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

Bent ligand-directed assembly and adsorption property modulation of pseudo-tetrahedral polyoxometalate-organic cages.

Chemical communications (Cambridge, England)·2026
Same author

Structural insights into Arabidopsis thaliana CTS-mediated fatty acid and hormone metabolism.

Nature communications·2026
Same author

Enhanced Polar Auxin Transport and Reduced Brassinosteroid Activity Drive Internode Elongation in Chinese Fir (<i>Cunninghamia lanceolata</i>).

Plants (Basel, Switzerland)·2026
Same author

Correction: A new mechanism of arterial calcification in diabetes: interaction between H3K18 lactylation and CHI3L1.

Clinical science (London, England : 1979)·2026
Same author

Corrigendum to 'Dapagliflozin activates the RAP1B/NRF2/GPX4 signaling and promotes mitochondrial biogenesis to alleviate vascular endothelial ferroptosis' [Cell Signal. 2025 Aug, 132:111824].

Cellular signalling·2026
Same author

Fabrication of Trimetallic Metal-Organic Frameworks for the Rapid Removal of Bisphenol A from Water.

Journal of chromatographic science·2026

Related Experiment Video

Updated: Aug 16, 2025

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

2.1K

Comparison of ischemic stroke diagnosis models based on machine learning.

Wan-Xia Yang1, Fang-Fang Wang1, Yun-Yan Pan1

  • 1Laboratory Medicine Center, Lanzhou University Second Hospital, Lanzhou, China.

Frontiers in Neurology
|December 22, 2022
PubMed
Summary

Machine learning models like LASSO, SVM-RFE, and RF show strong prediction capabilities for ischemic stroke (IS). While effective for positive cases, the artificial neural network (ANN) model struggles with negative sample classification.

Keywords:
artificial neural networkdiagnostic modelischemic strokemachine learningtranscriptomics

More Related Videos

Induction of Ischemic Stroke and Ischemia-reperfusion in Mice Using the Middle Artery Occlusion Technique and Visualization of Infarct Area
09:08

Induction of Ischemic Stroke and Ischemia-reperfusion in Mice Using the Middle Artery Occlusion Technique and Visualization of Infarct Area

Published on: February 2, 2017

16.5K
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

14.9K

Related Experiment Videos

Last Updated: Aug 16, 2025

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

2.1K
Induction of Ischemic Stroke and Ischemia-reperfusion in Mice Using the Middle Artery Occlusion Technique and Visualization of Infarct Area
09:08

Induction of Ischemic Stroke and Ischemia-reperfusion in Mice Using the Middle Artery Occlusion Technique and Visualization of Infarct Area

Published on: February 2, 2017

16.5K
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

14.9K

Area of Science:

  • Genomics
  • Bioinformatics
  • Computational Biology

Background:

  • Ischemic stroke (IS) presents a growing global health challenge with increasing incidence, prevalence, and mortality.
  • Early prediction and diagnosis of IS are crucial for mitigating its severe disease burden.

Purpose of the Study:

  • To develop and evaluate machine learning models for the early prediction and diagnosis of ischemic stroke (IS) using transcriptomic data.
  • To identify key feature genes and pathways associated with IS.

Main Methods:

  • Differential gene expression analysis was performed on IS and control samples using R software across datasets GSE16561, GSE58294, and GSE37587.
  • Feature genes for IS were identified using machine learning algorithms: least absolute shrinkage and selector operation (LASSO) logistic regression, support vector machine-recursive feature elimination (SVM-RFE), and Random Forest (RF).
  • Ischemic stroke diagnostic models were constructed using transcriptomics, machine learning, and artificial neural network (ANN) approaches.

Main Results:

  • Sixty-nine differentially expressed genes (DEGs) were identified, primarily linked to immune and inflammatory responses.
  • Key enriched pathways in IS included complement and coagulation cascades, lysosome, PPAR signaling, autophagy regulation, and toll-like receptor signaling.
  • Machine learning models (LASSO, SVM-RFE, RF) demonstrated high predictive performance with Area Under the Curve (AUC) values ranging from 0.805 to 1.000 across datasets. Combined models with ANN showed excellent performance on training data but variable results on test datasets, with high sensitivity but lower specificity and accuracy.

Conclusions:

  • LASSO, SVM-RFE, and RF models exhibit robust predictive capabilities for ischemic stroke.
  • The artificial neural network (ANN) model excels at classifying positive IS cases but is less effective for negative cases, indicating limitations in its diagnostic specificity.