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

Factors associated with rapid pediatric acute seizure emergency treatment: Quality Improvement in Time to Treat Status Epilepticus baseline cohort.

Epilepsia·2026
Same author

The Epilepsy-Cog study: Methods to establish a harmonized study of late onset epilepsy in a metacohort of six population-based cohorts in the United States.

Epilepsia·2026
Same author

Instrumental Activities of Daily Living in Older Adults with Epilepsy: A Cross-Sectional and Longitudinal Multicenter Study.

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

Acute and Long-Term EEG and seizure characteristics in new onset refractory status epilepticus (NORSE).

Epilepsia·2026
Same author

Alzheimer's disease neuroimaging signature aids identification of cognitive impairment in older adults with early-onset epilepsy.

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

Message From the Editors to Our Reviewers.

Neurology·2026

Related Experiment Video

Updated: Dec 2, 2025

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

26.1K

Deep active learning for Interictal Ictal Injury Continuum EEG patterns.

Wendong Ge1, Jin Jing1, Sungtae An2

  • 1Massachusetts General Hospital, Department of Neurology, Boston, MA, United States; Harvard Medical School, Boston, MA, United States.

Journal of Neuroscience Methods
|November 2, 2020
PubMed
Summary
This summary is machine-generated.

Active Learning (AL) can efficiently label electroencephalography (EEG) data for critically ill patients. A novel approach using label spreading and high confidence spread-based balanced querying (HCSBBQ) achieved expert-level performance with fewer labels.

Keywords:
Active learningConvolutional neural networkElectroencephalography(EEG)Embedding mapIctal Interictal Injury ContinuumMachine learningSeizure

More Related Videos

Non-restraining EEG Radiotelemetry: Epidural and Deep Intracerebral Stereotaxic EEG Electrode Placement
06:58

Non-restraining EEG Radiotelemetry: Epidural and Deep Intracerebral Stereotaxic EEG Electrode Placement

Published on: June 25, 2016

19.7K
Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

20.9K

Related Experiment Videos

Last Updated: Dec 2, 2025

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

26.1K
Non-restraining EEG Radiotelemetry: Epidural and Deep Intracerebral Stereotaxic EEG Electrode Placement
06:58

Non-restraining EEG Radiotelemetry: Epidural and Deep Intracerebral Stereotaxic EEG Electrode Placement

Published on: June 25, 2016

19.7K
Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy
10:22

Interictal High Frequency Oscillations Detected with Simultaneous Magnetoencephalography and Electroencephalography as Biomarker of Pediatric Epilepsy

Published on: December 6, 2016

20.9K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Critically ill patients frequently exhibit seizures and seizure-like patterns on electroencephalography (EEG), known as the ictal-interictal injury continuum (IIIC).
  • Automated detection of IIIC patterns is crucial for clinical care and research, but requires large, accurately labeled EEG datasets.
  • Active Learning (AL) offers a potential solution for efficient data labeling, yet the optimal AL strategy for this domain is not well-defined.

Purpose of the Study:

  • To investigate and optimize Active Learning (AL) strategies for labeling large electroencephalography (EEG) datasets.
  • To develop an efficient method for training accurate detectors of ictal-interictal injury continuum (IIIC) patterns in critically ill patients.
  • To compare different AL query selection and class balancing methods to determine the most effective approach.

Main Methods:

  • Assembled over 200,000 hours of EEG data from 1,454 hospitalized patients, creating a dataset of labeled and unlabeled 10-second EEG segments.
  • Employed a Dense-Net Convolutional Neural Network (CNN) for representation learning and utilized nearest-neighbor label spreading on a 2D embedding map to generate pseudo-labeled data.
  • Compared standard balanced-based querying (SBBQ) with high confidence spread-based balanced querying (HCSBBQ) for class balancing within AL queries.

Main Results:

  • Label spreading significantly accelerated the convergence of the AL process.
  • Most query criteria yielded comparable results to random sampling, highlighting the importance of the balancing strategy.
  • The HCSBBQ query balancing method demonstrated superior performance.
  • Achieved near expert-level model performance across all IIIC pattern categories with approximately 7,000 expert labels when using label spreading and HCSBBQ.

Conclusions:

  • The combination of label spreading and HCSBBQ represents an effective AL strategy for labeling large EEG datasets.
  • This approach provides valuable guidance for efficiently annotating EEG data from critically ill patients.
  • The developed methods can significantly reduce the effort required to train high-performance automated IIIC pattern detectors.