{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:27:08Z","timestamp":1778549228221,"version":"3.51.4"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T00:00:00Z","timestamp":1710460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0\u201380\u2009years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic\u2013clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for &amp;gt;10\u2009s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (&amp;gt;10\u2009s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (<jats:italic>n<\/jats:italic>\u2009=\u200981 subjects with seizures) and false detection rate (FDR) (<jats:italic>n<\/jats:italic>\u2009=\u2009all 230 subjects).<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR\/h (CI): tonic\u2013clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR\/h.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fninf.2024.1324981","type":"journal-article","created":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T04:59:35Z","timestamp":1710478775000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence"],"prefix":"10.3389","volume":"18","author":[{"given":"Pragya","family":"Rai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Knight","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matias","family":"Hiillos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Csaba","family":"Kert\u00e9sz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elizabeth","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniella","family":"Terney","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidsel Armand","family":"Larsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim","family":"\u00d8sterkjerhuus","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jukka","family":"Peltola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e1ndor","family":"Beniczky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,3,15]]},"reference":[{"key":"ref1","article-title":"Deep learning approaches for seizure video analysis: a review","author":"Ahmedt-Aristizabal","year":"2023","journal-title":"arXiv"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e135","DOI":"10.1111\/epi.17001","article-title":"Value of smartphone videos for diagnosis of seizures: everyone owns half an epilepsy monitoring unit","volume":"62","author":"Amin","year":"2021","journal-title":"Epilepsia"},{"key":"ref3","first-page":"875","article-title":"Chapter 93-psychogenic nonepileptic seizures","volume-title":"Handbook of clinical neurology [internet]","author":"Anne","year":"2013"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.yebeh.2016.06.008","article-title":"Diagnostic accuracy of audio-based seizure detection in patients with severe epilepsy and an intellectual disability","volume":"62","author":"Arends","year":"2016","journal-title":"Epilepsy Behav."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e2737","DOI":"10.1002\/brb3.2737","article-title":"Automated detection of nocturnal motor seizures using an audio-video system","volume":"12","author":"Armand Larsen","year":"2022","journal-title":"Brain Behav."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"108804","DOI":"10.1016\/j.yebeh.2022.108804","article-title":"Clinical utility of a video\/audio-based epilepsy monitoring system Nelli","volume":"133","author":"Basnyat","year":"2022","journal-title":"Epilepsy Behav."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/S1474-4422(18)30454-X","article-title":"Global, regional, and national burden of epilepsy, 1990\u20132016: a systematic analysis for the global burden of disease study 2016","volume":"18","author":"Beghi","year":"2019","journal-title":"Lancet Neurol."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1097\/WCO.0000000000000658","article-title":"Non-electroencephalography-based seizure detection","volume":"32","author":"Beniczky","year":"2019","journal-title":"Curr. Opin. Neurol."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1298","DOI":"10.1111\/epi.13799","article-title":"The new ILAE seizure classification: 63 seizure types?","volume":"58","author":"Beniczky","year":"2017","journal-title":"Epilepsia"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1111\/epi.14049","article-title":"Standards for testing and clinical validation of seizure detection devices","volume":"59","author":"Beniczky","year":"2018","journal-title":"Epilepsia"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1111\/epi.16818","article-title":"Automated seizure detection using wearable devices: a clinical practice guideline of the international league against epilepsy and the International Federation of Clinical Neurophysiology","volume":"62","author":"Beniczky","year":"2021","journal-title":"Epilepsia"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.compbiomed.2016.11.010","article-title":"Monitoring infants by automatic video processing: a unified approach to motion analysis","volume":"80","author":"Cattani","year":"2017","journal-title":"Comput. Biol. Med."