{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T18:03:51Z","timestamp":1790359431747,"version":"4.1.0"},"reference-count":50,"publisher":"Wiley","issue":"12","license":[{"start":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T00:00:00Z","timestamp":1698192000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Epilepsia"],"published-print":{"date-parts":[[2023,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Wrist\u2010 or ankle\u2010worn devices are less intrusive than the widely used electroencephalographic (EEG) systems for monitoring epileptic seizures. Using custom\u2010developed deep\u2010learning seizure detection models, we demonstrate the detection of a broad range of seizure types by wearable signals.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients admitted to the epilepsy monitoring unit were enrolled and asked to wear wearable sensors on either wrists or ankles. We collected patients' electrodermal activity, accelerometry (ACC), and photoplethysmography, from which blood volume pulse (BVP) is derived. Board\u2010certified epileptologists determined seizure onset, offset, and types using video and EEG recordings per the International League Against Epilepsy 2017 classification. We applied three neural network models\u2014a convolutional neural network (CNN) and a CNN\u2013long short\u2010term memory (LSTM)\u2010based generalized detection model and an autoencoder\u2010based personalized detection model\u2014to the raw time\u2010series sensor data to detect seizures and utilized performance measures, including sensitivity, false positive rate (the number of false alarms divided by the total number of nonseizure segments), number of false alarms per day, and detection delay. We applied a 10\u2010fold patientwise cross\u2010validation scheme to the multisignal biosensor data and evaluated model performance on 28 seizure types.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We analyzed 166 patients (47.6% female, median age\u2009=\u200910.0\u2009years) and 900 seizures (13\u2009254\u2009h of sensor data) for 28 seizure types. With a CNN\u2010LSTM\u2010based seizure detection model, ACC, BVP, and their fusion performed better than chance; ACC and BVP data fusion reached the best detection performance of 83.9% sensitivity and 35.3% false positive rate. Nineteen of 28 seizure types could be detected by at least one data modality with area under receiver operating characteristic curve\u2009&gt;\u2009.8 performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Significance<\/jats:title>\n                    <jats:p>Results from this in\u2010hospital study contribute to a paradigm shift in epilepsy care that entails noninvasive seizure detection, provides time\u2010sensitive and accurate data on additional clinical seizure types, and proposes a novel combination of an out\u2010of\u2010the\u2010box monitoring algorithm with an individualized person\u2010oriented seizure detection approach.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/epi.17774","type":"journal-article","created":{"date-parts":[[2023,9,16]],"date-time":"2023-09-16T00:25:21Z","timestamp":1694823921000},"page":"3213-3226","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":59,"title":["Artificial intelligence\u2010enhanced epileptic seizure detection by wearables"],"prefix":"10.1111","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7428-2600","authenticated-orcid":false,"given":"Shuang","family":"Yu","sequence":"first","affiliation":[{"name":"IBM Australia  Melbourne Victoria Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5600-1120","authenticated-orcid":false,"given":"Rima","family":"El\u00a0Atrache","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5440-0796","authenticated-orcid":false,"given":"Jianbin","family":"Tang","sequence":"additional","affiliation":[{"name":"IBM Australia  Melbourne Victoria Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9869-7333","authenticated-orcid":false,"given":"Michele","family":"Jackson","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adam","family":"Makarucha","sequence":"additional","affiliation":[{"name":"IBM Australia  Melbourne Victoria Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sarah","family":"Cantley","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8059-9388","authenticated-orcid":false,"given":"Theodore","family":"Sheehan","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5532-8690","authenticated-orcid":false,"given":"Solveig","family":"Vieluf","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeffrey L.","family":"Rogers","sequence":"additional","affiliation":[{"name":"Digital Health, IBM T. J. Watson Research Center  Yorktown Heights New York USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iven","family":"Mareels","sequence":"additional","affiliation":[{"name":"IBM Australia  Melbourne Victoria Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7947-330X","authenticated-orcid":false,"given":"Stefan","family":"Harrer","sequence":"additional","affiliation":[{"name":"IBM Australia  Melbourne Victoria Australia"},{"name":"Digital Health Cooperative Research Centre  Melbourne Victoria Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2074-0674","authenticated-orcid":false,"given":"Tobias","family":"Loddenkemper","sequence":"additional","affiliation":[{"name":"Boston Children's Hospital and Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,10,25]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(18)30038-3"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2014.06.023"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2021.108383"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eplepsyres.2019.02.007"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.13083"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.13899"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/abef8a"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.14049"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16967"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2019.02.018"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.13670"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2018.05.013"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1097\/WNP.0000000000000316"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"RoyS Kiral\u2010KornekI HarrerS.ChronoNet: a deep recurrent neural network for abnormal EEG identification. In: AIME.2019.","DOI":"10.1007\/978-3-030-21642-9_8"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01199"},{"key":"e_1_2_9_18_1","first-page":"355","article-title":"Emotion recognition based on EEG using LSTM recurrent neural network","volume":"8","author":"Alhagry S","year":"2017","journal-title":"Int J Adv Comput Sci Appl"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2959234"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103919"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.014"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098052"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"e_1_2_9_24_1","first-page":"5593","article-title":"Using wearable sensors for semiology\u2010independent seizure detection \u2010 towards ambulatory monitoring of epilepsy","volume":"2015","author":"Heldberg BE","year":"2015","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10286-018-0568-1"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2012.03444.x"},{"issue":"70","key":"e_1_2_9_27_1","first-page":"2079","article-title":"On over\u2010fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley GC","year":"2010","journal-title":"J Machine Learn Res"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"GarbarinoM LaiM BenderD PicardRW TognettiS.Empatica E3 \u2014 a wearable wireless multi\u2010sensor device for real\u2010time computerized biofeedback and data acquisition. In:2014 4th International Conference on Wireless Mobile Communication and Healthcare \u2010 Transforming Healthcare Through Innovations in Mobile and Wireless Technologies (MOBIHEALTH);2014. p. 39\u201342.","DOI":"10.4108\/icst.mobihealth.2014.257418"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16818"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2016.08.004"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2016.06.008"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1097\/WNP.0b013e3182051320"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.17297"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/s17102338"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2009.2038487"},{"key":"e_1_2_9_36_1","unstructured":"HoutaS BisginP DulichP.Machine learning methods for detection of epileptic seizures with long\u2010term wearable devices.2019."},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"NazeS TangJ KozloskiJR HarrerS.Features importance in seizure classification using scalp EEG reduced to single timeseries. In:2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC);2021. p. 329\u2013332.","DOI":"10.1109\/EMBC46164.2021.9630398"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2017.11.032"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16719"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-01449-2"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16343"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000004893"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2011.01.019"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.12120"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1586\/17434440.2014.947274"},{"key":"e_1_2_9_46_1","first-page":"4184","article-title":"Feature extraction with stacked autoencoders for epileptic seizure detection","volume":"2014","author":"Supratak A","year":"2014","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113788"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106542"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104016"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2864306"},{"key":"e_1_2_9_51_1","volume-title":"Advances in neural information processing systems [internet]","author":"Yoon J","year":"2019"}],"container-title":["Epilepsia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/epi.17774","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T07:07:00Z","timestamp":1721459220000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/epi.17774"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,25]]},"references-count":50,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2023,12]]}},"alternative-id":["10.1111\/epi.17774"],"URL":"https:\/\/doi.org\/10.1111\/epi.17774","archive":["Portico"],"relation":{},"ISSN":["0013-9580","1528-1167"],"issn-type":[{"value":"0013-9580","type":"print"},{"value":"1528-1167","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,25]]},"assertion":[{"value":"2023-04-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-09-14","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-10-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}