{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T06:24:13Z","timestamp":1787293453991,"version":"build-2736575974"},"reference-count":56,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T00:00:00Z","timestamp":1787270400000},"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. Digit. Health"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and examine a multimodal deep-learning framework utilizing clinical variables with and without time-dependent electroencephalogram (EEG) spectral features for predicting significant neurological injury (SNI) in pediatric patients with extracorporeal membrane oxygenation (ECMO).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Data were collected from 73 pediatric ECMO patients. After excluding patients who had missing or discontinuous temporal data within 72\u2005h after EEG initiation, 43 patients with usable EEG time-series data were analyzed. Neurological injury severity was quantified using a neuroimaging score (NIS) derived from post-cannulation imaging, with SNI defined as NIS\u2009\u2265\u20098. Model inputs included six clinical variables and six EEG features representing relative delta (1\u20134\u2005Hz) and theta (4\u20138\u2005Hz) power from the left, right, and bilateral hemispheres. Down-sampled EEG power signals were segmented into multiple 30-minute windows. A deep-learning fusion framework with modality-specific encoders was developed for SNI prediction, followed by SHapley Additive exPlanations (SHAP)-based feature attribution analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>At the patient level, the proposed multilayer perceptron model used only for clinical variables achieved the highest overall performance with an area under the curve (AUC) of 74.29%. The Wilcoxon signed-rank test was performed and showed no statistical significance in model performance between the clinical-only and fusion model. SHAP analysis indicated that clinical variables were the primary contributors, not the EEG inputs, to SNI prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>A multilayer perceptron neural network used with six clinical inputs demonstrated moderate performance in identifying SNI among pediatric ECMO patients; integration with EEG-derived spectral features did not significantly enhance the performance. However, this conclusion is highly exploratory and dependent on selected EEG inputs, thus needing to be valid with a larger patient cohort, appropriate EEG feature selections, and assess cross-site generalizability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fdgth.2026.1857835","type":"journal-article","created":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:37:09Z","timestamp":1787290629000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploratory deep-learning-driven early risk stratification of significant neurological injury in pediatric extracorporeal membrane oxygenation"],"prefix":"10.3389","volume":"8","author":[{"given":"Haiyang","family":"Tang","sequence":"first","affiliation":[{"name":"Department of Bioengineering, University of Texas at Arlington","place":["Arlington, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Molly","family":"McGetrick","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Division of Cardiology, Heart Center, Children's Health, UT Southwestern Medical Center","place":["Dallas, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Division of Cardiology, Heart Center, Children's Health, UT Southwestern Medical Center","place":["Dallas, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salman","family":"Sohrabi","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Texas at Arlington","place":["Arlington, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lakshmi","family":"Raman","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, UT Southwestern Medical Center","place":["Dallas, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanli","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, University of Texas at Arlington","place":["Arlington, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1016\/j.ccc.2017.06.005","article-title":"Pediatric extracorporeal membrane oxygenation.","volume":"33","author":"Jenks","year":"2017","journal-title":"Crit Care Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1594","DOI":"10.1007\/s00134-013-2985-x","article-title":"Neurologic complications in neonates supported with extracorporeal membrane oxygenation. An analysis of ELSO registry data","volume":"39","author":"Polito","year":"2013","journal-title":"Intensive Care Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1584","DOI":"10.1007\/s00134-013-2973-1","article-title":"Neurodevelopmental, educational and behavioral outcome at 8 years after neonatal