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1109\/TBME.2011.2178094","article-title":"Automated algorithm for generalized tonic\u2013Clonic epileptic seizure onset detection based on sEMG zero-crossing rate","volume":"59","author":"Conradsen","year":"2012","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref14","doi-asserted-by":"crossref","first-page":"4454","DOI":"10.1109\/EMBC.2012.6346955","article-title":"Using spatio-temporal interest points (STIP) for myoclonic jerk detection in nocturnal video","volume-title":"2012 annual international conference of the IEEE engineering in medicine and biology society","author":"Cuppens","year":"2012"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1111\/epi.16630","article-title":"A new era in electroencephalographic monitoring? Subscalp devices for ultra-long-term recordings","volume":"61","author":"Duun-Henriksen","year":"2020","journal-title":"Epilepsia"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/S1474-4422(18)30038-3","article-title":"Diagnostic challenges in epilepsy: seizure under-reporting and seizure detection","volume":"17","author":"Elger","year":"2018","journal-title":"Lancet Neurol."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1646","DOI":"10.1016\/S0140-6736(13)60899-5","article-title":"Premature mortality in epilepsy and the role of psychiatric comorbidity: a total population study","volume":"382","author":"Fazel","year":"2013","journal-title":"Lancet"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1212\/WNL.0000000000003509","article-title":"Prevalence and incidence of epilepsy","volume":"88","author":"Fiest","year":"2017","journal-title":"Neurology"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1111\/epi.13670","article-title":"Operational classification of seizure types by the international league against epilepsy: position paper of the ILAE Commission for Classification and Terminology","volume":"58","author":"Fisher","year":"2017","journal-title":"Epilepsia"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1111\/epi.17677","article-title":"P. da Silva H. A novel approach to automatic seizure detection using computer vision and independent component analysis","volume":"64","author":"Gar\u00e7\u00e3o","year":"2023","journal-title":"Epilepsia"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"2657","DOI":"10.1001\/jama.2016.18625","article-title":"New-onset seizure in adults and adolescents: a review","volume":"316","author":"Gavvala","year":"2016","journal-title":"JAMA"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1111\/epi.14050","article-title":"Automated video-based detection of nocturnal convulsive seizures in a residential care setting","volume":"59","author":"Geertsema","year":"2018","journal-title":"Epilepsia"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.1001\/archneur.64.11.1595","article-title":"Epilepsy: accuracy of patient seizure counts","volume":"64","author":"Hoppe","year":"2007","journal-title":"Arch. Neurol."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.seizure.2018.12.024","article-title":"Tonic-clonic seizure detection using accelerometry-based wearable sensors: a prospective, video-EEG controlled study","volume":"65","author":"Johansson","year":"2019","journal-title":"Seizure"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"3379","DOI":"10.1109\/TBME.2012.2215609","article-title":"Lopes da Silva F. Automatic segmentation of episodes containing epileptic clonic seizures in video sequences","volume":"59","author":"Kalitzin","year":"2012","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref27","article-title":"Deep learning methods for single camera based clinical in-bed movement action recognition","author":"Kar\u00e1csony","year":"2023","journal-title":"IEEE"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.1016\/j.clinph.2005.12.030","article-title":"Automated detection of videotaped neonatal seizures based on motion segmentation methods","volume":"117","author":"Karayiannis","year":"2006","journal-title":"Clin. Neurophysiol."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1111\/j.1528-1167.2005.56504.x","article-title":"Computerized motion analysis of videotaped neonatal seizures of epileptic origin","volume":"46","author":"Karayiannis","year":"2005","journal-title":"Epilepsia"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/epi.17833","article-title":"Artificial intelligence in epilepsy phenotyping","author":"Knight","year":"2024","journal-title":"Epilepsia"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1111\/j.1528-1167.2009.02397.x","article-title":"Definition of drug resistant epilepsy: consensus proposal by the ad hoc task force of the ILAE commission on therapeutic strategies","volume":"51","author":"Kwan","year":"2010","journal-title":"Epilepsia"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"2005","DOI":"10.1111\/epi.12356","article-title":"Minimum requirements for the diagnosis of psychogenic nonepileptic seizures: a staged approach","volume":"54","author":"LaFrance","year":"2013","journal-title":"Epilepsia"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.yebeh.2014.05.031","article-title":"The consequences of refractory epilepsy and its treatment","volume":"37","author":"Laxer","year":"2014","journal-title":"Epilepsy Behav."