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

Spike detection II: automatic, perception-based detection and clustering.

S B Wilson1, C A Turner, R G Emerson

  • 1Persyst Development Corporation, Prescott, AZ 86303, USA. sbw@compuserve.com

Clinical Neurophysiology : Official Journal of the International Federation of Clinical Neurophysiology
|June 11, 1999
PubMed
Summary
This summary is machine-generated.

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

Chondrocytic and pharmacokinetic properties of Phlpp inhibitors.

Osteoarthritis and cartilage open·2022
Same author

A pilot study to record visual evoked potentials during prone spine surgery using the SightSaver™ photic visual stimulator.

Journal of clinical monitoring and computing·2017
Same author

An estimation of the proton conductance of the inner membrane of turnip (Brassica napus L.) mitochondria.

Planta·2014
Same author

Preferential depletion of gut CD4-expressing iNKT cells contributes to systemic immune activation in HIV-1 infection.

Mucosal immunology·2012
Same author

Evidence-based guideline update: intraoperative spinal monitoring with somatosensory and transcranial electrical motor evoked potentials: report of the Therapeutics and Technology Assessment Subcommittee of the American Academy of Neurology and the American Clinical Neurophysiology Society.

Neurology·2012
Same author

Self-injurious behaviour: limbic dysregulation and stress effects in an animal model.

Journal of intellectual disability research : JIDR·2011
Same journal

The middle-latency components of somatosensory evoked potentials help to predict the outcome in of post-anoxic coma: a monocentric study.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same journal

Multimodal intraoperative monitoring of facial nerve function: combined use of blink reflex and corticobulbar motor evoked potentials.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same journal

The contribution of trapezius and sternocleidomastoideus motor evoked potentials in the diagnosis of Amyotrophic lateral sclerosis.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same journal

Modulating corticospinal excitability with transcranial ultrasound stimulation: meta-analytic evidence of online and offline effects.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same journal

Fast oscillations as useful biomarkers of the degree of epileptogenicity in each generalized epilepsy syndrome.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
Same journal

Neuropsychological, biological, and electrophysiological outcomes of gamma-tACS in MCI-AD: A case series.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2026
See all related articles

We developed a novel algorithm for detecting and clustering epilepsy spikes in EEG data. This automated approach closely matches human expert performance, offering a clinically useful tool for neurologists.

Area of Science:

  • Neuroscience
  • Medical Technology
  • Signal Processing

Background:

  • Epilepsy diagnosis relies heavily on identifying abnormal brain activity, specifically spikes, in electroencephalogram (EEG) data.
  • Manual spike detection and classification are time-consuming and subjective, necessitating automated solutions.
  • Existing automated methods face challenges with accuracy and overtraining.

Purpose of the Study:

  • To develop and evaluate perception-based algorithms for automated spike detection and clustering in EEG.
  • To assess the performance of a novel Multiple Monotonic Neural Network (MMNN) for spike detection.
  • To compare automated spike clustering with expert manual grouping.

Main Methods:

  • A novel Multiple Monotonic Neural Network (MMNN) was employed for spike detection.

Related Experiment Videos

  • The MMNN algorithm was tested on two EEG databases comprising 2400 spikes from 50 epilepsy patients and 10 controls.
  • Hierarchical clustering based on spike topology and morphology was used for automatic spike grouping and visually compared to manual grouping.

    • Main Results:

    • The MMNN algorithm demonstrated performance comparable to human experts in spike detection.
    • The MMNN algorithm effectively mitigated issues associated with overtraining.
    • Hierarchical clustering produced spike groupings that were strikingly similar to those identified by human experts.

    Conclusions:

    • Automated spike detection algorithms can be clinically useful even if not perfectly matching human expert accuracy.
    • A user interface enabling rapid artifact deletion and identification of multiple spike generators is sufficient for clinical utility.
    • The developed MMNN and clustering algorithms offer a promising approach for improving the efficiency and objectivity of epilepsy diagnosis.