording, the SD is placed in the docking station, which allows recharging of the battery. In addition, when the SD is in the docking station, the SD EEG data are automatically uploaded to the cloud via a Wi‐Fi connection. (3) Afterward, the absence detection algorithm analyzes the data and flags segments of interest (in red). (4) Finally, the flagged data are sent back to the treating neurologist, who can then review the flagged SD EEG data in a short time.
FIGURE 2
FIGURE 2
Examples of 3‐Hz spike‐and‐wave discharges visible on the two‐channel Sensor Dot during an absence seizure in (A) a pediatric patient and (B) an adult patient. A high‐pass filter of .53 Hz, a low‐pass filter of 35 Hz, and a notch filter were applied. Sensitivity: 100 µV/cm. Time base: 10 s. Absences lasting 8 s (A) and 5 s (B) were marked. Ch1#1, left; Ch2#1, right
FIGURE 3
FIGURE 3
Common reasons for a false positive (FP) or false negative (FN) annotation on Sensor Dot. (A) Chewing artifact, characterized by 2‐Hz slow waves with superimposed muscle artifacts, which were often mistaken for seizures (FPs). (B, C) Commonly missed absences due to the presence of chewing artifacts (B) and muscle artifacts (C). A high‐pass filter of .53 Hz, a low‐pass filter of 35 Hz, and a notch filter were applied. Sensitivity: 100 µV/cm. Time base: 10 s. Ch1#1, left; Ch2#1, right
FIGURE 4
FIGURE 4
Percentage of seizures (defined in this study as a discharge lasting 3 s or longer) of different duration reported by the patients themselves or by caregivers for children. (A) Each duration separately. (B) Grouped into shorter and longer duration in relation to the findings by Guo et al. EEG, electroencephalographic

