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

Cardiovascular hospitalization dynamics in Iran's second-largest city: A spatial and temporal perspective.

PloS one·2026

Same author

FairGuard: Blockchain-Enforced Continuous Fairness Governance for Demographically Equitable LLM-Based Emergency Triage Decision Support.

Studies in health technology and informatics·2026

Same author

Development and evaluation of a clinical dashboard for nephrology inpatients: a pilot study.

BMC medical informatics and decision making·2026

Same author

Enhancing healthcare explainability through multiobjective counterfactual explanations.

Scientific reports·2026

Same author

Geographical Distribution of Patients With Chronic Kidney Disease Receiving Hemodialysis Care in Northwest Iran: A Retrospective Cross-Sectional Study.

Health science reports·2026

Same author

A mobile-based educational tool for training medical students in emergency trauma management: development and pilot study.

BMC medical education·2026

Same journal

MCT1 inhibition reprograms Treg metabolism via ABC transporters: implications for tumor immunity and the prognosis of acute myeloid leukemia patients.

European journal of medical research·2026

Same journal

Delayed bedtime on workdays is associated with an increased prevalence of gallstones: a population-based study.

European journal of medical research·2026

Same journal

Salvianolic acid B attenuates post-cardiac arrest cerebral ischemia-reperfusion injury via activation of the Nrf2 signaling pathway.

European journal of medical research·2026

Same journal

Clinical value of sputum galactomannan testing in the diagnosis of invasive pulmonary aspergillosis among chronic obstructive pulmonary disease patients.

European journal of medical research·2026

Same journal

Integrative analysis reveals luteolin's molecular targets and mechanisms in pancreatic cancer treatment.

European journal of medical research·2026

Same journal

Non-linear association between cardiometabolic index and helicobacter pylori infection: a cross-sectional study.

European journal of medical research·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 7, 2025

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

Predicting stroke severity of patients using interpretable machine learning algorithms.

Amir Sorayaie Azar^1,2, Tahereh Samimi^3,4, Ghanbar Tavassoli^3,4,5

¹SDU Health Informatics and Technology, The Maersk Mc-Kinney Moller Institute, University of Southern Denmark, Odense, Denmark.

European Journal of Medical Research

|November 14, 2024

Summary

This summary is machine-generated.

Machine learning models accurately predict stroke severity using the Rapid Arterial Occlusion Evaluation (RACE) and National Institutes of Health Stroke Scale (NIHSS). Random Forest achieved the highest accuracy, identifying key predictors like triglyceride levels and age.

Keywords:

Interpretable machine learning Machine learning Prediction Stroke severity

More Related Videos

The Mouse Stroke Unit Protocol with Standardized Neurological Scoring for Translational Mouse Stroke Studies

The Mouse Stroke Unit Protocol with Standardized Neurological Scoring for Translational Mouse Stroke Studies

Published on: February 7, 2025

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: Jun 7, 2025

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

The Mouse Stroke Unit Protocol with Standardized Neurological Scoring for Translational Mouse Stroke Studies

The Mouse Stroke Unit Protocol with Standardized Neurological Scoring for Translational Mouse Stroke Studies

Published on: February 7, 2025

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:

Neurology
Medical Informatics
Artificial Intelligence

Background:

Stroke is a leading cause of death globally, necessitating accurate severity assessment for patient outcomes.
Current stroke assessment tools include the Rapid Arterial Occlusion Evaluation (RACE) and National Institutes of Health Stroke Scale (NIHSS).
Predicting stroke severity is vital for effective treatment and resource allocation in healthcare systems.

Purpose of the Study:

To apply Machine Learning (ML) algorithms for predicting stroke severity.
To compare the performance of ML models using the RACE and NIHSS scales.
To identify key clinical features influencing stroke severity prediction.

Main Methods:

Utilized two datasets from Urmia, Iran, for RACE and NIHSS stroke severity assessments.
Applied seven ML algorithms: KNN, DT, RF, AdaBoost, XGBoost, SVM, and ANN.
Employed grid search for hyperparameter tuning and SHapley Additive Explanations (SHAP) for feature interpretability.

Main Results:

The Random Forest (RF) model demonstrated superior performance, achieving 92.68% accuracy for RACE and 91.19% for NIHSS.
Area Under the Curve (AUC) values reached 92.02% for RACE and 97.86% for NIHSS.
SHAP analysis highlighted triglyceride levels, hospital stay duration, and age as significant predictors of stroke severity.

Conclusions:

This study pioneers the application of ML to RACE and NIHSS scales for stroke severity prediction.
SHAP analysis enhances model interpretability, fostering clinical trust in ML tools.
The developed ML model serves as a valuable aid for clinicians in predicting stroke severity.