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

Neural networks for ischemic stroke.

Ralph W Barnes1, James F Toole, J J Nelson

  • 1Department of Neurology, Wake Forest University School of Medicine, Winston-Salem, North Carolina, USA.

Journal of Stroke and Cerebrovascular Diseases : the Official Journal of National Stroke Association
|October 2, 2007
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

Attending an Historically Black College or University and all-cause mortality in US Black adults.

American journal of epidemiology·2026
Same author

Prior Myocardial Infarction and Cognitive Decline: The REGARDS Cohort.

Stroke·2026
Same author

Temporal changes in depressive symptoms and incident stroke in a national cohort of Black and White adults: the REGARDS study.

Aging & mental health·2026
Same author

Sex-specific trends in incident stroke: The Framingham Heart Study.

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

Life's Essential 8 and Risk of Severe COVID-19 Among Adults Without Clinical Cardiovascular Disease: The C4R Study.

Journal of the American Heart Association·2026
Same author

Blood Biomarkers and the Risk of Coronary Disease in Atrial Fibrillation.

Journal of the American Heart Association·2026
Same journal

Efficacy of Cognitive Behavioral Therapy for Post-Stroke Fatigue: A Systematic Review and Meta-Analysis.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Admission Cognitive Function Independently Predicts Discharge Walking Function and Functional Independence After Stroke: A Multicenter Retrospective Cohort Study.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Association Between Race, Ethnicity, and Sex with Prehospital Identification and Outcomes of Patients with Stroke.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Direct Oral Anticoagulants versus Aspirin for Prevention of Overt and Covert Cerebral Infarction: A Meta-Analysis.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Efficacy of Pharyngeal Balloon Muscle Resistance Treatment in Post-Stroke Dysphagia: A Randomized Controlled Trial.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
Same journal

Detection of atrial fibrillation via adhesive single-lead ECG vs. Holter monitoring in embolic stroke of undetermined source: the AVANT-GARDE trial.

Journal of stroke and cerebrovascular diseases : the official journal of National Stroke Association·2026
See all related articles

Computer networks accurately classify transient ischemic attack (TIA) and stroke symptoms. This technology enables efficient population screening for TIA and stroke prevalence, aiding in diagnosis and research.

Area of Science:

  • Neurology
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Uniform criteria are needed for evaluating transient ischemic attack (TIA) and stroke prevalence.
  • Validated instruments are essential for objective assessment and classification of TIA and stroke.

Purpose of the Study:

  • To develop and validate a neural network system for rapid and accurate classification of TIA and stroke symptoms.
  • To enable objective assessment and classification of TIA/stroke for population studies.

Main Methods:

  • Patient responses regarding TIA/stroke symptoms were used to program individual neural networks.
  • Models were designed for rapid classification into 7 outputs: no event, TIA, or stroke (by vascular distribution).
  • Neural networks were tested against a validated questionnaire using an independent dataset of 381 patients.

Related Experiment Videos

Main Results:

  • Neural network classification showed strong correlation with diagnoses made by stroke clinicians.
  • All patients reporting no neurologic event were correctly classified.
  • Ten symptomatic patients were initially misclassified due to incomplete data, but this was resolved after network adjustment.

Conclusions:

  • Computer networks can be trained for rapid, accurate classification of TIA or stroke by vascular distribution.
  • This technology facilitates population screening for TIA and stroke incidence and prevalence assessment.