},{"key":"ref34","doi-asserted-by":"crossref","first-page":"1041","DOI":"10.1016\/B978-0-323-04743-2.50078-0","article-title":"CHAPTER 76- Seizure Disorders (Epilepsy)","volume-title":"Massachusetts General Hospital Comprehensive clinical psychiatry","author":"Lee","year":"2008"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1109\/TBME.2012.2228649","article-title":"Quantifying limb movements in epileptic seizures through color-based video analysis","volume":"60","author":"Lu","year":"2013","journal-title":"I.E.E.E. Trans. Biomed. Eng."},{"key":"ref36","first-page":"210","article-title":"Privacy-preserving early detection of epileptic seizures in videos","author":"Mehta","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1111\/epi.17492","article-title":"Duration of epileptic seizure types: a data-driven approach","volume":"64","author":"Meritam Larsen","year":"2023","journal-title":"Epilepsia"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1365","DOI":"10.1111\/epi.16550","article-title":"Which seizure elements do patients memorize? A comparison of history and seizure documentation","volume":"61","author":"Mielke","year":"2020","journal-title":"Epilepsia"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/JBHI.2015.2462079","article-title":"Automated detection of tonic\u2013Clonic seizures using 3-D Accelerometry and surface electromyography in pediatric patients","volume":"20","author":"Milo\u0161evi\u0107","year":"2016","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1002\/epi4.12327","article-title":"The utility of an automated and ambulatory device for detecting and differentiating epileptic and psychogenic non-epileptic seizures","volume":"4","author":"Naganur","year":"2019","journal-title":"Epilepsia Open"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"106486","DOI":"10.1016\/j.eplepsyres.2020.106486","article-title":"An integrative method to quantitatively detect nocturnal motor seizures","volume":"169","author":"Ojanen","year":"2021","journal-title":"Epilepsy Res."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1133","DOI":"10.1016\/j.cmpb.2012.08.005","article-title":"Vision-based motion detection, analysis and recognition of epileptic seizures--a systematic review","volume":"108","author":"Pediaditis","year":"2012","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"S65","DOI":"10.1111\/epi.17207","article-title":"Semiautomated classification of nocturnal seizures using video recordings","author":"Peltola","year":"2023","journal-title":"Epilepsia"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1016\/j.clinph.2013.12.119","article-title":"Real-time automated detection of clonic seizures in newborns","volume":"125","author":"Pisani","year":"2014","journal-title":"Clin. Neurophysiol."},{"key":"ref45","doi-asserted-by":"publisher","first-page":"3200","DOI":"10.1109\/TPAMI.2022.3183112","article-title":"Human action recognition from various data modalities: a review","volume":"45","author":"Sun","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref46","doi-asserted-by":"publisher","first-page":"492","DOI":"10.1038\/nrneurol.2009.118","article-title":"Sudden unexpected death in epilepsy: risk factors and potential pathomechanisms","volume":"5","author":"Surges","year":"2009","journal-title":"Nat. Rev. Neurol."},{"key":"ref47","doi-asserted-by":"publisher","first-page":"e419","DOI":"10.1212\/WNL.0000000000008741","article-title":"Clinical risk factors in SUDEP: a nationwide population-based case-control study","volume":"94","author":"Sveinsson","year":"2020","journal-title":"Neurology"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"1432","DOI":"10.1111\/epi.13083","article-title":"Electromyography-based seizure detector: preliminary results comparing a generalized tonic\u2013clonic seizure detection algorithm to video-EEG recordings","volume":"56","author":"Szab\u00f3","year":"2015","journal-title":"Epilepsia"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"1807","DOI":"10.1111\/epi.16967","article-title":"Seizure detection using wearable sensors and machine learning: setting a benchmark","volume":"62","author":"Tang","year":"2021","journal-title":"Epilepsia"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.seizure.2016.06.008","article-title":"Automated seizure detection systems and their effectiveness for each type of seizure","volume":"40","author":"Ulate-Campos","year":"2016","journal-title":"Seizure"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"S36","DOI":"10.1111\/epi.16504","article-title":"Automated video-based detection of nocturnal motor seizures in children","author":"van Westrhenen","year":"2020","journal-title":"Epilepsia"},{"key":"ref52","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1684\/epd.2020.1137","article-title":"The importance of semiological information based on epileptic seizure history","volume":"22","author":"Wolf","year":"2020","journal-title":"Epileptic Disord."}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2024.1324981\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T04:59:40Z","timestamp":1710478780000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2024.1324981\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,15]]},"references-count":51,"alternative-id":["10.3389\/fninf.2024.1324981"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2024.1324981","relation":{},"ISSN":["1662-5196"],"issn-type":[{"value":"1662-5196","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,15]]},"article-number":"1324981"}}