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 Experiment Videos

Seizure detection algorithm for neonates based on wave-sequence analysis.

Michael A Navakatikyan1, Paul B Colditz, Chris J Burke

  • 1BrainZ Instruments Ltd, 25 Carbine Road, Mt Wellington, P.O. Box 51078 Pakuranga, Auckland 1730, New Zealand. michael.navakatikyan@brainz.com

Clinical Neurophysiology : Official Journal of the International Federation of Clinical Neurophysiology
|April 20, 2006
PubMed
Summary

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

Relationships between sequential MRI in the neonatal period and early motor repertoire in very preterm infants.

Early human development·2026
Same author

Assessment of parasympathetic tone during therapeutic hypothermia in infants with brain injury following neonatal encephalopathy.

Pediatric research·2026
Same author

Evaluating the Predictive Value of Umbilical Cord and Infant Blood Gases in Hypoxic-Ischemic Encephalopathy.

The Journal of pediatrics·2026
Same author

Moderate neuroprotection of combination cell therapy in fetal growth restricted newborns at postnatal day 10.

Stem cells translational medicine·2026
Same author

Relationships between cerebral blood flow and cognition in young adults born very preterm and at term.

Scientific reports·2026
Same author

Concordance and Association of Kidokoro MRI Scores at 32 and 40 weeks post-menstrual age with Neurodevelopmental Outcomes in Very Preterm Infants.

AJNR. American journal of neuroradiology·2026

A new real-time seizure detection algorithm for newborns shows improved performance. This wave-sequence analysis method offers higher sensitivity and positive predictive value with fewer false positives than existing algorithms.

Area of Science:

  • Neonatal neurology
  • Medical device technology
  • Signal processing

Background:

  • Neonatal seizures are a critical concern requiring accurate detection.
  • Existing seizure detection algorithms have limitations in sensitivity and specificity.
  • Real-time monitoring is essential for timely intervention in newborns.

Purpose of the Study:

  • To describe and evaluate a novel real-time seizure detection algorithm for neonatal electroencephalogram (EEG) signals.
  • To compare the performance of the new algorithm against established methods.

Main Methods:

  • The algorithm fragments EEG signals into waves, extracts and averages wave features, and employs a multi-stage detection process.
  • It identifies EEG waves based on regularity, intervals, amplitudes, and shapes.

Related Experiment Videos

  • Performance was assessed using event-based and time-based metrics and compared with Gotman's and Liu's algorithms.

    • Main Results:

    • The algorithm achieved sensitivities of 83-95% and positive predictive values (PPV) of 48-77% in 55 neonates (17 with seizures).
    • It generated only 2.0 false positive detections per hour.
    • Compared to Gotman's (45-88% sensitivity, 29-56% PPV, 7.4 false positives/hour) and Liu's (96-99% sensitivity, 10-25% PPV, 15.7 false positives/hour) algorithms, the proposed method demonstrated superior performance.

    Conclusions:

    • The wave-sequence analysis algorithm significantly outperforms previous methods in sensitivity, PPV, and false positive rates for neonatal seizure detection.
    • This algorithm represents a significant advancement for neonatal seizure detection and monitoring systems.