Multichannel automatic detection of sleep spindles in focal epilepsy
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13845Keywords:
Biomedical signal measurement and processing, Clinical trial, Clinical validation, Decision support and control in medicine, Neuro-system modeling, Biomedical system modeling, identification, and simulationAbstract
Sleep spindles have emerged as neurophysiological biomarkers in paediatric focal epilepsy, although their manual identification in electroencephalographic (EEG) recordings remains a slow and subjective process. This preliminary study presents a multichannel adaptation and optimization of a single-channel method for the automatic detection of sleep spindles in paediatric patients with focal epilepsy. The study was conducted on polysomnographic recordings from seven patients, using six bipolar EEG derivations and a multichannel validation based on the simultaneous detection of events across different brain regions. Detector parameters were optimized by maximizing the F1-score with respect to annotations from an expert in neurophysiology. The optimal system configuration achieved a global F1-score of 0.625, comparable to inter-expert agreement reported in the literature. In addition, the estimated spindle densities showed physiologically plausible ranges consistent with previous paediatric studies. Overall, the results suggest that multichannel automatic detection constitutes a promising tool for the objective and reproducible analysis of sleep spindles in paediatric epilepsy.
References
Chen, C., Wang, K., Belkacem, A.N., Lu, L., Yi, W., Liang, J., Huang, Z., Ming, D., 2023. A comparative analysis of sleep spindle characteristics of sleep-disordered patients and normal subjects. Frontiers in Neuroscience 17, 1110320. DOI: 10.3389/fnins.2023.1110320.
Fisher, R.S., Acevedo, C., Arzimanoglou, A., et al., 2014. ILAE official report: A practical clinical definition of epilepsy. Epilepsia 55(4), 475–482. DOI: 10.1111/EPI.12550
Fortini, S., Beghi, E., Canevini, M.P., et al., 2021. More than one self-limited epilepsy of childhood in the same patient: A multicenter study. Epilepsy Research 177, 106768. DOI: 10.1016/J.EPLEPSYRES.2021.106768.
Gallotto, S., Seeck, M., 2023. EEG biomarker candidates for the identification of epilepsy. Clinical Neurophysiology Practice 8, 32–41. DOI: 10.1016/j.cnp.2022.11.004.
Gruber, R., Wise, M.S., 2016. Sleep spindle characteristics in children with neurodevelopmental disorders and their relation to cognition. Neural Plasticity 2016, 4724792. DOI: 10.1155/2016/4724792.
Iber, C., Ancoli-Israel, S., Chesson, A.L., 2015. The AASM manual for the scoring of sleep and associated events. American Academy of Sleep Medicine, Westchester, IL, USA.
Kramer, M.A., Stoyell, S.M., Chinappen, D., Ostrowski, L.M., Spencer, E.R., Morgan, A.K., Emerton, B.C., Jing, J., Westover, M.B., Eden, U.T., Stickgold, R., Manoach, D.S., Chu, C.J., 2021. Focal sleep spindle deficits reveal focal thalamocortical dysfunction and predict cognitive deficits in sleep activated developmental epilepsy. The Journal of Neuroscience 41(8), 1816–1829. DOI: 10.1523/JNEUROSCI.2009-20.2020.
McLaren, J.R., Luo, Y., Kwon, H., Shi, W., Kramer, M.A., Chu, C.J., 2023. Preliminary evidence of a relationship between sleep spindles and treatment response in epileptic encephalopathy. Annals of Clinical and Translational Neurology 10(9), 1513–1524. DOI: 10.1002/ACN3.51840.
Mei, N., Grossberg, M.D., Ng, K., Navarro, K.T., Ellmore, T.M., 2017. Identifying sleep spindles with multichannel EEG and classification optimization. Computers in Biology and Medicine 89, 441–448. DOI: 10.1016/J.COMPBIOMED.2017.08.030.
Miao, J., Zhu, W., 2022. Precision–recall curve (PRC) classification trees. Evolutionary Intelligence 15(3), 1545–1569. DOI: 10.1007/s12065-021-00565-2.
Organización Mundial de la Salud, 2025. Epilepsia. Organización Mundial de la Salud. Disponible en: https://www.who.int/es/news-room/fact-sheets/detail/epilepsy
Parekh, A., Selesnick, I.W., Rapoport, D.M., Ayappa, I., 2015. Detection of K-complexes and sleep spindles (DETOKS) using sparse optimization. Journal of Neuroscience Methods 251, 37–46. DOI: 10.1016/j.jneumeth.2015.04.006.
Purcell, M., Manoach, D.S., Demanuele, C., et al., 2017. Characterizing sleep spindles in 11,630 individuals from the National Sleep Research Resource. Nature Communications 8(1), 1–16. DOI: 10.1038/ncomms15930.
Schönauer, M., Pöhlchen, D., 2018. Sleep spindles. Current Biology 28(19), R1129–R1130. DOI: 10.1016/j.cub.2018.07.035.
Shlobin, N.A., Singh, G., Newton, C.R., Sander, J.W., 2021. Classifying epilepsy pragmatically: Past, present, and future. Journal of the Neurological Sciences 427, 117515. DOI: 10.1016/J.JNS.2021.117515.
Tamamoto, Y., Fujie, T., Umimoto, K., Nakamura, H., 2024. Factors affecting discrepancies between scorers in manual sleep spindle detections in single-channel electroencephalography in young adult males. Frontiers in Sleep 3. DOI: 10.3389/frsle.2024.1427540.
Wendt, S.L., Welinder, P., Sorensen, H.B.D., Peppard, P.E., Jennum, P., Perona, P., Mignot, E., Warby, S.C., 2015. Inter-expert and intra-expert reliability in sleep spindle scoring. Clinical Neurophysiology 126(8), 1548–1556. DOI: 10.1016/j.clinph.2014.10.158.
Wirrell, E.C., Nabbout, R., Scheffer, I.E., et al., 2022. Methodology for classification and definition of epilepsy syndromes with list of syndromes: Report of the ILAE task force on nosology and definitions. Epilepsia 63(6), 1333–1348. DOI: 10.1111/EPI.17237.
Zhang, W., Xin, M., Song, G., Liang, J., 2023. Childhood absence epilepsy patients with cognitive impairment have decreased sleep spindle density. Sleep Medicine 103, 89–97. DOI: 10.1016/j.sleep.2023.01.012.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Cristina Montserrat-Font, Paula Romano-Romeo, Jan Pinyol-Pont, Mónica Vicente-Rasoamalala, Miguel A. Mañanas, Sergio Romero
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
