{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T18:56:39Z","timestamp":1784573799458,"version":"3.55.0"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T00:00:00Z","timestamp":1756425600000},"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. Pediatr."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Neonatal encephalopathy (NE) is a significant cause of neurodevelopmental impairment, with therapeutic hypothermia (TH) being the current standard of care for mitigating brain injury in affected neonates. Despite advances, there is a critical need for early, reliable biomarkers that can predict brain injury severity and long-term outcomes, particularly during the 72-h hypothermia window. This study explores the potential of digital biomarkers derived from continuous bedside physiologic monitoring to predict MRI-confirmed brain injury in neonates with NE.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We collected continuous physiologic data from 138 neonates undergoing TH, including heart rate, systemic oxygen saturation (SpO\u2082), cerebral oxygen saturation (rcSO\u2082), systolic and diastolic blood pressure, and mean arterial pressure (MAP). Using a Long Short-Term Memory (LSTM) neural network, we developed predictive models to classify neonates into no\/mild or moderate\/severe brain injury groups based on MRI findings. Model performance was evaluated at 24 and 48\u2005h of data collection. An ablation study was conducted to assess the relative importance of individual biomarkers.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Seventy-three neonates (52.9%) were classified as having moderate\/severe injury, while 65 neonates (47.1%) had no\/mild injury on MRI. The predictive accuracy of the LSTM model improved significantly with extended data duration, achieving an accuracy of 91.2% at 48\u2005h compared to 84.6% at 24\u2005h. The ablation study identified heart rate as the most significant biomarker, whereas rcSO\u2082 trends showed potential but did not consistently contribute to prediction accuracy in later models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>Our study highlights the potential of digital biomarkers in predicting brain injury severity during the therapeutic hypothermia window. Machine learning models, such as LSTM networks, offer an opportunity for real-time prediction and risk stratification, ultimately enhancing clinical decision-making and neuroprotective strategies in neonates with NE. Future studies will focus on integrating real-time data capture and improving predictive accuracy.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fped.2025.1617155","type":"journal-article","created":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T05:45:54Z","timestamp":1756446354000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Digital biomarkers as predictors of brain injury in neonatal encephalopathy"],"prefix":"10.3389","volume":"13","author":[{"given":"Nahla","family":"Zaghloul","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Neel Kamal","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihuang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaitlyn","family":"Lagnese","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Livia","family":"Sura","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Carlos","family":"Roig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet","family":"Albayram","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhanashree","family":"Rajderkar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James L.","family":"Wynn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alina","family":"Zare","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael D.","family":"Weiss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,8,29]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s40748-018-0074-4","article-title":"Incidence and short term outcomes of neonates with hypoxic ischemic encephalopathy in a peri urban teaching hospital, Uganda: a prospective cohort study","volume":"4","author":"Namusoke","year":"2018","journal-title":"Matern Health Neonatol Perinatol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"645","DOI":"10.1007\/s00431-007-0437-8","article-title":"Long-term cognitive and behavioral consequences of neonatal encephalopathy following perinatal asphyxia: a review","volume":"166","author":"Van Handel","year":"2007","journal-title":"Eur J Pediatr"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1574","DOI":"10.1056\/NEJMcps050929","article-title":"Whole- body hypothermia for neonates with hypoxic-ischemic encephalopathy","volume":"353","author":"Shankaran","year":"2005","journal-title":"N Engl J Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1001\/archpediatrics.2012.284","article-title":"Prognostic utility of magnetic resonance imaging in neonatal hypoxic-ischemic encephalopathy: substudy of a randomized trial","volume":"166","author":"Cheong","year":"2012","journal-title":"Arch Pediatr Adolesc Med"},{"key":"B5","volume-title":"BEST (Biomarkers, Endpoints, and Other Tools) Resource","year":"2016"},{"key":"B6","doi-asserted-by":"publisher","first-page":"101084","DOI":"10.1016\/j.siny.2020.101084","article-title":"Small molecule biomarkers for neonatal hypoxic ischemic encephalopathy","volume":"25","author":"Sanchez-Illana","year":"2020","journal-title":"Semin Fetal Neonatal Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1136\/archdischild-2020-321096","article-title":"Neuronal exosome proteins: novel biomarkers for predicting neonatal response to therapeutic hypothermia","volume":"107","author":"Pineles","year":"2022","journal-title":"Arch Dis Child Fetal Neonatal Ed"},{"key":"B8","doi-asserted-by":"publisher","first-page":"934755","DOI":"10.3389\/fneur.2022.934755","article-title":"Concentration of serum biomarkers of brain injury in neonates with a low cord pH with or without mild hypoxic- ischemic encephalopathy","volume":"13","author":"Gaulee","year":"2022","journal-title":"Front Neurol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1038\/s41390-022-01994-0","article-title":"Combined GFAP, NFL, tau, and UCH-L1 panel increases prediction of outcomes in neonatal encephalopathy","volume":"93","author":"Yang","year":"2023","journal-title":"Pediatr Res"},{"key":"B10","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1111\/epi.18163","article-title":"Machine learning for forecasting initial seizure onset in neonatal hypoxic-ischemic encephalopathy","volume":"66","author":"Bernardo","year":"2025","journal-title":"Epilepsia"},{"key":"B11","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1002\/ana.27154","article-title":"Automated neuroprognostication via machine learning in neonates with hypoxic-ischemic encephalopathy","volume":"97","author":"Lewis","year":"2025","journal-title":"Ann Neurol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"728","DOI":"10.21037\/tp-24-425","article-title":"Current progress and future prospects of machine learning in the diagnosis of neonatal encephalopathy: a narrative review","volume":"14","author":"Huang","year":"2025","journal-title":"Transl Pediatr"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e07411","DOI":"10.1016\/j.heliyon.2021.e07411","article-title":"Predictive modelling of hypoxic ischaemic encephalopathy risk following perinatal asphyxia","volume":"7","author":"Mooney","year":"2021","journal-title":"Heliyon"},{"key":"B14","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1159\/000530352","article-title":"Graphic intelligent diagnosis of hypoxic-ischemic encephalopathy using MRI-based deep learning model","volume":"120","author":"Tian","year":"2023","journal-title":"Neonatology"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e240076","DOI":"10.1148\/ryai.240076","article-title":"Artificial intelligence outcome prediction in neonates with encephalopathy (AI-OPiNE)","volume":"6","author":"Lew","year":"2024","journal-title":"Radiol Artif Intell"},{"key":"B16","doi-asserted-by":"publisher","first-page":"94","DOI":"10.7861\/futurehosp.6-2-94","article-title":"The potential for artificial intelligence in healthcare","volume":"6","author":"Davenport","year":"2019","journal-title":"Future Healthc J"},{"key":"B17","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1080\/13645706.2019.1575882","article-title":"Introduction to artificial intelligence in medicine","volume":"28","author":"Mintz","year":"2019","journal-title":"Minim Invasive Ther Allied Technol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1577","DOI":"10.1016\/S0140-6736(19)30037-6","article-title":"Reporting of artificial intelligence prediction models","volume":"393","author":"Collins","year":"2019","journal-title":"Lancet"},{"key":"B19","volume-title":"Technology Assessment: Early Sense for Monitoring Vital Signs in Hospitalized Patients.","author":"Helfand","year":"2016"},{"key":"B20","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1159\/000487848","article-title":"Enteral feeding as an adjunct to hypothermia in neonates with hypoxic-ischemic encephalopathy","volume":"113","author":"Chang","year":"2018","journal-title":"Neonatology"},{"key":"B21","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.jpeds.2017.09.043","article-title":"A novel magnetic resonance imaging score predicts neurodevelopmental outcome after perinatal asphyxia and therapeutic hypothermia","volume":"192","author":"Weeke","year":"2018","journal-title":"J Pediatr"},{"key":"B22","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1111\/geb.13185","article-title":"Handling missing values in trait data","volume":"30","author":"Johnson","year":"2020","journal-title":"Glob Ecol Biogeogr"},{"key":"B23","doi-asserted-by":"publisher","first-page":"4062","DOI":"10.3390\/s22114062","article-title":"Predicting energy consumption using LSTM, multi-layer GRU and drop-GRU neural networks","volume":"22","author":"Mahjoub","year":"2022","journal-title":"Sensors (Basel)"},{"key":"B24","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.pediatrneurol.2020.11.015","article-title":"MRI Score ability to detect abnormalities in mild hypoxic-ischemic encephalopathy","volume":"116","author":"Machie","year":"2021","journal-title":"Pediatr Neurol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"e2020022962","DOI":"10.1542\/peds.2020-022962","article-title":"Predictive models of neurodevelopmental outcomes after neonatal hypoxic-ischemic encephalopathy","volume":"147","author":"Peeples","year":"2021","journal-title":"Pediatrics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e14110","DOI":"10.14814\/phy2.14110","article-title":"Heart rate variability and inflammatory markers in neonates with hypoxic-ischemic encephalopathy","volume":"7","author":"Yasova Barbeau","year":"2019","journal-title":"Physiol Rep"},{"key":"B27","doi-asserted-by":"publisher","first-page":"E70","DOI":"10.1097\/ANC.0000000000000686","article-title":"Correlation between heart rate characteristic Index score and severity of brain injury in neonates with hypoxic-ischemic encephalopathy","volume":"20","author":"Kayton","year":"2020","journal-title":"Adv Neonatal Care"},{"key":"B28","doi-asserted-by":"publisher","first-page":"836","DOI":"10.1038\/jp.2014.108","article-title":"Heart rate variability in encephalopathic newborns during and after therapeutic hypothermia","volume":"34","author":"Massaro","year":"2014","journal-title":"J Perinatol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1038\/s41372-023-01754-w","article-title":"Prediction of outcome of hypoxic-ischemic encephalopathy in newborns undergoing therapeutic hypothermia using heart rate variability","volume":"44","author":"Presacco","year":"2024","journal-title":"J Perinatol"},{"key":"B30","doi-asserted-by":"publisher","first-page":"6347","DOI":"10.1113\/JP287001","article-title":"Machine learning models of cerebral oxygenation (rcSO2) for brain injury detection in neonates with hypoxic-ischaemic encephalopathy","volume":"602","author":"Ashoori","year":"2024","journal-title":"J Physiol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1159\/000468976","article-title":"Prediction of outcome in neonates with hypoxic-ischemic encephalopathy II: role of amplitude-integrated electroencephalography and cerebral oxygen saturation measured by near-infrared spectroscopy","volume":"112","author":"Goeral","year":"2017","journal-title":"Neonatology"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2025.1617155\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T05:45:55Z","timestamp":1756446355000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2025.1617155\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,29]]},"references-count":31,"alternative-id":["10.3389\/fped.2025.1617155"],"URL":"https:\/\/doi.org\/10.3389\/fped.2025.1617155","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,29]]},"article-number":"1617155"}}