ORIGINAL RESEARCH article
Front. Pediatr.
Sec. Neonatology
Volume 13 - 2025 | doi: 10.3389/fped.2025.1560760
This article is part of the Research TopicEvaluating Efficacy and Outcomes in Neonatal HIE Treatment: A Global PerspectiveView all 7 articles
The future is in the background: Background EEG patterns, not acute seizures, predict epilepsy and neurodevelopmental outcomes in neonatal HIE
Provisionally accepted
Kristine E Woodward1*
Pauline Dejesus2
Kimberly Amador3
Pauline Mouches3Marvin Braun1Khorshid Mohammad1
Nils Daniel Forkert4
Michael J Esser5- 1Department of Pediatrics, University of Calgary, Calgary, Canada
- 2Department of Clinical Neurosciences, University of Calgary, Calgary, Alberta, Canada
- 3Department of Radiology, University of Calgary, Calgary, Alberta, Canada
- 4Department of Clinical Neurosciences, Department of Radiology, Department of Electrical and Software Engineering, University of Calgary, Calgary, Alberta, Canada
- 5Department of Clinical Neurosciences, Department of Pediatrics, University of Calgary, Calgary, Alberta, Canada
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Background: Hypoxic ischemic encephalopathy (HIE) is the most common neurologic emergency in neonates, with a broad range of neurodevelopmental outcomes. It is also the leading cause of seizures during the neonatal period. Predicting long-term outcomes remains challenging. We aimed to examine EEG background data to assess its relationship with neurodevelopment and epilepsy risk, and its predictive value compared to other clinical data. Methods: Patients were retrospectively recruited from NICUs in Calgary (2014–2020). All met criteria for therapeutic hypothermia. Clinical data included exams, blood work, MRI, medications, and continuous video EEG (cvEEG) scored separately for background and ictal features. Neurodevelopmental follow-up occurred at two years, and patients were categorized by epilepsy status. Poisson regression and supervised learning models were used to evaluate predictors. Results: Among 206 patients, only 18% of those with seizures developed epilepsy, compared to 52% with severely abnormal EEG background. Ictal burden and anti-seizure medications did not predict outcomes. Background score strongly predicted epilepsy (adjusted ß = 2.75, p = 0.002; RR = 7.22) and neurodevelopment (adjusted ß = 1.74, p < 0.001; RR = 2.44). Machine learning confirmed background features as the most predictive, with XGBoost achieving the best accuracy (0.724) and random forest the highest AUC (0.751). Conclusions: EEG background patterns outperformed ictal burden in predicting neurodevelopmental and epilepsy outcomes in neonatal HIE. Although not modifiable, background abnormalities are powerful early markers of brain injury severity and can guide prognostication and family counseling.
Keywords: neonatal HIE, cEEG = continuous EEG, neurodevelopmental outcome, Epilepsy prediction, background EEG, Background EEG activity
Received: 14 Jan 2025; Accepted: 22 Aug 2025.
Copyright: © 2025 Woodward, Dejesus, Amador, Mouches, Braun, Mohammad, Forkert and Esser. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Kristine E Woodward, Department of Pediatrics, University of Calgary, Calgary, Canada
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.