{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:56:21Z","timestamp":1784800581599,"version":"3.55.0"},"reference-count":57,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T00:00:00Z","timestamp":1730678400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["R01NS104322"],"award-info":[{"award-number":["R01NS104322"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000065","name":"National Institute of Neurological Disorders and Stroke","doi-asserted-by":"publisher","award":["K23NS105198"],"award-info":[{"award-number":["K23NS105198"]}],"id":[{"id":"10.13039\/100000065","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005595","name":"University of California","doi-asserted-by":"publisher","award":["7503781"],"award-info":[{"award-number":["7503781"]}],"id":[{"id":"10.13039\/100005595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Epilepsia"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>This study was undertaken to develop a machine learning (ML) model to forecast initial seizure onset in neonatal hypoxic\u2013ischemic encephalopathy (HIE) utilizing clinical and quantitative electroencephalogram (QEEG) features.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We developed a gradient boosting ML model (Neo\u2010GB) that utilizes clinical features and QEEG to forecast time\u2010dependent seizure risk. Clinical variables included cord blood gas values, Apgar scores, gestational age at birth, postmenstrual age (PMA), postnatal age, and birth weight. QEEG features included statistical moments, spectral power, and recurrence quantification analysis (RQA) features. We trained and evaluated Neo\u2010GB on a University of California, San Francisco (UCSF) neonatal HIE dataset, augmenting training with publicly available neonatal electroencephalogram (EEG) datasets from Cork University and Helsinki University Hospitals. We assessed the performance of Neo\u2010GB at providing dynamic and static forecasts with diagnostic performance metrics and incident\/dynamic area under the receiver operating characteristic curve (iAUC) analyses. Model explanations were performed to assess contributions of QEEG features and channels to model predictions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The UCSF dataset included 60 neonates with HIE (30 with seizures). In subject\u2010level static forecasting at 30\u2009min after EEG initiation, baseline Neo\u2010GB without time\u2010dependent features had an area under the receiver operating characteristic curve (AUROC) of .76 and Neo\u2010GB with time\u2010dependent features had an AUROC of .89. In time\u2010dependent evaluation of the initial seizure onset within a 24\u2010h seizure occurrence period, dynamic forecast with Neo\u2010GB demonstrated median iAUC = .79 (interquartile range [IQR] .75\u2013.82) and concordance index (C\u2010index) = .82, whereas baseline static forecast at 30\u2009min demonstrated median iAUC = .75 (IQR .72\u2013.76) and C\u2010index = .69. Model explanation analysis revealed that spectral power, PMA, RQA, and cord blood gas values made the strongest contributions in driving Neo\u2010GB predictions. Within the most influential EEG channels, as the preictal period advanced toward eventual seizure, there was an upward trend in broadband spectral power.<\/jats:p><\/jats:sec><jats:sec><jats:title>Significance<\/jats:title><jats:p>This study demonstrates an ML model that combines QEEG with clinical features to forecast time\u2010dependent risk of initial seizure onset in neonatal HIE. Spectral power evolution is an early EEG marker of seizure risk in neonatal HIE.<\/jats:p><\/jats:sec>","DOI":"10.1111\/epi.18163","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T13:59:43Z","timestamp":1730728783000},"page":"89-103","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Machine learning for forecasting initial seizure onset in neonatal hypoxic\u2013ischemic encephalopathy"],"prefix":"10.1111","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1077-2963","authenticated-orcid":false,"given":"Danilo","family":"Bernardo","sequence":"first","affiliation":[{"name":"Department of Neurology and Weill Institute for Neurosciences University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Neurology and Neurological Sciences Stanford University  Palo Alto California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5233-0800","authenticated-orcid":false,"given":"Marie\u2010Coralie","family":"Cornet","sequence":"additional","affiliation":[{"name":"Department of Pediatrics University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1594-9812","authenticated-orcid":false,"given":"Adam L.","family":"Numis","sequence":"additional","affiliation":[{"name":"Department of Neurology and Weill Institute for Neurosciences University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron","family":"Scheffler","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6389-2638","authenticated-orcid":false,"given":"Vikram R.","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Neurology and Weill Institute for Neurosciences University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edilberto","family":"Amorim","sequence":"additional","affiliation":[{"name":"Department of Neurology and Weill Institute for Neurosciences University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3879-1966","authenticated-orcid":false,"given":"Hannah C.","family":"Glass","sequence":"additional","affiliation":[{"name":"Department of Neurology and Weill Institute for Neurosciences University of California, San Francisco  San Francisco California USA"},{"name":"Department of Pediatrics University of California, San Francisco  San Francisco California USA"},{"name":"Department of Epidemiology and Biostatistics University of California, San Francisco  San Francisco