Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Seizures: Classification01:13

Seizures: Classification

Epilepsy is primarily characterized by unpredictable seizures, either provoked by an identifiable factor, such as injury or illness, or unprovoked, occurring spontaneously without apparent cause.
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Identification of genetic markers of quinine partial resistance in Plasmodium falciparum.

Nature microbiology·2026
Same author

Gastrointestinal Dysfunction in Critically Ill Patients With Traumatic Brain Injury: Clinical Implications and Putative Mechanisms: a Narrative Review.

Current neurology and neuroscience reports·2026
Same author

Cost-Effectiveness of EEG Monitoring in Hypoxic-Ischemic Brain Injury After Cardiac Arrest.

Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society·2026
Same author

Neonatal Brain Network Integration Trajectories Predict Neurodevelopment in Congenital Heart Disease.

medRxiv : the preprint server for health sciences·2026
Same author

Association of parental holding during therapeutic hypothermia and NICU outcomes for infants with hypoxic-ischemic encephalopathy.

Journal of perinatology : official journal of the California Perinatal Association·2026
Same author

Advances in LLM Reasoning Enable Flexibility in Clinical Problem-Solving.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026

Related Experiment Video

Updated: Jun 12, 2026

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice
09:29

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Published on: June 11, 2020

3.3K

Machine learning for forecasting initial seizure onset in neonatal hypoxic-ischemic encephalopathy.

Danilo Bernardo1, Jonathan Kim2, Marie-Coralie Cornet3

  • 1Department of Neurology and Weill Institute for Neurosciences, University of California, San Francisco, San Francisco, California, USA.

Epilepsia
|November 4, 2024
PubMed
Summary

This study developed a machine learning model to predict seizures in neonatal hypoxic-ischemic encephalopathy (HIE) using clinical data and quantitative electroencephalogram (QEEG) features. The model accurately forecasts seizure risk, identifying spectral power evolution as an early marker.

Keywords:
machine learningneonatal hypoxic–ischemic encephalopathyneonatal seizuresseizure forecasting

More Related Videos

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy
05:52

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy

Published on: October 28, 2022

738
Author Spotlight: Assessing the Feasibility of Using Amplitude-Integrated EEG During Neonatal Transport
05:15

Author Spotlight: Assessing the Feasibility of Using Amplitude-Integrated EEG During Neonatal Transport

Published on: June 21, 2024

599

Related Experiment Videos

Last Updated: Jun 12, 2026

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice
09:29

Continuous Video Electroencephalogram during Hypoxia-Ischemia in Neonatal Mice

Published on: June 11, 2020

3.3K
Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy
05:52

Early Pathological and Magnetic Resonance Detection of Cerebral Injury Using a Rat Model of Neonatal Hypoxic Ischemic Encephalopathy

Published on: October 28, 2022

738
Author Spotlight: Assessing the Feasibility of Using Amplitude-Integrated EEG During Neonatal Transport
05:15

Author Spotlight: Assessing the Feasibility of Using Amplitude-Integrated EEG During Neonatal Transport

Published on: June 21, 2024

599

Area of Science:

  • Neonatal neurology
  • Machine learning in medicine
  • Quantitative electroencephalography

Background:

  • Neonatal hypoxic-ischemic encephalopathy (HIE) is a significant cause of brain injury in newborns.
  • Seizures are a common complication of HIE, necessitating accurate and timely prediction.
  • Current methods for seizure prediction in HIE have limitations in accuracy and timeliness.

Purpose of the Study:

  • To develop and validate a machine learning (ML) model for forecasting initial seizure onset in neonatal HIE.
  • To integrate clinical variables and quantitative electroencephalogram (QEEG) features for enhanced predictive accuracy.
  • To assess the model's ability to provide time-dependent seizure risk predictions.

Main Methods:

  • Developed a gradient boosting ML model (Neo-GB) incorporating clinical data (cord blood gas, Apgar scores, gestational age, etc.) and QEEG features (statistical moments, spectral power, RQA).
  • Trained and evaluated the model on a UCSF HIE dataset, augmented with international neonatal EEG datasets.
  • Assessed model performance using diagnostic metrics, incident/dynamic area under the receiver operating characteristic curve (iAUC), and concordance index (C-index).

Main Results:

  • The Neo-GB model with time-dependent features achieved an AUROC of .89 for static forecasting and a median iAUC of .79 for dynamic forecasting.
  • Model explanations highlighted spectral power, postmenstrual age (PMA), RQA, and cord blood gas values as key predictors.
  • Analysis revealed an upward trend in broadband spectral power in influential EEG channels preceding seizure onset.

Conclusions:

  • An ML model combining QEEG and clinical features can effectively forecast time-dependent seizure risk in neonatal HIE.
  • Spectral power evolution in EEG serves as an early indicator of seizure risk in neonates with HIE.
  • This approach offers a promising tool for proactive management and intervention in neonatal HIE.