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

Improvement of persistent anuria by long-term percutaneous ventricular assist device management and successful bridge to left ventricular assist device implantation in a patient with acute myocardial infarction: a case report.

European heart journal. Case reports·2026
Same author

Whole-body CT characteristics of patients with severe fever with thrombocytopenia syndrome.

Japanese journal of radiology·2026
Same author

Factors associated with achieving the 10-minute scene-to-ECG transmission target in prehospital care: the role of EMS agency-level cumulative ECG transmissions.

BMC emergency medicine·2026
Same author

Performance of large language models and prompt engineering strategies for data extraction in systematic reviews.

Frontiers in digital health·2026
Same author

Use of Commercially Available Large Language Models to Generate Information Leaflets on Post-Intensive Care Syndrome: Clinical Utility Assessment.

JMIR formative research·2026
Same author

Diagnosis-specific patterns for direct ED discharge after physician-staffed HEMS transport in Japan: A nationwide registry study.

The American journal of emergency medicine·2026

Related Experiment Video

Updated: Oct 16, 2025

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
09:52

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Published on: January 15, 2017

17.4K

A prehospital diagnostic algorithm for strokes using machine learning: a prospective observational study.

Yosuke Hayashi1, Tadanaga Shimada1, Noriyuki Hattori1

  • 1Department of Emergency and Critical Care Medicine, Chiba University Graduate School of Medicine, 1-8-1 Inohana, Chiba, 260-8677, Japan.

Scientific Reports
|October 16, 2021
PubMed
Summary
This summary is machine-generated.

Machine learning algorithms demonstrate high accuracy in prehospital stroke diagnosis. These advanced tools accurately predict strokes, large vessel occlusions, and various hemorrhage types, improving emergency medical services.

More Related Videos

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.3K
Prehospital Thrombolysis: A Manual from Berlin
05:52

Prehospital Thrombolysis: A Manual from Berlin

Published on: November 26, 2013

22.0K

Related Experiment Videos

Last Updated: Oct 16, 2025

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide
09:52

Setting Up a Stroke Team Algorithm and Conducting Simulation-based Training in the Emergency Department - A Practical Guide

Published on: January 15, 2017

17.4K
A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia
09:59

A Magnetic Resonance Imaging Protocol for Stroke Onset Time Estimation in Permanent Cerebral Ischemia

Published on: September 16, 2017

14.3K
Prehospital Thrombolysis: A Manual from Berlin
05:52

Prehospital Thrombolysis: A Manual from Berlin

Published on: November 26, 2013

22.0K

Area of Science:

  • Neurology
  • Medical Informatics
  • Emergency Medicine

Background:

  • Accurate prehospital stroke diagnosis is critical for timely treatment.
  • Large vessel occlusions (LVOs) and various stroke types require precise identification.

Purpose of the Study:

  • To evaluate the predictive value of machine learning diagnostic algorithms for strokes and their subcategories in a prehospital setting.
  • To compare the performance of different machine learning models for stroke diagnosis.

Main Methods:

  • Prospective, multicenter observational study involving 1446 adult patients with suspected strokes.
  • Evaluation of five machine learning algorithms: logistic regression, random forest, support vector machine, and eXtreme Gradient Boosting (XGBoost).
  • Algorithms were tested for diagnosing stroke, acute ischemic stroke (with/without LVOs), intracranial hemorrhage, and subarachnoid hemorrhage.

Main Results:

  • eXtreme Gradient Boosting (XGBoost) achieved the highest diagnostic value for overall stroke detection (AUC 0.980).
  • XGBoost demonstrated high predictive value for stroke subcategories: acute ischemic stroke (with/without LVOs) (AUC 0.898/0.882), intracranial hemorrhage (AUC 0.866), and subarachnoid hemorrhage (AUC 0.926).

Conclusions:

  • Prehospital diagnostic algorithms utilizing machine learning, particularly XGBoost, exhibit high predictive accuracy for strokes and their various subtypes.
  • These findings support the integration of machine learning into prehospital stroke diagnostic protocols to enhance patient care and outcomes.