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

Correlation between ECG and Cardiac Cycle01:25

Correlation between ECG and Cardiac Cycle

13.0K
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...
13.0K
Electrocardiogram01:29

Electrocardiogram

9.0K
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...
9.0K
Pulse rhythm01:30

Pulse rhythm

1.6K
Pulse rhythm refers to the pattern of pulsations within specific intervals, offering valuable insights into the regularity or irregularity of the heart's beats as observed through the pattern of pulsation within specific intervals. A regular pulse exhibits a consistent heart rate with uniform waveforms and pulsation force, variations of which can be classified as normal, weak, or bounding.
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
1.6K

You might also read

Related Articles

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

Sort by
Same author

A Dataset of Microelectrode Recordings from Deep Brain Stimulation Procedures.

Scientific data·2026
Same author

Theoretical and Scientific Underpinnings of Peripheral Muscle Electrostimulation in Cardiac Rehabilitation of the Elderly: A Systematic Review.

Journal of clinical medicine·2026
Same author

The dataset for extending EMNIST evaluation.

Scientific data·2026
Same author

A novel method of diagnosing and monitoring cardiac arrhythmias in patients with chronic lymphocytic leukemia treated with ibrutinib.

Polish archives of internal medicine·2025
Same author

Gold standard, multi-genre dataset for named entity recognition and linking.

Scientific data·2025
Same author

Guidelines for the management of hypertension in Poland 2024 - the position paper of the Polish Society of Hypertension and Polish Cardiac Society experts.

Kardiologia polska·2025

Related Experiment Video

Updated: Apr 22, 2026

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

3.4K

Low-latency HRV analysis from ultra-short ECG windows using a modular deep-learning framework.

Jan Dobrosolski1, Julian Szymański2, Dariusz Kozłowski3

  • 1Faculty of Electronics, Telecommunications and Informatics, Gdansk University of Technology, Narutowicza 11/12, Gdańsk, 80-233, Poland. jan.dobrosolski@pg.edu.pl.

Scientific Reports
|April 20, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning framework for real-time heart rate variability (HRV) analysis. The model achieves superior accuracy and robustness in estimating RMSSD, outperforming traditional methods on diverse ECG datasets.

Keywords:
Deep learningECGHRVLow-Latency InferenceRMSSDSignal analysis

More Related Videos

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
06:07

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

4.1K
Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.9K

Related Experiment Videos

Last Updated: Apr 22, 2026

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis
08:22

Author Spotlight: Advancing the Study of Brain-Heart Interplay with a Comprehensive EEGLAB Plugin for Multimodal Signal Analysis

Published on: April 26, 2024

3.4K
Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
06:07

Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice

Published on: May 23, 2021

4.1K
Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy
11:54

Simultaneous Video-EEG-ECG Monitoring to Identify Neurocardiac Dysfunction in Mouse Models of Epilepsy

Published on: January 29, 2018

25.9K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Cardiology

Background:

  • Accurate heart rate variability (HRV) analysis is crucial for assessing cardiac health.
  • Existing methods for HRV analysis, particularly RMSSD estimation, face challenges with noisy or pathological ECG data and real-time processing.
  • Deep learning offers potential for robust and efficient physiological signal analysis.

Purpose of the Study:

  • To develop a universal, modular deep learning framework for low-latency, streaming-compatible HRV analysis.
  • To utilize RMSSD as an exemplar metric, demonstrating the framework's capability in robust estimation.
  • To create a single, deployable model that integrates quality screening and RMSSD estimation.

Main Methods:

  • A convolutional autoencoder was pretrained and used as a frozen encoder to generate latent representations from ECG windows.
  • Task-specific heads, including BiLSTM adapters, Conv1D refinement, and attention pooling, operated on the shared latent representation.
  • A discriminator head screened low-quality ECG windows, and a regression head estimated RMSSD, with a gated inference block ensuring estimation only on valid windows.

Main Results:

  • The proposed deep learning model achieved 92.12% accuracy and 95.43% F1 score on combined datasets, significantly outperforming classical baselines (HeartPy and NeuroKit2).
  • RMSSD estimation accuracy was substantially improved, with a mean absolute error (MAE) of 10.56 ms (vs. 45.12 ms / 27.93 ms) and drastically reduced tail errors.
  • The model demonstrated strong performance on out-of-distribution data (Apple Watch subset) and achieved real-time processing with low latency (15.0 ms at batch size 1) and a compact model size.

Conclusions:

  • The developed deep learning framework provides a robust, accurate, and efficient solution for real-time HRV analysis, particularly for RMSSD estimation.
  • The integrated quality screening mechanism significantly enhances the reliability of HRV metrics, even with noisy or pathological ECG signals.
  • The model's compact size and real-time capabilities make it suitable for deployment in various clinical and wearable applications.