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

Real-World Practice in Secondary Stroke Prevention Following Embolic Stroke of Undetermined Source: Secondary Analysis of the CASPR Registry.

Neurology. Clinical practice·2026
Same author

Factors Associated With the Rising Trend in Self-Reported Cognitive Disability Among U.S. Adults Aged 18-39 From 2013-2024.

Annals of clinical and translational neurology·2026
Same author

Endovascular Thrombectomy in Medium and Distal Vessel Occlusions: A Focused Guideline From the Society of Vascular and Interventional Neurology Guidelines and Practice Standards Committee.

Stroke (Hoboken, N.J.)·2026
Same author

Final Infarct Volume as a Surrogate End Point in Anterior Circulation ICAS-LVO Stroke: Post Hoc Secondary Analysis of RESCUE-ICAS.

Stroke (Hoboken, N.J.)·2026
Same author

Spatial co-expression and cell-cell communication inference from spatially resolved transcriptomics with CONCISE.

bioRxiv : the preprint server for biology·2026
Same author

The Financial Value of an Academic Neurologist.

Annals of neurology·2026

Related Experiment Video

Updated: Jun 26, 2025

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia
06:01

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

14.8K

StrokeClassifier: ischemic stroke etiology classification by ensemble consensus modeling using electronic health

Ho-Joon Lee1, Lee H Schwamm2,3, Lauren H Sansing3

  • 1Department of Genetics and Yale Center for Genome Analysis, Yale School of Medicine, New Haven, CT, USA. ho-joon.lee@yale.edu.

NPJ Digital Medicine
|May 17, 2024
PubMed
Summary

An AI tool, StrokeClassifier, accurately predicts acute ischemic stroke causes using electronic health records. This artificial intelligence system rivals neurologist performance and aids in identifying stroke etiology for better prevention.

More Related Videos

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery
07:26

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Published on: May 24, 2021

7.1K
Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model
05:32

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

1.9K

Related Experiment Videos

Last Updated: Jun 26, 2025

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia
06:01

A Thrombotic Stroke Model Based On Transient Cerebral Hypoxia-ischemia

Published on: August 18, 2015

14.8K
Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery
07:26

Modeling Stroke in Mice: Transient Middle Cerebral Artery Occlusion via the External Carotid Artery

Published on: May 24, 2021

7.1K
Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model
05:32

Author Spotlight: Assessing Ischemic Stroke Damage Through Middle Cerebral Artery Occlusion Model

Published on: August 11, 2023

1.9K

Area of Science:

  • Neurology
  • Artificial Intelligence
  • Medical Informatics

Background:

  • Determining acute ischemic stroke (AIS) etiology is crucial for secondary prevention but remains diagnostically challenging.
  • Accurate etiological classification guides targeted treatment strategies and improves patient outcomes.
  • Existing methods rely on expert review, which can be time-consuming and resource-intensive.

Purpose of the Study:

  • To develop and validate an automated classification tool, StrokeClassifier, for predicting AIS etiology.
  • To assess the performance of StrokeClassifier against expert diagnoses using electronic health record (EHR) data.
  • To evaluate the potential of StrokeClassifier in reducing cryptogenic stroke diagnoses.

Main Methods:

  • Trained and validated StrokeClassifier, an ensemble consensus meta-model, on EHR text from 2039 non-cryptogenic AIS patients.
  • Utilized natural language processing (NLP) to extract features from discharge summaries.
  • Externally validated the tool on 406 discharge summaries from the MIMIC-III dataset.

Main Results:

  • StrokeClassifier achieved a mean cross-validated accuracy of 0.74 and weighted F1 of 0.74 for multi-class classification.
  • External validation in MIMIC-III yielded accuracy of 0.70 and weighted F1 of 0.71.
  • The tool reduced cryptogenic diagnoses from 25.2% to 7.2% when applied to cryptogenic stroke patients.

Conclusions:

  • StrokeClassifier demonstrates performance comparable to vascular neurologists in classifying ischemic stroke etiology.
  • The AI tool shows promise as a clinical decision support system for stroke diagnosis.
  • Further development could enhance its utility in real-world clinical settings.