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 journal

Ophthalmic health communication in the video-based social media era: A narrative review of information quality, engagement dynamics, and professional education.

Digital health·2026
Same journal

Feasibility and acceptability of FinCare: A personalized online tool for estimating out-of-pocket costs for cancer treatment.

Digital health·2026
Same journal

Photo-based deep learning for detection of pediatric adenoid hypertrophy.

Digital health·2026
Same journal

Initial evidence of effects of a novel digital behavioural treatment for chronic pain: A series of replicated randomized single-case experimental design studies.

Digital health·2026
Same journal

Insomnia severity modifies diary-based sleep-continuity and sleep-initiation associations with next-day daytime HRV in a real-world wearable dataset.

Digital health·2026
Same journal

Psychiatrists' experiences and opinions of generative AI: An exploratory online mixed methods survey in Germany.

Digital health·2026

Related Experiment Video

Updated: May 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.1K

Integrating expert knowledge with machine learning for AI-based stroke identifications and treatment systems.

Taddesse Kassu Yimenu1, Abebe Belay Adege2,3, Sofonias Yitagesu Techan4

  • 1Department of Computer Science, Debre Berhan University, Debre Berhan, Ethiopia.

Digital Health
|May 5, 2025
PubMed
Summary

An AI-driven system improves stroke diagnosis and treatment, especially in areas lacking specialists. This artificial intelligence tool achieved 99.4% accuracy, aiding healthcare providers in critical decision-making.

Keywords:
AI-based systemdomain expertknowledge-based systemmachine learningstroke disease

More Related Videos

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

742
Author Spotlight: Innovative Techniques and Future Directions in Stroke Research
04:46

Author Spotlight: Innovative Techniques and Future Directions in Stroke Research

Published on: May 5, 2023

3.3K

Related Experiment Videos

Last Updated: May 9, 2025

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.1K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

742
Author Spotlight: Innovative Techniques and Future Directions in Stroke Research
04:46

Author Spotlight: Innovative Techniques and Future Directions in Stroke Research

Published on: May 5, 2023

3.3K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Neurology

Background:

  • Stroke is a major global cause of death and disability.
  • Limited access to specialists in resource-limited settings hinders timely stroke diagnosis and treatment.
  • Accurate and early stroke detection is crucial for improving patient outcomes.

Purpose of the Study:

  • To develop an AI-driven system for stroke identification and treatment.
  • To enable healthcare providers to make informed decisions without direct specialist input.
  • To enhance stroke management in underserved regions.

Main Methods:

  • Data collection from a referral hospital and a public Kaggle dataset.
  • Feature selection using decision trees, Chi-Square tests, Elastic Net, and correlation analysis.
  • Development of a hybrid expert system combining Prolog for expert knowledge and Python for machine learning models (Decision Tree, Random Forest, Support Vector Machine).
  • Evaluation of machine learning models using k-fold cross-validation.

Main Results:

  • Random Forest classifier achieved the highest accuracy of 99.4%.
  • Shapley Additive Explanations confirmed the feasibility of feature selection in AI model development.
  • Medical professionals validated the system's effectiveness as a decision-support tool.

Conclusions:

  • The AI-driven expert system significantly enhances stroke diagnosis and treatment capabilities.
  • This approach offers a viable solution for improving stroke care in regions with limited specialist access.
  • The system demonstrates the potential of AI to bridge healthcare gaps and improve patient outcomes.