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

You might also read

Related Articles

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

Sort by
Same author

BFRCNet: Addressing the class imbalance problem in the rapid serial visual presentation paradigm for decoding.

Journal of neural engineering·2025
Same author

SQI-DOANet: electroencephalogram-based deep neural network for estimating signal quality index and depth of anaesthesia.

Journal of neural engineering·2024
Same author

Transformer-Based Network with Optimization for Cross-Subject Motor Imagery Identification.

Bioengineering (Basel, Switzerland)·2023
Same author

Filter bank sinc-convolutional network with channel self-attention for high performance motor imagery decoding.

Journal of neural engineering·2023
Same author

MRASleepNet: a multi-resolution attention network for sleep stage classification using single-channel EEG.

Journal of neural engineering·2022
Same author

Multi-objective optimization approach for channel selection and cross-subject generalization in RSVP-based BCIs.

Journal of neural engineering·2021

Related Experiment Video

Updated: May 14, 2025

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

789

Robust EEG Characteristics for Predicting Neurological Recovery from Coma After Cardiac Arrest.

Meitong Zhu1, Meng Xu2, Meng Gao1

  • 1Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China.

Sensors (Basel, Switzerland)
|April 12, 2025
PubMed
Summary
This summary is machine-generated.

Electroencephalogram (EEG) analysis using machine learning identifies key biomarkers for predicting neurological recovery after cardiac arrest. Specific EEG patterns, like functional connectivity and burst suppression, improve early prognosis assessment in comatose patients.

Keywords:
EEG signal feature extractioncardiac arrestneurological recovery and prognosis

More Related Videos

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
09:16

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

25.5K
Author Spotlight: Enhancing Cerebral Ischemia Research with a Simplified Rat Model
03:37

Author Spotlight: Enhancing Cerebral Ischemia Research with a Simplified Rat Model

Published on: July 5, 2024

434

Related Experiment Videos

Last Updated: May 14, 2025

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke
06:37

Electroencephalography Network Indices as Biomarkers of Upper Limb Impairment in Chronic Stroke

Published on: July 14, 2023

789
Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury
09:16

Use of a Wireless Video-EEG System to Monitor Epileptiform Discharges Following Lateral Fluid-Percussion Induced Traumatic Brain Injury

Published on: June 21, 2019

25.5K
Author Spotlight: Enhancing Cerebral Ischemia Research with a Simplified Rat Model
03:37

Author Spotlight: Enhancing Cerebral Ischemia Research with a Simplified Rat Model

Published on: July 5, 2024

434

Area of Science:

  • Neuroscience
  • Medical Informatics
  • Signal Processing

Background:

  • Coma after cardiac arrest presents challenges in predicting neurological recovery.
  • Standardized prognostication aims to reduce clinical judgment errors and opinion discrepancies.
  • Early and objective assessment of neurological prognosis is crucial for patient management.

Purpose of the Study:

  • To analyze electroencephalogram (EEG) signal patterns in comatose cardiac arrest patients.
  • To identify key EEG indicators for assessing neurological recovery prognosis.
  • To develop a machine learning-based framework for objective prognosis evaluation.

Main Methods:

  • Sequential application of machine learning models for feature selection and filtering.
  • Utilizing CatBoost as a superior classification method.
  • Employing Shapley Additive Explanation (SHAP) values for feature importance analysis.

Main Results:

  • Achieved a fivefold cross-validation ROC of 0.87 using three distinct EEG features.
  • Functional connectivity features contributed 70% to classification accuracy.
  • Low-frequency long-distance connectivity (45%) indicated poor prognosis; high-frequency short-distance connectivity (25%) indicated good prognosis.
  • Burst suppression ratio (20%) at high thresholds showed strong discriminative power.

Conclusions:

  • Identified low-frequency connectivity and burst suppression thresholds as key EEG biomarkers.
  • Machine learning algorithms and SHAP values enhance the reliability of prognosis predictions.
  • Established a clinically actionable framework for improving early, objective neurological prognosis assessments and patient care.