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 Experiment Videos

Accuracy and Reliability of AI Models in Emergency Myocardial Infarction Education.

İbrahim Korkmaz1

  • 1Emergency Department, Izmir City Hospital, Izmir, Turkey.

Emergency Medicine International
|June 15, 2026
PubMed
Summary

Large language models (LLMs) show promise for patient education on acute myocardial infarction (AMI). ChatGPT-4o demonstrated superior accuracy, while Claude 3.7 offered enhanced readability for AMI information.

Related Concept Videos

Cardiopulmonary Resuscitation III: AED Use01:23

Cardiopulmonary Resuscitation III: AED Use

Introduction to AEDAn Automated External Defibrillator (AED) is a portable medical device that analyzes the heart's rhythm and, if necessary, delivers an electrical shock to help the heart re-establish an effective rhythm during sudden cardiac arrest (SCA). SCA occurs when the heart suddenly and unexpectedly stops beating, leading to a loss of blood flow to the brain and other vital organs. In such emergencies, time is of the essence, and using an AED, combined with Cardiopulmonary...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prediction of Early Clinical Deterioration in Acute Pancreatitis: A Machine Learning-based Approach.

Journal of clinical gastroenterology·2026
See all related articles

Area of Science:

  • Medical Informatics
  • Artificial Intelligence in Healthcare
  • Patient Education

Background:

  • Acute myocardial infarction (AMI) is a significant global health concern.
  • Large language models (LLMs) are increasingly utilized for patient education.
  • This study assesses LLM performance in providing educational content on AMI.

Purpose of the Study:

  • To evaluate the accuracy, reliability, and readability of three leading LLMs (ChatGPT-4o, Claude 3.7 Sonnet, Gemini Advanced 2.0 Flash) for patient education on acute myocardial infarction (AMI).
  • To compare the performance of these LLMs across different domains of AMI knowledge, including general information, diagnostics, and treatment.

Main Methods:

  • A cross-sectional study was conducted in February-March 2025.
  • Three LLMs were presented with 30 patient-focused questions about AMI, covering disease knowledge, diagnostics, and treatment.
Keywords:
artificial intelligenceeducation of patientsemergency servicehospitalmyocardial infarction

Related Experiment Videos

  • Responses were evaluated by emergency medicine experts for accuracy, reliability, and readability using Likert scales and established tools (DISCERN, EQIP).

    • Main Results:

    • ChatGPT-4o achieved the highest accuracy (4.38 ± 0.38), outperforming Claude 3.7 (4.09 ± 0.55) and Gemini 2.0 (3.92 ± 0.41) (p < 0.001).
    • ChatGPT-4o excelled in general information and diagnostics, while Claude 3.7 showed superiority in treatment-related content and produced significantly more readable responses across all indices.
    • All models demonstrated good reliability, with no significant differences observed between them.

    Conclusions:

    • LLMs offer potential for enhancing patient education on AMI, with ChatGPT-4o providing superior accuracy and Claude 3.7 offering better readability.
    • This study is the first to compare these LLMs for AMI education in an emergency setting.
    • Physician oversight remains crucial for the safe and effective use of LLMs in emergency medicine patient education.