California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,11,4]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.physd.2004.02.013"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1155\/2014\/295070"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.1212\/01.wnl.0000279335.85797.2c"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.siny.2018.02.001"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra2300188"},{"key":"e_1_2_12_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.14671"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000207202"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM199908123410704"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pediatrneurol.2020.08.002"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1203\/PDR.0b013e31822f24c7"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2016.03.035"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000012293"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41390-018-0242-2"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1136\/adc.2004.068551"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41390-018-0040-x"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000000282"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1097\/WNP.0000000000000574"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.17468"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00004-3"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.97.4.456"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2005-1524"},{"key":"e_1_2_12_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pediatrneurol.2016.10.019"},{"key":"e_1_2_12_24_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2011.03401.x"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000006548"},{"key":"e_1_2_12_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41582-021-00464-1"},{"key":"e_1_2_12_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(20)30396-3"},{"key":"e_1_2_12_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(13)70075-9"},{"key":"e_1_2_12_29_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16418"},{"key":"e_1_2_12_30_1","first-page":"S72","article-title":"Seizure forecasting: bifurcations in the long and winding road","volume":"64","author":"Baud MO","year":"2022","journal-title":"Epilepsia"},{"key":"e_1_2_12_31_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.16541"},{"key":"e_1_2_12_32_1","first-page":"252","article-title":"Risk of seizures in neonates with hypoxic\u2010ischemic encephalopathy receiving hypothermia plus erythropoietin or placebo","volume":"1","author":"Glass HC","year":"2022","journal-title":"Pediatr Res"},{"key":"e_1_2_12_33_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0b013e31820af91a"},{"key":"e_1_2_12_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpeds.2011.07.015"},{"key":"e_1_2_12_35_1","doi-asserted-by":"publisher","DOI":"10.1159\/000486820"},{"key":"e_1_2_12_36_1","doi-asserted-by":"publisher","DOI":"10.1097\/WNP.0b013e3182872b24"},{"key":"e_1_2_12_37_1","doi-asserted-by":"publisher","DOI":"10.1111\/epi.13661"},{"key":"e_1_2_12_38_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2019.39"},{"key":"e_1_2_12_39_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02002-8"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.pediatrneurol.2004.09.014"},{"key":"e_1_2_12_41_1","article-title":"Exploration of short\u2010range neonatal seizure forecasting with quantitative EEG based deep learning","author":"Kim J","year":"2023","journal-title":"medRxiv"},{"key":"e_1_2_12_42_1","unstructured":"PayneDE ChambersJD BurkittA CookMJ KuhlmanL FreestoneDR et\u00a0al.Epileptic seizure forecasting with long short\u2010term memory (LSTM) neural networks. arXiv preprint arXiv:230909471.2023."},{"key":"e_1_2_12_43_1","doi-asserted-by":"crossref","unstructured":"ChenT GuestrinC editors.Xgboost: A scalable tree boosting system2016.2016.","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_12_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2015.03.010"},{"key":"e_1_2_12_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eplepsyres.2011.07.012"},{"key":"e_1_2_12_46_1","doi-asserted-by":"crossref","unstructured":"AkibaT SanoS YanaseT OhtaT KoyamaM editors.Optuna: A next\u2010generation hyperparameter optimization framework2019.2019.","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_12_47_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.2005.030814.x"},{"key":"e_1_2_12_48_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.2000.00337.x"},{"key":"e_1_2_12_49_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.1982.03320430047030"},{"key":"e_1_2_12_50_1","first-page":"1","article-title":"The R package geepack for generalized estimating equations","volume":"15","author":"H\u00f8jsgaard S","year":"2006","journal-title":"J Stat Softw"},{"key":"e_1_2_12_51_1","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg SM","year":"2017","journal-title":"Adv Neural Inf Proces Syst"},{"key":"e_1_2_12_52_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.26301"},{"key":"e_1_2_12_53_1","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000002090"},{"key":"e_1_2_12_54_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2019.4656"},{"key":"e_1_2_12_55_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2017.2459"},{"key":"e_1_2_12_56_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaneurol.2021.1437"},{"key":"e_1_2_12_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2017.03.002"},{"key":"e_1_2_12_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(22)00029-2"}],"container-title":["Epilepsia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/epi.18163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T06:30:44Z","timestamp":1741761044000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/epi.18163"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,4]]},"references-count":57,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1111\/epi.18163"],"URL":"https:\/\/doi.org\/10.1111\/epi.18163","archive":["Portico"],"relation":{},"ISSN":["0013-9580","1528-1167"],"issn-type":[{"value":"0013-9580","type":"print"},{"value":"1528-1167","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,4]]},"assertion":[{"value":"2023-08-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}