{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T07:21:45Z","timestamp":1792135305917,"version":"4.4.0"},"reference-count":42,"publisher":"Society for Neuroscience","issue":"10","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":182,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"name":"CURE Epilepsy Award"},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R21NS122011"],"award-info":[{"award-number":["R21NS122011"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K08NS105929"],"award-info":[{"award-number":["K08NS105929"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["eneuro.org"],"crossmark-restriction":true},"short-container-title":["eNeuro"],"accepted":{"date-parts":[[2025,9,22]]},"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:p>Sleep\u2013wake states bidirectionally interact with epilepsy and seizures, but the mechanisms are unknown. A barrier to comprehensive characterization and the study of mechanisms has been the difficulty of annotating large chronic recording datasets. To overcome this barrier, we sought to develop an automated method of classifying sleep\u2013wake states, seizures, and the postictal state in mice ranging from controls to mice with severe epilepsy with accompanying background electroencephalographic (EEG) abnormalities. We utilized a large dataset of recordings, including electromyogram, EEG, and hippocampal local field potentials, from control and intra-amygdala kainic acid-treated mice. We found that an existing sleep\u2013wake classifier performed poorly, even after retraining. A support vector machine, relying on typically used scoring parameters, also performed below our benchmark. We then trained and evaluated several multilayer neural network architectures and found that a bidirectional long short-term memory\u2013based model performed best. This \u201cSleep\u2013Wake and Ictal State Classifier\u201d (SWISC) showed high agreement between ground-truth and classifier scores for all sleep and seizure states in an unseen and unlearned epileptic dataset (average agreement 96.41%\u2009\u00b1\u2009SD 3.80%) and saline animals (97.77\u2009\u00b1\u20091.40%). Channel dropping showed that SWISC was primarily dependent on hippocampal signals yet still maintained good performance (\u223c90% agreement) with EEG alone, thereby expanding the classifier's applicability to other epilepsy datasets. SWISC enables the efficient combined scoring of sleep\u2013wake and seizure states in mouse models of epilepsy and healthy controls, facilitating comprehensive and mechanistic studies of sleep\u2013wake and biological rhythms in epilepsy.<\/jats:p>","DOI":"10.1523\/eneuro.0226-25.2025","type":"journal-article","created":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:50:19Z","timestamp":1759945819000},"page":"ENEURO.0226-25.2025","update-policy":"https:\/\/doi.org\/10.1523\/eneuro.crossmarkpolicy","source":"Crossref","is-referenced-by-count":3,"title":["Automated Classification of Sleep\u2013Wake States and Seizures in Mice"],"prefix":"10.1523","volume":"12","author":[{"given":"Brandon J.","family":"Harvey","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Viktor J.","family":"Olah","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lauren M.","family":"Aiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucie I.","family":"Rosenberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Danny J.","family":"Lasky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Moxon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nigel P.","family":"Pedersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"393","published-online":{"date-parts":[[2025,10,8]]},"reference":[{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.1","unstructured":"Abadi M , et al. (2015) TensorFlow: large-scale machine learning on heterogeneous systems. Software available from https:\/\/tensorflow.org\/"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.2","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.yebeh.2016.09.031","article-title":"Distinct behavioral and epileptic phenotype differences in 129\/P mice compared to C57BL\/6 mice subject to intraamygdala kainic acid-induced status epilepticus","volume":"64","author":"Almeida Silva","year":"2016","journal-title":"Epilepsy Behav"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0224642"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.4","doi-asserted-by":"crossref","first-page":"S3","DOI":"10.1111\/epi.17664","article-title":"Sleep, oscillations, and epilepsy","volume":"64","author":"Bernard","year":"2023","journal-title":"Epilepsia"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.5","unstructured":"Chollet F (2015) Keras. Software available from https:\/\/keras.io"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.6","doi-asserted-by":"publisher","DOI":"10.1177\/001316446002000104"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.7","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16714"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.8","doi-asserted-by":"publisher","DOI":"10.1016\/S0165-0270(03)00229-2"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.9","doi-asserted-by":"publisher","DOI":"10.1162\/15324430260185628"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.10","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1157.1998.tb01352.x"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.11","unstructured":"Dozat T (2016) Incorporating nesterov momentum into adam. In: International Conference on Learning Representations Workshops."},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.12","doi-asserted-by":"crossref","first-page":"zsz272","DOI":"10.1093\/sleep\/zsz272","article-title":"Supervised and unsupervised machine learning for automated scoring of sleep-wake and cataplexy in a mouse model of narcolepsy","volume":"43","author":"Exarchos","year":"2020","journal-title":"Sleep"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.13","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1145\/301631.301661","article-title":"A fast Fourier transform compiler","volume":"34","author":"Frigo","year":"1999","journal-title":"ACM SIGPLAN Not"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.14","doi-asserted-by":"crossref","unstructured":"Graves A , Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM networks. