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

Electrocardiogram Fundamentals01:28

Electrocardiogram Fundamentals

Introduction
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin to...
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...

You might also read

Related Articles

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

Sort by
Same author

Documented Obstructive Sleep Apnea, Cardiometabolic Phenotype, and Rhythm-Related Outcomes After Atrial Fibrillation Ablation: An Observational Cohort Study.

Journal of arrhythmia·2026
Same author

Caregivers' perspectives on family meetings and preparedness for imminent death: A qualitative descriptive study in a palliative care setting.

Palliative medicine·2026
Same author

Discovery of Novel Magnetocardiography Parameters Predicting Future ICD Therapies: Insights From the Magneto-SCD Study.

Circulation. Arrhythmia and electrophysiology·2026
Same author

The Role of Extracellular Vesicles in Vein Graft Disease.

Cells·2026
Same author

Early treatment of Atrial fibrillation for Stroke prevention Trial in acute STROKE (EAST-STROKE): protocol for an international investigator-initiated, prospective, randomised, open, blinded endpoint assessment (PROBE) interventional multi-centre trial.

European stroke journal·2026
Same author

A systematic review of physical activity guidelines for adults with cardio-respiratory diseases: Stepping towards evidence-based recommendations.

Clinical rehabilitation·2026

Related Experiment Video

Updated: Jun 13, 2026

A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis
18:11

A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis

Published on: December 28, 2012

Benchmarking General Purpose Artificial Intelligence for Accessory Pathway Localisation on 12-Lead

Ahmed Abdelrazik1,2,3, Mahmoud Eldesouky1,2,3, Ibrahim Antoun1,2

  • 1Department of Cardiology, University Hospitals of Leicester NHS Trust, Glenfield Hospital, Leicester LE3 9QP, UK.

Journal of Clinical Medicine
|June 12, 2026
PubMed
Summary
This summary is machine-generated.

General-purpose AI models like ChatGPT and Gemini showed poor accuracy and reproducibility in localizing accessory pathways from ECGs for Wolff-Parkinson-White syndrome. Their current clinical use for this purpose is not supported due to unreliable performance.

Keywords:
ECG interpretationWolff–Parkinson–Whiteaccessory pathwayartificial intelligenceelectrophysiologylarge language model

More Related Videos

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
10:17

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

Related Experiment Videos

Last Updated: Jun 13, 2026

A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis
18:11

A Research Method For Detecting Transient Myocardial Ischemia In Patients With Suspected Acute Coronary Syndrome Using Continuous ST-segment Analysis

Published on: December 28, 2012

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System
10:17

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

Area of Science:

  • Cardiology
  • Artificial Intelligence in Medicine
  • Medical Diagnostics

Background:

  • Accurate localization of accessory pathways is crucial for pre-procedural planning in Wolff-Parkinson-White syndrome.
  • General-purpose AI models' reliability for ECG-based accessory pathway localization is largely unknown.
  • Purpose-built AI models have shown promise in ECG interpretation.

Purpose of the Study:

  • To evaluate the diagnostic accuracy and reproducibility of two general-purpose multimodal large language models (ChatGPT 5 Thinking and Gemini 2.5 Pro) for accessory pathway localization using 12-lead ECGs.
  • To compare AI performance against an electrophysiology-confirmed reference standard.
  • To assess the reliability of these AI systems across repeated analyses.

Main Methods:

  • Retrospective, single-center diagnostic accuracy study involving 49 patients with confirmed accessory pathways.
  • Anonymized 12-lead ECGs were analyzed by ChatGPT 5 Thinking and Gemini 2.5 Pro using predefined EASY-WPW categories.
  • Each model underwent three independent, context-reset runs to assess repeated-run accuracy and reproducibility.

Main Results:

  • Both models demonstrated poor performance, with ChatGPT 5 Thinking achieving 19.0% and Gemini 2.5 Pro achieving 12.2% accuracy, both below the no-information baseline of 36.7%.
  • Very low exact output consistency (2/49 for ChatGPT, 0/49 for Gemini) and frequent no-consensus outputs (30/49 and 26/49, respectively) were observed.
  • Reproducibility was poor, with limited abstention ('unable to identify' responses).

Conclusions:

  • General-purpose multimodal large language models exhibit inadequate accuracy and reproducibility for localizing accessory pathways from 12-lead ECGs.
  • Current findings do not support the clinical application of these AI models for accessory pathway localization.
  • Future advancements are expected from specialized, signal-native, or rigorously validated cardiac AI systems.