ECMO: a nationwide multicenter study","volume":"39","author":"Madderom","year":"2013","journal-title":"Intensive Care Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"760","DOI":"10.1097\/PCC.0000000000001612","article-title":"Neurologic outcomes after extracorporeal membrane oxygenation: a systematic review","volume":"19","author":"Boyle","year":"2018","journal-title":"Pediatr Crit Care Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1097\/MAT.0000000000000933","article-title":"Neurologic outcomes in a two-center cohort of neonatal and pediatric patients supported on extracorporeal membrane oxygenation","volume":"66","author":"Bembea","year":"2020","journal-title":"Asaio J"},{"key":"B6","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1177\/0883073808330765","article-title":"Neurologic outcome at school entry for newborns treated with extracorporeal membrane oxygenation for noncardiac indications","volume":"24","author":"Waitzer","year":"2009","journal-title":"J Child Neurol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1007\/s12028-023-01836-9","article-title":"Neurophysiologic features reflecting brain injury during pediatric ECMO support","volume":"40","author":"Hanalioglu","year":"2024","journal-title":"Neurocritical care"},{"key":"B8","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1016\/j.jtcvs.2014.02.078","article-title":"Blood lactate level during extracorporeal life support as a surrogate marker for survival","volume":"148","author":"Park","year":"2014","journal-title":"J Thoracic Cardiovasc Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1097\/CCM.0000000000005308","article-title":"Routine neuroimaging: understanding brain injury in pediatric extracorporeal membrane oxygenation*","volume":"50","author":"Farhat","year":"2022","journal-title":"Crit Care Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1016\/j.clp.2024.04.006","article-title":"Advances in electroencephalographic biomarkers of neonatal hypoxic ischemic encephalopathy","volume":"51","author":"Proietti","year":"2024","journal-title":"Clin Perinatol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.clinph.2015.05.018","article-title":"EEG Background features that predict outcome in term neonates with hypoxic ischaemic encephalopathy: a structured review","volume":"127","author":"Awal","year":"2016","journal-title":"Clin Neurophysiol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.pedneo.2018.03.010","article-title":"Automated EEG background analysis to identify neonates with hypoxic-ischemic encephalopathy treated with hypothermia at risk for adverse outcome: a pilot study","volume":"60","author":"Dereymaeker","year":"2019","journal-title":"Pediatr Neonatol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"103132","DOI":"10.1016\/j.neucli.2025.103132","article-title":"Quantitative EEG enhances early assessment and prognostic stratification of brain dysfunction in infants with abusive head trauma","volume":"56","author":"Hess","year":"2026","journal-title":"Neurophysiol Clin"},{"key":"B14","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1097\/MAT.0000000000001013","article-title":"Noninvasive neurological monitoring in extracorporeal membrane oxygenation","volume":"66","author":"Cho","year":"2020","journal-title":"Asaio J"},{"key":"B15","doi-asserted-by":"publisher","first-page":"2512","DOI":"10.3390\/jcm9082512","article-title":"EEG Is A predictor of neuroimaging abnormalities in pediatric extracorporeal membrane oxygenation","volume":"9","author":"Fox","year":"2020","journal-title":"Journal Clinical Medicine"},{"key":"B16","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1177\/02676591211066804","article-title":"Feasibility of non-invasive neuro-monitoring during extracorporeal membrane oxygenation in children","volume":"38","author":"McDevitt","year":"2023","journal-title":"Perfusion"},{"key":"B17","doi-asserted-by":"publisher","first-page":"2718","DOI":"10.3390\/jcm9092718","article-title":"Neural networks to predict radiographic brain injury in pediatric patients treated with extracorporeal membrane oxygenation","volume":"9","author":"Shah","year":"2020","journal-title":"J Clin Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.xjon.2024.06.001","article-title":"Acute brain injury risk prediction models in venoarterial extracorporeal membrane oxygenation patients with tree-based machine learning: an extracorporeal life support organization registry analysis.","volume":"20","author":"Kalra","year":"2024","journal-title":"Jtcvs Open"},{"key":"B19","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s13054-024-05248-9","article-title":"Development and external validation of a machine learning model for brain injury in pediatric patients on extracorporeal membrane