References

    1. Commission on Classification and Terminology of the International League Against Epilepsy . Proposal for revised clinical and electroencephalographic classification of epileptic seizures. Epilepsia. 1981;22(4):489–501.
    1. Guilhoto LM. Absence epilepsy: continuum of clinical presentation and epigenetics? Seizure. 2017;44:53–7.
    1. Scheffer IE, Berkovic S, Capovilla G, Connolly MB, French J, Guilhoto L, et al. ILAE classification of the epilepsies: position paper of the ILAE Commission for Classification and Terminology. Epilepsia. 2017;58(4):512–21.
    1. Antwi P, Atac E, Ryu JH, Arencibia CA, Tomatsu S, Saleem N, et al. Driving status of patients with generalized spike–wave on EEG but no clinical seizures. Epilepsy Behav. 2019;92:5–13.
    1. Kessler SK, McGinnis E. A practical guide to treatment of childhood absence epilepsy. Pediatr Drugs. 2019;21(1):15–24.
    1. Grosso S, Galimberti D, Vezzosi P, Farnetani M, Di Bartolo RM, Bazzotti S, et al. Childhood absence epilepsy: evolution and prognostic factors. Epilepsia. 2005;46(11):1796–801.
    1. Callenbach PMC, Bouma PAD, Geerts AT, Arts WFM, Stroink H, Peeters EAJ, et al. Long‐term outcome of childhood absence epilepsy: Dutch Study of Epilepsy in Childhood. Epilepsy Res. 2009;83(2–3):249–56.
    1. Holtkamp M, Janz D, Kirschbaum A, Kowski AB, Vorderwülbecke BJ. Absence epilepsy beyond adolescence: an outcome analysis after 45 years of follow‐up. J Neurol Neurosurg Psychiatry. 2018;89(6):603–10.
    1. Elger CE, Hoppe C. Diagnostic challenges in epilepsy: seizure under‐reporting and seizure detection. Lancet Neurol. 2018;17(3):279–88.
    1. Akman CI, Montenegro MA, Jacob S, Eck K, Chiriboga C, Gilliam F. Seizure frequency in children with epilepsy: factors influencing accuracy and parental awareness. Seizure. 2009;18(7):524–9.
    1. Keilson MJ, Hauser A, Magrill JP, Tepperberg J. Ambulatory cassette EEG in absence epilepsy. Pediatr Neurol. 1987;3:273–6.
    1. Fiest KM, Birbeck GL, Jacoby A, Jette N. Stigma in epilepsy. Curr Neurol Neurosci Rep. 2014;14(5):444.
    1. Ryvlin P, Beniczky S. Seizure detection and mobile health devices in epilepsy: recent developments and future perspectives. Epilepsia. 2020;61:1–2.
    1. Zibrandtsen IC, Kidmose P, Christensen CB, Kjaer TW. Ear‐EEG detects ictal and interictal abnormalities in focal and generalized epilepsy—a comparison with scalp EEG monitoring. Clin Neurophysiol. 2017;128(12):2454–61.
    1. Zibrandtsen IC, Kidmose P, Kjaer TW. Detection of generalized tonic‐clonic seizures from ear‐EEG based on EMG analysis. Seizure. 2018;59:54–9.
    1. Frankel MA, Lehmkuhle MJ, Watson M, Fetrow K, Frey L, Drees C, et al. Electrographic seizure monitoring with a novel, wireless, single‐channel EEG sensor. Clin Neurophysiol Pract. 2021;6:172–8.
    1. Bruno E, Simblett S, Lang A, Biondi A, Odoi C, Schulze‐Bonhage A, et al. Wearable technology in epilepsy: the views of patients, caregivers, and healthcare professionals. Epilepsy Behav. 2018;85:141–9.
    1. Simblett SK, Biondi A, Bruno E, Ballard D, Stoneman A, Lees S, et al. Patients’ experience of wearing multimodal sensor devices intended to detect epileptic seizures: a qualitative analysis. Epilepsy Behav. 2020;102:106717.
    1. EIT Health . SeizeIT2: Discreet, personalised epileptic seizure detection device. 2020. . Accessed 8 April 2021.
    1. Seeck M, Koessler L, Bast T, Leijten F, Michel C, Baumgartner C, et al. The standardized EEG electrode array of the IFCN. Clin Neurophysiol. 2017;128(10):2070–7.
    1. Keogh EJ, Pazzani MJ, editors. Derivative dynamic time warping. International Conference on Data Mining. Chicago, IL: SIAM; 2001. p. 1–11.
    1. Vandecasteele K, De Cooman T, Dan J, Cleeren E, Van Huffel S, Hunyadi B, et al. Visual seizure annotation and automated seizure detection using behind‐the‐ear electroencephalographic channels. Epilepsia. 2020;61(4):766–75.
    1. Kjaer TW, Sorensen HBD, Groenborg S, Pedersen CR, Duun‐Henriksen J. Detection of paroxysms in long‐term, single‐channel EEG‐monitoring of patients with typical absence seizures. IEEE J Transl Eng Heal Med. 2017;5(2000):1–8.
    1. Yen S‐J, Lee Y‐S. Cluster‐based under‐sampling approaches for imbalanced data distributions. Expert Syst Appl. 2009;36(3):5718–27.
    1. Deviaene M, Testelmans D, Borzée P, Buyse B, Van Huffel S, Varon C, editors. Feature selection algorithm based on random forest applied to sleep apnea detection. In: Proceedings of the 41th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC). Berlin, Germany; 2019. p. 1–4.
    1. Logesparan L, Rodriguez‐Villegas E, Casson AJ. The impact of signal normalization on seizure detection using line length features. Med Biol Eng Comput. 2015;53:929–42.
    1. Filzmoser P, Liebmann B, Varmuza K. Repeated double cross validation. J Chemom. 2009;23(4):160–71.
    1. Parvandeh S, Yeh HW, Paulus MP, McKinney BA. Consensus features nested cross‐validation. Bioinformatics. 2020;36(10):3093–8.
    1. Blomquist HK, Zetterlund B. Evaluation of treatment in typical absence seizures: the roles of long‐term EEG monitoring and ethosuximide. Acta Paediatr Scand. 1985;74(3):409–15.
    1. Appleton RE, Beirne M. Absence epilepsy in children: the role of EEG in monitoring response to treatment. Seizure. 1996;5:147–8.
    1. Guo JN, Kim R, Chen YU, Negishi M, Jhun S, Weiss S, et al. Impaired consciousness in patients with absence seizures investigated by functional MRI, EEG, and behavioural measures: a cross‐sectional study. Lancet Neurol. 2016;15:1336–45.
    1. Crunelli V, Lőrincz ML, McCafferty C, Lambert RC, Leresche N, Di Giovanni G, et al. Clinical and experimental insight into pathophysiology, comorbidity and therapy of absence seizures. Brain. 2020;143(8):2341–68.
    1. Duun‐Henriksen J, Madsen RE, Remvig LS, Thomsen CE, Sorensen HBD, Kjaer TW. Automatic detection of childhood absence epilepsy seizures: toward a monitoring device. Pediatr Neurol. 2012;46(5):287–92.
    1. Beniczky S, Ryvlin P. Standards for testing and clinical validation of seizure detection devices. Epilepsia. 2018;59:9–13.

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi