{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T16:24:33Z","timestamp":1790699073914,"version":"4.1.0"},"reference-count":28,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T00:00:00Z","timestamp":1742774400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Epilepsia"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Seizure detection in epilepsy monitoring units (EMUs) is essential for the clinical assessment of drug\u2010resistant epilepsy. Automated video analysis using machine learning provides a promising aid for seizure detection, with resultant reduction in the resources required for diagnostic monitoring. We employ a three\u2010dimensional (3D) convolutional neural network with fully fine\u2010tuned backbone layers to identify seizures from EMU videos.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A two\u2010stream inflated 3D\u2010ConvNet architecture (I3D) classified video clips as a seizure or not a seizure. A pretrained action classifier was fine\u2010tuned on 11\u2009h of video containing 49 tonic\u2013clonic seizures from 25 patients monitored at a large academic hospital (site A) using leave\u2010one\u2010patient\u2010out cross\u2010validation. Performance was evaluated by comparing model predictions to ground\u2010truth annotations obtained from video\u2010electroencephalographic review by an epileptologist on videos from site A and a separate dataset from a second large academic hospital (site B).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The model achieved a leave\u2010one\u2010patient\u2010out cross\u2010validation F1\u2010score of .960\u2009\u00b1\u2009.007 (mean\u2009\u00b1\u2009SD) and area under the receiver operating curve score of .988\u2009\u00b1\u2009.004 at site A. Evaluation on full videos detected all seizures (95% binomial exact confidence interval\u2009=\u200994.1%\u2013100%), with median detection latency of 0.0 s (interquartile range = 0.0\u20133.0) from seizure onset. The site A model had an average false alarm rate of 1.81 alarms per hour, although 36 of the 49 videos (73.5%) had no false alarms. Evaluation at site B demonstrated generalizability of the architecture and training strategy, although cross\u2010site evaluation (site A model tested on site B data and vice versa) resulted in diminished performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Significance<\/jats:title>\n                    <jats:p>Our model demonstrates high performance in the detection of epileptic seizures from video data using a fine\u2010tuned I3D model and outperforms similar models identified in the literature. This study provides a foundation for future work in real\u2010time EMU seizure monitoring and possibly for reliable, cost\u2010effective at\u2010home detection of tonic\u2013clonic seizures.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/epi.18381","type":"journal-article","created":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T18:39:52Z","timestamp":1742927992000},"page":"2495-2506","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Video\u2010based detection of tonic\u2013clonic seizures using a three\u2010dimensional convolutional neural network"],"prefix":"10.1111","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0786-4440","authenticated-orcid":false,"given":"Aidan","family":"Boyne","sequence":"first","affiliation":[{"name":"Department of Neurology Baylor College of Medicine  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsiang J.","family":"Yeh","sequence":"additional","affiliation":[{"name":"Department of Neurology University of California, Los Angeles  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony K.","family":"Allam","sequence":"additional","affiliation":[{"name":"Department of Neurology Baylor College of Medicine  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brandon M.","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Neurology Baylor College of Medicine  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Tabaeizadeh","sequence":"additional","affiliation":[{"name":"Department of Neurology University of California, Los Angeles  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3549-1642","authenticated-orcid":false,"given":"John M.","family":"Stern","sequence":"additional","affiliation":[{"name":"Department of Neurology University of California, Los Angeles  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. James","family":"Cotton","sequence":"additional","affiliation":[{"name":"Shirley Ryan Ability Lab  Chicago Illinois USA"},{"name":"Department of Physical Medicine and Rehabilitation Northwestern University  Chicago Illinois USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zulfi","family":"Haneef","sequence":"additional","affiliation":[{"name":"Department of Neurology Baylor College of Medicine  Houston Texas USA"},{"name":"Neurology Care Line Michael E. DeBakey Veterans Affairs Medical Center  Houston Texas USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,3,24]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2018.00639"},{"issue":"5","key":"e_1_2_12_3_1","article-title":"Challenges and prospects in epilepsy monitoring units: a comprehensive review of logistic barriers","volume":"16","author":"Albarrak A","year":"2024","journal-title":"Cureus"},{"issue":"4","key":"e_1_2_12_4_1","first-page":"491","article-title":"The power of ECG in semi\u2010automated seizure detection in addition to Two\u2010Channel behind\u2010the\u2010ear EEG","volume":"10","author":"Bhagubai M","year":"2023","journal-title":"Bioeng Basel Switz"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2015.2462079"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2016.01.003"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2012.6346955"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/459636"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2215609"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.14050"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2006.00571.x"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-23133-9"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3049649"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.17605"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2016.1141062"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87240-3_32"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.17926"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_2_12_19_1","article-title":"The kinetics human action video dataset","author":"Kay W","year":"2017","journal-title":"arXiv"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_12_21_1","unstructured":"MMAciton2 Contributors.Action Recognition Models.2020.https:\/\/mmaction2.readthedocs.io\/en\/latest\/model_zoo\/recognition.html#I3D"},{"key":"e_1_2_12_22_1","unstructured":"MMAction2 Contributors.OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark.2020.https:\/\/github.com\/open\u2010mmlab\/mmaction2"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16818"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2018.02.010"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2012.08.005"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2024.109735"},{"key":"e_1_2_12_27_1","unstructured":"McMahanHB MooreE RamageD HampsonS ArcasBA.Communication\u2010efficient learning of deep networks from decentralized data.arXiv.2016.https:\/\/arxiv.org\/abs\/1602.05629v4"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23020968"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1002\/brb3.2737"}],"container-title":["Epilepsia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/epi.18381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,9]],"date-time":"2025-11-09T09:07:47Z","timestamp":1762679267000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/epi.18381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,24]]},"references-count":28,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1111\/epi.18381"],"URL":"https:\/\/doi.org\/10.1111\/epi.18381","archive":["Portico"],"relation":{},"ISSN":["0013-9580","1528-1167"],"issn-type":[{"value":"0013-9580","type":"print"},{"value":"1528-1167","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,24]]},"assertion":[{"value":"2025-01-09","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-10","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}