Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Electrocardiogram Fundamentals

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...

You might also read

Related Articles

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

Sort by

Same author

Peak QRS/T ratio and the spatial ventricular gradient differentiate acute vs chronic left bundle branch block after transcatheter aortic valve replacement.

Heart rhythm O2·2026

Same author

AI Electrocardiogram as a Potential Surrogate for Septal Fibrosis-Reply.

JAMA cardiology·2026

Same author

AI-ECG classification for Brugada syndrome: A study of machine learning techniques to optimise for limited datasets.

PLOS digital health·2026

Same author

AI-ECG for predicting regurgitant valve disease-addressing implementation challenges.

European heart journal·2026

Same author

Larger spatial ventricular gradient magnitude is associated with higher rates of response to cardiac resynchronization therapy.

Heart rhythm O2·2025

Same author

The cost of explainability in artificial intelligence-enhanced electrocardiogram models.

NPJ digital medicine·2025

Search research articles

Related Experiment Video

Updated: Aug 18, 2025

Semi-automated Optical Heartbeat Analysis of Small Hearts

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

A fully-automated paper ECG digitisation algorithm using deep learning.

Huiyi Wu¹, Kiran Haresh Kumar Patel¹, Xinyang Li¹

¹Imperial College London, National Heart & Lung Institute, London, W12 0NN, UK.

Scientific Reports

|December 5, 2022

Summary

This summary is machine-generated.

We developed an automated tool to digitize paper electrocardiograms (ECGs) for deep learning. This method converts scanned ECGs into digital signals, enabling large-scale analysis for AI-driven cardiac research.

More Related Videos

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

Related Experiment Videos

Last Updated: Aug 18, 2025

Semi-automated Optical Heartbeat Analysis of Small Hearts

Semi-automated Optical Heartbeat Analysis of Small Hearts

Published on: September 16, 2009

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Capturing Dynamic Finger Gesturing with High-resolution Surface Electromyography and Computer Vision

Published on: March 28, 2025

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

Area of Science:

Biomedical Engineering
Artificial Intelligence in Medicine
Cardiology

Background:

Deep learning (DL) models, particularly neural networks (NNs), show promise in analyzing electrocardiograms (ECGs) for predicting cardiac conditions.
A significant barrier to DL in cardiology is the large volume of historical ECGs stored in paper format, unsuitable for computational analysis.
Automated methods are needed to convert these paper ECGs into usable digital data.

Purpose of the Study:

To develop and validate a fully-automated online tool for digitizing paper ECGs.
To enable the use of historical paper ECG data for deep learning applications in cardiology.
To create a user-friendly solution for converting scanned ECGs into digital signals without manual intervention.

Main Methods:

Developed an automated online ECG digitization tool employing horizontal and vertical anchor point detection for image segmentation.
Utilized a dynamical morphological algorithm to extract relevant ECG signal data from segmented lead images.
Validated the tool's performance on 515 digital ECGs, including 45 that were printed, scanned, and re-digitized.

Main Results:

Achieved 99.0% correlation between digitized signals and ground truth for standard 3-by-4 ECGs (n=515) after excluding leads with signal overlap.
Without exclusions, average correlation ranged from 90-97% across leads for 3-by-4 ECGs.
Demonstrated 96% correlation for ECGs that were printed, scanned, and re-digitized, indicating robustness.

Conclusions:

A fully-automated, user-friendly online ECG digitization tool has been successfully developed and validated.
This tool eliminates the need for manual segmentation, facilitating rapid processing of large paper ECG archives.
The developed system is poised to significantly advance deep learning research in cardiology by unlocking historical ECG data.