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

Classification of Signals01:30

Classification of Signals

In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
Instrumentation Amplifier01:25

Instrumentation Amplifier

An electrocardiography (ECG) machine is an essential piece of medical equipment used to monitor the electrical activity of the heart. It operates by detecting small electrical changes on the skin that result from the depolarization of the heart muscle during each heartbeat. However, these signals are in the microvolt range and can be easily overwhelmed by noise or interference.
To overcome this challenge, an ECG machine utilizes an instrumentation amplifier. This specialized amplifier is...
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...
Clipper Circuit01:18

Clipper Circuit

A clipper circuit is a fundamental wave-shaping device that harnesses the unique properties of diodes to alter and control waveform characteristics. This technology is widely used in electronic devices, especially in television and radar communication systems, where it enhances waveform modulation in both transmitters and receivers.
The operation of a clipper circuit can be exemplified by analyzing a dual-clipper configuration setup that integrates two ideal diodes, each paired with a biasing...
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...
Correlation between ECG and Cardiac Cycle01:25

Correlation between ECG and Cardiac Cycle

The electrical signals recorded on an electrocardiogram (ECG) occur before the mechanical processes of contraction and relaxation during the cardiac cycle.
A cardiac action potential originates in the SA node and spreads throughout the atria and the AV node in approximately 0.03 seconds. This results in the P wave in an ECG and triggers atrial contraction. The action potential is then briefly slowed at the AV node, allowing the atria to contract and fill the ventricles with blood before...

You might also read

Related Articles

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

Sort by
Same author

Bioelectrocatalyst for O<sub>2</sub> Reduction Based on a Novel Recombinant Two-Domain Laccase from <i>Streptomyces ochraceisleroticus</i> Immobilized on Naphthyl-Modified MWCNTs.

International journal of molecular sciences·2025
Same author

Machine learning-based detection of cardiovascular disease using ECG signals: performance vs. complexity.

Frontiers in cardiovascular medicine·2023
Same author

New drugs and stock market: a machine learning framework for predicting pharma market reaction to clinical trial announcements.

Scientific reports·2023
Same author

Mitigating First-Cycle Capacity Losses in NMC811 via Lithicone Layers Grown by Molecular Layer Deposition.

ACS applied materials & interfaces·2023
Same author

Assessing Long-Term Cycling Stability of Single-Crystal Versus Polycrystalline Nickel-Rich NCM in Pouch Cells with 6 mAh cm<sup>-2</sup> Electrodes.

Small (Weinheim an der Bergstrasse, Germany)·2022
Same author

The lived experience of female genital cutting (FGC) in Somali-Canadian women's daily lives.

PloS one·2018

Related Experiment Videos

Zero-shot classification of ECG signals using CLIP-based models.

Navmeet Jassal1, Konstantin Egorov2, Semen Budennyy3

  • 1Department of Computer Science, National Research University Higher School of Economics, Saint Petersburg, 190121, Russia. navmeetjassal@gmail.com.

Scientific Reports
|July 3, 2026
PubMed
Summary

Contrastive Language-Image Pre-training (CLIP) models show promise for zero-shot electrocardiogram (ECG) classification, adapting to new diagnostic classes without extensive retraining. This offers a flexible alternative for evolving clinical needs.

Keywords:
CLIPClassificationECGZero-shot learning

Related Experiment Videos

Area of Science:

  • Cardiology
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional electrocardiogram (ECG) classification models require extensive labeled data for each diagnostic class, hindering adaptability to novel conditions.
  • The adaptability of AI models to new diagnostic classes is crucial for evolving clinical needs in healthcare.

Purpose of the Study:

  • To evaluate the effectiveness of Contrastive Language-Image Pre-training (CLIP) models for zero-shot ECG classification across diverse datasets and diagnostic categories.
  • To assess the impact of various encoder architectures and training dataset sizes on CLIP model performance for both in-distribution and out-of-distribution generalization.

Main Methods:

  • Trained and evaluated 24 CLIP-based models using different image and text encoders on 27 seen ECG classes across three datasets (PTB-XL, Ningbo, Gerogia).
  • Assessed zero-shot classification performance on 11 unseen ECG classes, including internal evaluation (Experiment A) and external validation on independent datasets (SPH, CODE-15% - Experiment B).
  • Investigated the influence of training dataset size, encoder architectures, and pretraining on generalization capabilities.

Main Results:

  • The top-performing CLIP models achieved a macro-averaged ROC-AUC of 0.70 for zero-shot out-of-distribution classification and 0.70 for zero-shot in-distribution classification.
  • For out-of-distribution classification using classic training, the best models reached a ROC-AUC of 0.83.
  • CLIP-based models demonstrated meaningful classification of ECG conditions beyond their training scope.

Conclusions:

  • CLIP-based models offer a flexible and adaptable approach to ECG classification, outperforming traditional methods in zero-shot scenarios.
  • These findings suggest CLIP models can effectively classify unseen ECG conditions, providing a valuable alternative for dynamic clinical environments.
  • The study highlights the potential of CLIP for developing more versatile and data-efficient diagnostic tools in cardiology.