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

[Incorporation of the family perspective in the renewal of parent information sheets].

Journal of healthcare quality research·2026
Same author

[Evolution of the perception of the safety culture of healthcare professionals in a pediatric emergency department].

Journal of healthcare quality research·2023
Same author

Simple and complex febrile seizures: is there such a difference? Management and complications in an emergency department.

Neurologia·2022
Same author

Quality of life and psychiatric comorbidities in pediatric patients with Gilles de la Tourette syndrome.

Revista de neurologia·2021
Same author

[Evaluation of the effectiveness of a procedure for identifying patients with allergy in paediatric emergency rooms].

Journal of healthcare quality research·2021
Same author

Video discharge instructions for pediatric gastroenteritis in an emergency department: a randomized, controlled trial.

European journal of pediatrics·2020

Related Experiment Video

Updated: Feb 20, 2026

Computerized Adaptive Testing System of Functional Assessment of Stroke
05:21

Computerized Adaptive Testing System of Functional Assessment of Stroke

Published on: January 7, 2019

6.3K

Artificial intelligence in pediatric stroke: An ally in screening?

I Ojeda-Velázquez1, B Bermejo-González1, M García de Oteyza2

  • 1Pediatric Medical Intern, Pediatrics Department, Hospital General Universitario Gregorio Marañón, Madrid, Spain.

European Journal of Paediatric Neurology : EJPN : Official Journal of the European Paediatric Neurology Society
|February 18, 2026
PubMed
Summary

ChatGPT shows limited utility in diagnosing stroke suspicion or calculating neurological scales in pediatric emergency settings. However, a low stroke probability score may help rule out stroke, suggesting a potential supportive role.

Keywords:
Artificial intelligenceEmergency medical servicesGlasgow coma scaleNeurologyPediatricsStroke

More Related Videos

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

18.0K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

8.1K

Related Experiment Videos

Last Updated: Feb 20, 2026

Computerized Adaptive Testing System of Functional Assessment of Stroke
05:21

Computerized Adaptive Testing System of Functional Assessment of Stroke

Published on: January 7, 2019

6.3K
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

18.0K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

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

Published on: January 11, 2020

8.1K

Area of Science:

  • Pediatric Emergency Medicine
  • Artificial Intelligence in Healthcare
  • Neurology

Background:

  • Evaluating AI tools like ChatGPT for clinical decision support is crucial.
  • Stroke suspicion in children requires accurate and timely diagnosis.
  • Standardized scales (GCS, PEDNIHSS) are vital for neurological assessment.

Purpose of the Study:

  • To assess ChatGPT's diagnostic guidance accuracy for suspected pediatric stroke.
  • To evaluate ChatGPT's ability to predict stroke likelihood.
  • To analyze ChatGPT's performance in calculating the Glasgow Coma Scale (GCS) and Pediatric National Institute of Health Stroke Scale (PEDNIHSS).

Main Methods:

  • Retrospective observational study in a Pediatric Emergency Department.
  • Standardized patient case templates were used in ChatGPT conversations.
  • ChatGPT was prompted for diagnosis, stroke probability, GCS, and PEDNIHSS calculations, with results compared to clinical assessments.

Main Results:

  • ChatGPT demonstrated weak diagnostic guidance concordance (k=0.291) but high sensitivity (90.9%) and low specificity (57.4%).
  • The Area Under the Curve (AUC) for stroke probability prediction was 0.796; a score <4 showed high negative predictive value (93.75%).
  • Concordance for GCS (k=0.227) and PEDNIHSS (k=0.261) calculations was weak.

Conclusions:

  • ChatGPT is currently not suitable for direct diagnostic guidance or scale calculation in suspected pediatric stroke cases.
  • A stroke probability score below 4 generated by ChatGPT may assist in ruling out stroke.
  • ChatGPT could potentially serve as a supplementary tool in pediatric stroke code activations.