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

Performance of Vision-Enabled Large Language Models in Image-Based Electrocardiogram Interpretation: Exploratory

Nibras Soubh1,2, Eva Rasenack1,2, Helge Haarmann1,2

  • 1Department of Cardiology and Pneumology, University Medical Center Göttingen (UMG), Robert-Koch-Str. 40, Göttingen, 37075, Germany, 49 15114609645.

Journal of Medical Internet Research
|June 4, 2026
PubMed
Summary

Related Concept Videos

Electrocardiogram01:29

Electrocardiogram

An electrocardiogram (ECG or EKG) is a critical diagnostic tool that records the electrical signals produced by the heart during each heartbeat. This recording is achieved through electrodes placed strategically on the arms, legs, and chest. The electrocardiograph amplifies these signals and produces 12 distinct tracings, offering a comprehensive understanding of the heart's electrical activity.
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and the T...
Imaging Studies for Cardiovascular System I:Echocardiography01:17

Imaging Studies for Cardiovascular System I:Echocardiography

Cardiac imaging studies encompass a wide range of noninvasive and minimally invasive techniques designed to visualize the heart's structure and function in detail. One such technique is echocardiography, which uses high-frequency ultrasound waves to produce detailed images of the heart, known as echocardiograms.
Indications: Echocardiography is utilized to diagnose heart failure, valve disorders, and myocardial infarction. It also assesses cardiac structures' size, shape, and motion, evaluates...

You might also read

Related Articles

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

Sort by
Same author

First Experience With Extravascular Implantable Cardioverter-Defibrillator Under Deep Sedation.

Pacing and clinical electrophysiology : PACE·2026
Same author

<i>CAV1</i>-A Susceptibility Gene for Atrial Fibrillation: The Impact of Coding and Noncoding Variants.

Journal of the American Heart Association·2026
Same author

Mechanosensitive ion channels as novel targets in osteoporosis.

Journal of bone and mineral research : the official journal of the American Society for Bone and Mineral Research·2025
Same author

Smartwatch-enabled early detection and treatment of cardiomyopathy induced by premature atrial contractions: a case report.

European heart journal. Case reports·2025
Same author

Disease mechanism and novel drug therapies for atrial fibrillation.

Medizinische Genetik : Mitteilungsblatt des Berufsverbandes Medizinische Genetik e.V·2025
Same author

First experience with a new tool for automatic mapping of fragmented signals in a case report of cardioneuroablation.

Future cardiology·2025
Same journal

American Medical Association Shares Framework to Address the Escalating Risk of Physician Deepfakes.

Journal of medical Internet research·2026
Same journal

Online Social Interaction, Neighborhood Perception, and the Mediating Role of Social Capital in Charitable Giving for Seriously Ill Patients: Cross-Sectional Study.

Journal of medical Internet research·2026
Same journal

Evaluation of Large Language Models for Structured Data Extraction From Interstitial Lung Disease Clinical Notes: Comparative Study.

Journal of medical Internet research·2026
Same journal

Digital Interventions Targeting Parents to Improve Early Childhood Movement, Nutrition, and Sleep Behaviors: Systematic Review.

Journal of medical Internet research·2026
Same journal

Physical Activity Interventions Using Digital Health Interventions for Cancer-Related Fatigue in People With a History of Cancer: Scoping Review.

Journal of medical Internet research·2026
Same journal

Effectiveness of a Home-Based and Group-Based Tele-Exercise Program for Breast Cancer Survivors: Pilot Randomized Controlled Trial.

Journal of medical Internet research·2026
See all related articles
This summary is machine-generated.

Vision-enabled large language models (VE-LLMs) show moderate performance in interpreting electrocardiograms (ECGs), but their low sensitivity and agreement with expert interpretation limit clinical use.

Area of Science:

  • Artificial Intelligence in Medicine
  • Medical Image Analysis
  • Cardiology

Background:

  • Vision-enabled large language models (VE-LLMs) offer potential for flexible and explainable medical image interpretation.
  • Systematic assessment of VE-LLM performance on real-world clinical data like 12-lead electrocardiograms (ECGs) is lacking.

Purpose of the Study:

  • Evaluate the diagnostic accuracy and reliability of generalist VE-LLMs for interpreting real-world ECG images.
  • Compare the performance of generalist VE-LLMs against specialized ECG LLMs.

Main Methods:

  • Tested 6 generalist VE-LLMs and 2 specialized ECG LLMs on 70 deidentified ECG images.
  • Standardized prompts requested 9 ECG determinations (rhythm, blocks, QTc, etc.).
  • Expert consensus served as the reference standard; outputs evaluated using diagnostic metrics.
Keywords:
AIECGLLMsartificial intelligenceelectrocardiographylarge language modelsmachine learning

Related Experiment Videos

Main Results:

  • Overall balanced accuracy for generalist VE-LLMs ranged from 50.1% to 61.8%.
  • Sensitivity for key findings like atrial fibrillation, AV block, and ST-segment deviation was notably low across generalist models.
  • Agreement with expert interpretation was poor-to-fair (Cohen κ ≤0.39). Specialized models showed improved performance in specific tasks.

Conclusions:

  • Generalist VE-LLMs demonstrate moderate overall performance but insufficient sensitivity and expert agreement for clinical ECG interpretation.
  • Performance is inconsistent across models and diagnostic categories, precluding current clinical deployment.
  • Specialized ECG LLMs show promise but require further validation.