oxygenation","volume":"29","author":"Deng","year":"2025","journal-title":"Critical Care"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e315","DOI":"10.1097\/MAT.0000000000001970","article-title":"Association between disrupted cerebral autoregulation and radiographic neurologic injury for children on extracorporeal membrane oxygenation: a prospective pilot study","volume":"69","author":"Sanford","year":"2023","journal-title":"Asaio J"},{"key":"B21","first-page":"3","article-title":"The ten-twenty electrode system of the international federation. The international federation of clinical neurophysiology","volume":"52","author":"Klem","year":"1999","journal-title":"Electroencephalogr Clin Neurophysiol Suppl"},{"key":"B22","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1097\/MAT.0000000000001896","article-title":"Clinical guidelines for routine neuromonitoring in neonatal and pediatric patients supported on extracorporeal membrane oxygenation","volume":"69","author":"Pandiyan","year":"2023","journal-title":"Asaio Journal"},{"key":"B23","first-page":"353","article-title":"Data analysis for continuous EEG monitoring in the ICU: seeing the forest and the trees","volume":"21","author":"Scheuer","year":"2004","journal-title":"J Clin Neurophysiol"},{"key":"B24","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"B25","first-page":"3149","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","year":"2017","journal-title":"Advances Neural Information Processing Systems"},{"key":"B26","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1145\/3459665","article-title":"k-Nearest neighbour classifiers - A tutorial","volume":"54","author":"Cunningham","year":"2021","journal-title":"ACM Comput Surv"},{"key":"B27","first-page":"785","article-title":"XGBoost: a scalable tree boosting system. Kdd'16","author":"Chen","year":"2016"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann Stat"},{"key":"B29","doi-asserted-by":"publisher","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Human brain mapping"},{"key":"B30","doi-asserted-by":"publisher","first-page":"36672","DOI":"10.1109\/ACCESS.2022.3161489","article-title":"EEG-ITNet: an explainable inception temporal convolutional network for motor imagery classification","volume":"10","author":"Salami","year":"2022","journal-title":"Ieee Access"},{"key":"B31","year":""},{"key":"B32","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B33","doi-asserted-by":"publisher","first-page":"E1372","DOI":"10.1212\/WNL.0000000000010188","article-title":"EEG Features of brain injury during extracorporeal membrane oxygenation in children","volume":"95","author":"Sansevere","year":"2020","journal-title":"Neurology"},{"key":"B34","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1097\/WNP.0000000000000165","article-title":"Consensus statement on continuous EEG in critically ill adults and children, part II: personnel, technical specifications, and clinical practice","volume":"32","author":"Herman","year":"2015","journal-title":"J Clin Neurophysiol"},{"key":"B35","doi-asserted-by":"publisher","first-page":"3237810","DOI":"10.1155\/2018\/3237810","article-title":"Cerebral pathophysiology in extracorporeal membrane oxygenation: pitfalls in daily clinical management","volume":"2018","author":"Kazmi","year":"2018","journal-title":"Crit Care Res Pract"},{"key":"B36","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/j.pediatrneurol.2020.03.014","article-title":"Neurological monitoring and complications of pediatric extracorporeal membrane oxygenation support","volume":"108","author":"Said","year":"2020","journal-title":"Pediatr Neurol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1016\/j.jtcvs.2021.09.063","article-title":"Neuromonitoring detects brain injury in patients receiving extracorporeal membrane oxygenation support","volume":"165","author":"Ong","year":"2023","journal-title":"J Thoracic Cardiovasc Surg"},{"key":"B38","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1007\/s12028-023-01675-8","article-title":"Neuromonitoring during ECMO support in children","volume":"39","author":"Felling","year":"2023","journal-title":"Neurocrit Care"},{"key":"B39","doi-asserted-by":"publisher","first-page":"7473","DOI":"10.1038\/s41598-017-07613-x","article-title":"Standardization of electroencephalography for multi-site, multi-platform and multi-investigator studies: insights from the Canadian biomarker integration network in depression","volume":"7","author":"Farzan","year":"2017","journal-title":"Sci Rep"},{"key":"B40","doi-asserted-by":"publisher","first-page":"425","DOI":"10.3389\/fnins.2017.00425","article-title":"The effect of electroencephalogram (EEG) reference choice on information-theoretic measures of the complexity and integration