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

Assessing infants' sleep in the home setting: designing rational study approaches.

Pediatric research·2026
Same author

Brain activity as a candidate biomarker for personalised caffeine treatment in premature neonates.

Frontiers in pediatrics·2026
Same author

Clinical AI is Not (Yet) Trustworthy-But It Could Be.

Journal of medical Internet research·2026
Same author

Rethinking Trust in Synthetic Health Data: Lessons From 7 European Research Initiatives.

Journal of medical Internet research·2026
Same author

Prototype-based sleep micro-structure learning for explainable and robust multimodal recognition of sleep-related conditions.

Research square·2026
Same author

Medication, Vaccine, and Folic Acid Use Among Pregnant Women in Belgium: Insights from the BELpREG Cohort.

Pharmacoepidemiology and drug safety·2026

Related Experiment Video

Updated: Oct 3, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
06:28

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

2.6K

Automatic annotation correction for wearable EEG based epileptic seizure detection.

Jingwei Zhang1, Christos Chatzichristos1, Kaat Vandecasteele1

  • 1Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium.

Journal of Neural Engineering
|February 14, 2022
PubMed
Summary

Automated correction of seizure annotations in wearable EEG significantly improves seizure detection accuracy. This method enhances sensitivity and reduces false positives compared to manual correction or original vEEG annotations.

Keywords:
automated seizure detectionautomatic annotation correctionepilepsywearable EEG

More Related Videos

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.9K
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

8.8K

Related Experiment Videos

Last Updated: Oct 3, 2025

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems
06:28

Author Spotlight: Unraveling Seizure Dynamics and Novel Therapeutics for Status Epilepticus Using CMOS High-Density Microelectrode Array Systems

Published on: September 27, 2024

2.6K
Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.9K
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

8.8K

Area of Science:

  • Neurology
  • Biomedical Engineering
  • Signal Processing

Background:

  • Video-electroencephalography (vEEG) is the gold standard for seizure detection but is impractical for long-term home monitoring.
  • Wearable EEG devices offer a comfortable and unobtrusive solution for continuous home monitoring of epileptic seizures.
  • Accurate seizure annotations are crucial for developing reliable data-driven seizure detection algorithms using wearable EEG data, but existing annotations often have limitations.

Purpose of the Study:

  • To develop and evaluate an automatic approach for correcting imperfect seizure annotations in wearable EEG data.
  • To improve the training of automated seizure detection algorithms by refining annotation accuracy.
  • To compare the performance of seizure detection models trained with original, visually corrected, and automatically corrected seizure annotations.

Main Methods:

  • Investigated the efficacy of visual correction for seizure annotations on wearable EEG data.
  • Developed a novel automatic method to identify and remove non-seizure epochs mislabeled as seizures in wearable EEG recordings.
  • Trained and evaluated seizure detection models using three distinct annotation sets: original vEEG, visually corrected, and automatically corrected.

Main Results:

  • Seizure detection models trained with automatically corrected annotations demonstrated superior performance.
  • The automated correction approach resulted in higher seizure detection sensitivity.
  • Fewer false-positive detections were observed when using automatically corrected annotations compared to visual correction and original annotations.

Conclusions:

  • Automatic correction of seizure annotations in wearable EEG data is a viable and effective strategy.
  • This approach significantly enhances the performance of automated seizure detection algorithms.
  • The findings support the use of automatically corrected wearable EEG data for more accurate long-term epilepsy monitoring.