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, Vol. 4. pp 2047\u20132052.","DOI":"10.1109\/IJCNN.2005.1556215"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-91286-0"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.16","doi-asserted-by":"publisher","DOI":"10.1016\/S0006-8993(99)02452-X"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.17","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.18","doi-asserted-by":"publisher","DOI":"10.4196\/kjpp.2019.23.2.131"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1157.1962.tb05235.x"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.20","doi-asserted-by":"publisher","DOI":"10.1002\/hipo.22838"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2020.108834"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2015.03.007"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.23","doi-asserted-by":"crossref","first-page":"43","DOI":"10.3389\/fnsys.2020.00043","article-title":"EEG-based emotion classification using a deep neural network and sparse autoencoder","volume":"14","author":"Liu","year":"2020","journal-title":"Front Syst Neurosci"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.24","doi-asserted-by":"publisher","DOI":"10.1093\/sleep\/32.2.139"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.25","unstructured":"NVIDIA , Vingelmann P , Fitzek FHP (2021). CUDA, release: 11.2.2. Available at: https:\/\/developer.nvidia.com\/cuda-toolkit ."},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.26","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"JMLR"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.27","unstructured":"Pitk\u00e4nen A , Buckmaster PS , Galanopoulou AS , Mosh\u00e9 SL (2017) Models of seizures and epilepsy , Ed 2. London, United Kingdom: Elsevier Inc."},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.28","doi-asserted-by":"publisher","DOI":"10.1111\/ejn.15884"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.29","unstructured":"Rechtschaffen A , Kales A (1968) A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects . Washington, DC: United States Government Printing Office."},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2011.08.023"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.31","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1038\/s41582-025-01064-z","article-title":"Mechanistic insights into the interaction between epilepsy and sleep","volume":"21","author":"Sheybani","year":"2025","journal-title":"Nat Rev Neurol"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.32","doi-asserted-by":"publisher","DOI":"10.1016\/0014-4886(82)90086-3"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.33","doi-asserted-by":"publisher","DOI":"10.1016\/j.expneurol.2024.114860"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.34","doi-asserted-by":"crossref","first-page":"3786","DOI":"10.3390\/s21113786","article-title":"A review of EEG signal features and their application in driver drowsiness detection systems","volume":"21","author":"Stancin","year":"2021","journal-title":"Sensors"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.35","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16651"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.36","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aa8069"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.37","first-page":"261","article-title":"The support vector method","volume-title":"Artificial neural networks \u2014 ICANN'97. ICANN 1997. Lecture notes in computer science","volume":") Vol. 1327","author":"Vapnik","year":"1997"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.38","doi-asserted-by":"crossref","unstructured":"Wei L , Gerbatin R , Mamad O , Boutouil H , Reschke C , Lowery M , Henshall D , Morris G , Mooney C (2020) XGboost-based method for seizure detection in mouse models of epilepsy. 2020 IEEE Signal Processing in Medicine and Biology Symposium (SPMB):1\u20133. https:\/\/doi.org\/10.1109\/SPMB50085.2020.9353632","DOI":"10.1109\/SPMB50085.2020.9353632"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.39","doi-asserted-by":"crossref","first-page":"056060","DOI":"10.1088\/1741-2552\/ac2ca0","article-title":"Detection of spontaneous seizures in EEGs in multiple experimental mouse models of epilepsy","volume":"18","author":"Wei","year":"2021","journal-title":"J Neural Eng"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.40","doi-asserted-by":"crossref","first-page":"fcaa036","DOI":"10.1093\/braincomms\/fcaa036","article-title":"Kurtosis and skewness of high-frequency brain signals are altered in paediatric epilepsy","volume":"2","author":"Xiang","year":"2020","journal-title":"Brain Commun"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.41","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-40055-1"},{"key":"2025102810551227000_12.10.ENEURO.0226-25.2025.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2019.108566"}],"container-title":["eneuro"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1523\/ENEURO.0226-25.2025","content-type":"unspecified","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1523\/ENEURO.0226-25.2025","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T17:55:20Z","timestamp":1761674120000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.eneuro.org\/lookup\/doi\/10.1523\/ENEURO.0226-25.2025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,28]]},"published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1523\/ENEURO.0226-25.2025"],"URL":"https:\/\/doi.org\/10.1523\/eneuro.0226-25.2025","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2023.04.07.536063","asserted-by":"object"}]},"ISSN":["2373-2822"],"issn-type":[{"value":"2373-2822","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}