of EEG signals","volume":"11","author":"Trujillo","year":"2017","journal-title":"Front Neurosci"},{"key":"B41","doi-asserted-by":"publisher","first-page":"2399","DOI":"10.1152\/jn.00978.2015","article-title":"Utility of EEG measures of brain function in patients with acute stroke","volume":"115","author":"Wu","year":"2016","journal-title":"J Neurophysiol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1093\/braincomms\/fcab017","article-title":"The prognostic value of resting-state EEG in acute post-traumatic unresponsive states","volume":"3","author":"O'Donnell","year":"2021","journal-title":"Brain Commun"},{"key":"B43","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1177\/0883073820915323","article-title":"Prognostic value of continuous electroencephalogram Delta power in neonates with hypoxic-ischemic encephalopathy","volume":"35","author":"Kota","year":"2020","journal-title":"J Child Neurol"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1368","DOI":"10.3390\/children9091368","article-title":"The role of electroencephalography in the prognostication of clinical outcomes in critically ill children: a review","volume":"9","author":"Gilman","year":"2022","journal-title":"Children-Basel"},{"key":"B45","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1136\/pn-2023-003798","article-title":"Electroencephalography in encephalopathy and encephalitis","volume":"24","author":"Morris","year":"2024","journal-title":"Pract Neurol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1111\/epi.18196","article-title":"Development of a model to predict electroencephalographic seizures in neonates with hypoxic ischemic encephalopathy treated with therapeutic hypothermia","volume":"66","author":"Massey","year":"2025","journal-title":"Epilepsia"},{"key":"B47","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1159\/000530299","article-title":"Evaluating injury severity in neonatal encephalopathy using automated quantitative electroencephalography analysis: a pilot study","volume":"46","author":"Catenaccio","year":"2024","journal-title":"Dev Neurosci"},{"key":"B48","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1038\/jp.2016.262","article-title":"Early EEG power predicts MRI injury in infants with hypoxic-ischemic encephalopathy","volume":"37","author":"Jain","year":"2017","journal-title":"Journal Perinatology"},{"key":"B49","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.pediatrneurol.2021.06.001","article-title":"EEG Spectral power: a proposed physiological biomarker to classify the hypoxic-ischemic encephalopathy severity in real time","volume":"122","author":"Kota","year":"2021","journal-title":"Pediatr Neurol"},{"key":"B50","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1176\/jnp.13.1.77","article-title":"An EEG severity index of traumatic brain injury","volume":"13","author":"Thatcher","year":"2001","journal-title":"Journal Neuropsychiatry Clinical Neurosciences"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1016\/S1388-2457(03)00093-2","article-title":"EMG Contamination of EEG: spectral and topographical characteristics","volume":"114","author":"Goncharova","year":"2003","journal-title":"Clin Neurophysiol"},{"key":"B52","first-page":"1942","article-title":"Investigating effects of different artefact types on motor imagery BCI","author":"Frolich","year":"2015"},{"key":"B53","first-page":"1205","article-title":"Efficient feature selection via analysis of relevance and redundancy","volume":"5","author":"Yu","year":"2004","journal-title":"J Mach Learn Res"},{"key":"B54","first-page":"1021","article-title":"NEONATAL EEG","author":"Twarowska","year":"1993"},{"key":"B55","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1111\/apa.12869","article-title":"Overcoming the practical challenges of electroencephalography for very preterm infants in the neonatal intensive care unit","volume":"104","author":"Lloyd","year":"2015","journal-title":"Acta Paediatr"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2552\/aace8c","article-title":"EEGNet: a compact convolutional neural network for EEG-based brain-computer interfaces","year":"2018","journal-title":"J. Neural Eng"}],"container-title":["Frontiers in Digital Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1857835\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T05:37:11Z","timestamp":1787290631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdgth.2026.1857835\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,21]]},"references-count":56,"alternative-id":["10.3389\/fdgth.2026.1857835"],"URL":"https:\/\/doi.org\/10.3389\/fdgth.2026.1857835","relation":{},"ISSN":["2673-253X"],"issn-type":[{"value":"2673-253X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,21]]},"article-number":"1857835"}}