Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Risk factors associated with cancer and metabolic encephalopathy in Alzheimer's disease patients.

Frontiers in aging neuroscience·2026

Same author

Machine learning for Alzheimer's disease progression under extreme class imbalance.

Frontiers in neuroscience·2026

Same author

Sex differences in comorbidities associated with exclusion from thrombolytic therapy in ischemic stroke patients with heart failure: A retrospective data analysis.

JRSM cardiovascular disease·2026

Same author

Examining pharmacological and demographic factors among male and female alzheimer's disease patients diagnosed with attention concentration disorder and cognitive communication disorder.

Geriatric nursing (New York, N.Y.)·2025

Same author

A cross-domain framework for emotion and stress detection using WESAD, SCIENTISST-MOVE, and DREAMER datasets.

Frontiers in bioengineering and biotechnology·2025

Same author

Empowering Underrepresented Minority Students: a STEM-Focused Research Internship Program Bridging the Path to Graduate and Professional Success.

Innovative higher education·2025

Same journal

Multimodal data fusion of dual-modal DWI-ADC MRI and clinical variables for prognostic prediction in acute ischemic stroke.

Frontiers in neurology·2026

Same journal

Acute injury characteristics predict chronic neuropathic pain development after spinal cord injury.

Frontiers in neurology·2026

Same journal

Summary of the best evidence for non-pharmacological management of dysphagia in Parkinson's disease patients.

Frontiers in neurology·2026

Same journal

Quantifying cerebral autoregulation following endovascular thrombectomy using wavelet transformation.

Frontiers in neurology·2026

Same journal

Surgical strategies for spontaneous intracerebral hemorrhage: a Bayesian network meta-analysis of randomized controlled trials.

Frontiers in neurology·2026

Same journal

Procedure-related vasospasm and reperfusion vulnerability during mechanical thrombectomy.

Frontiers in neurology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

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

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

Published on: October 10, 2018

Evaluating machine learning models for stroke prediction based on clinical variables.

Patrick O Akinwumi¹, Stephen Ojo², Thomas I Nathaniel³

¹College of Education, Clemson University, Clemson, SC, United States.

Frontiers in Neurology

|September 29, 2025

Summary

This summary is machine-generated.

Machine learning models show promise for predicting stroke risk, with Logistic Regression and Gradient Boosting achieving high accuracy. However, identifying rare stroke cases remains a challenge, indicating a need for further research.

Keywords:

clinical decision support systems feature importance analysis imbalanced data handling machine learning in healthcare predictive modelling stroke risk prediction

More Related Videos

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Published on: February 22, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Related Experiment Videos

Last Updated: Jan 16, 2026

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

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

Published on: October 10, 2018

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Determining the Functional Status of the Corticospinal Tract Within One Week of Stroke

Published on: February 22, 2020

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

Area of Science:

Biomedical Informatics
Computational Epidemiology
Public Health

Background:

Stroke is a leading cause of death and disability globally.
Existing stroke risk prediction models have limitations in handling complex data.
Machine learning (ML) offers advanced capabilities for personalized risk assessment.

Purpose of the Study:

To evaluate the performance of five supervised ML algorithms for stroke risk prediction.
To identify key predictors of stroke using ML-based feature importance analysis.
To compare ML models against traditional risk assessment methods.

Main Methods:

Utilized a public Kaggle dataset for stroke prediction.
Implemented and compared Logistic Regression, Random Forest, Gradient Boosting, SVM, and KNN algorithms.
Applied class imbalance correction and evaluated models using accuracy, ROC-AUC, and confusion matrices.

Main Results:

Logistic Regression and Gradient Boosting demonstrated the highest accuracy (95.11%) and ROC-AUC (0.836).
All models exhibited low recall for identifying rare stroke cases.
Age, average glucose levels, and BMI were identified as significant stroke predictors.

Conclusions:

ML models show potential for improving stroke risk prediction accuracy.
Current ML approaches face challenges in detecting infrequent stroke occurrences.
Future research should focus on multi-modal data and advanced algorithms to enhance clinical utility.