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 Video

Updated: Jun 21, 2026

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

MSCA-TNet based deep learning method for ECG arrhythmia classification.

Songjian Huang1,2, Senpeng Chen2, Zihao Guo3

  • 1Applied Technology Engineering Center of Fujian Provincial Higher Education for Visual Perception and Intelligent Analysis, Quanzhou, 362000, Fujian, China.

Scientific Reports
|June 19, 2026
PubMed
Summary

Related Concept Videos

Dysrhythmias II: Classification of Tachyarrhythmias01:28

Dysrhythmias II: Classification of Tachyarrhythmias

Tachyarrhythmias are a type of dysrhythmia where the heart rate exceeds 100 beats per minute. Here are some common types of tachyarrhythmias:Sinus TachycardiaSinus tachycardia originates from increased impulses from the sinus node, leading to an elevated heart rate. It is often triggered by stress, fever, or exercise.Patients may experience palpitations, a sensation of a racing heart, dizziness, and chest discomfort.Causes and Risk Factors: Common causes include physical exertion, emotional...

You might also read

Related Articles

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

Sort by
Same author

Engineering a Thiamine-Dependent Benzoylformate Decarboxylase for Stereodivergent Radical C(sp<sup>3</sup>)-C(sp<sup>3</sup>) Bond Formation.

Journal of the American Chemical Society·2026
Same author

CD40LG/CD28-Mediated Rho GTPase Signaling Drives Survival and Chemoresistance in Non-ETP T-ALL.

International journal of molecular sciences·2026
Same author

Electrical regulation of multilayer graphene and graphene nanoscrolls using deionized water as a gate dielectric.

Nanoscale·2026
Same author

[Identification, expression profiling, and natural allelic variation analysis of the Sbsgr gene family in sorghum].

Sheng wu gong cheng xue bao = Chinese journal of biotechnology·2026
Same author

Highly synergistic degradation of fluoroquinolones driven by redox dual channel mechanism in Fe(Ⅲ)-mediated thermally activated persulfate system.

Journal of hazardous materials·2026
Same author

Rapid assessment of local disease control measures against the Marburg virus outbreak in Ethiopia in late 2025.

Infectious Disease Modelling·2026
This summary is machine-generated.

This study introduces an advanced AI model for accurate arrhythmia detection from noisy electrocardiography (ECG) signals. The method effectively handles signal noise and imbalanced data, improving diagnostic efficiency.

Area of Science:

  • Biomedical Engineering
  • Artificial Intelligence in Healthcare
  • Cardiology

Background:

  • Electrocardiography (ECG) is crucial for cardiac monitoring but susceptible to noise and class imbalance in datasets.
  • Wearable ECG devices often yield low-quality signals due to motion and environmental factors.
  • Manual arrhythmia diagnosis is labor-intensive, prone to bias, and requires expert interpretation.

Purpose of the Study:

  • To develop a robust automated arrhythmia detection algorithm for improved diagnostic accuracy and efficiency.
  • To address challenges of noise interference and class imbalance in ECG signal processing.
  • To enhance the clinical utility of ECG analysis for cardiovascular disease diagnosis.

Main Methods:

  • Discrete Wavelet Transform (DWT) for noise elimination.
Keywords:
Arrhythmia detectionAttentionDeep learningECG classificationTransformer

Related Experiment Videos

Last Updated: Jun 21, 2026

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

  • SMOTE-Tomek for mitigating class imbalance in datasets.
  • Proposed MSCA-TNet: a hybrid architecture with Adaptive Channel Attention (ACA) and Transformer for feature extraction.

    • Main Results:

    • The MSCA-TNet model achieved high performance on benchmark datasets (MIT-BIH and INCART).
    • Macro-average accuracies reached 93.97% and 98.79%.
    • Overall accuracies were 98.88% and 99.47%, demonstrating robust arrhythmia detection.

    Conclusions:

    • The proposed MSCA-TNet effectively extracts local and global features from ECG sequences.
    • The ACA module enhances discriminative feature identification.
    • The developed algorithm offers a promising solution for automated, accurate arrhythmia detection, easing clinical workload.