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

You might also read

Related Articles

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

Sort by
Same author

Microstrip Antenna Design and Its Application in Moisture Detection.

Sensors (Basel, Switzerland)·2026
Same author

A Synergistic Dual-Antibody Cocktail Targeting α-Toxin Protects Against Invasive <i>Staphylococcus aureus</i> Infection by Neutralizing Virulence and Enhancing Host Defense.

MedComm·2026
Same author

[Advances in the application of the HEART score in patients with acute coronary syndromes].

Zhong nan da xue xue bao. Yi xue ban = Journal of Central South University. Medical sciences·2026
Same author

Latent profiles of actual and perceived motor competence are associated with physical activity and BMI in childhood: a latent profile analysis.

Scientific reports·2026
Same author

Multivalent Aptamers: Contemporary Engineering Strategies and Biomedical Applications.

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Real-time lane-level abnormal traffic detection on freeways using sparse telematics data.

Accident; analysis and prevention·2026

Related Experiment Video

Updated: Jan 2, 2026

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

2.0K

An incremental learning system for atrial fibrillation detection based on transfer learning and active learning.

Haotian Shi1, Haoren Wang1, Chengjin Qin1

  • 1School of Mechanical Engineering, Shanghai Jiao Tong University, 800 Dongchuan Road, Shanghai 200240, PR China.

Computer Methods and Programs in Biomedicine
|December 2, 2019
PubMed
Summary

This study introduces a cost-effective incremental learning system for detecting atrial fibrillation (AF). The new method significantly reduces labeling costs while continuously improving AF detection model performance.

Keywords:
Active learningAtrial fibrillationDeep neural networkElectrocardiogram (ECG)Transfer learning

More Related Videos

A New Single Chamber Implantable Defibrillator with Atrial Sensing: A Practical Demonstration of Sensing and Ease of Implantation
16:40

A New Single Chamber Implantable Defibrillator with Atrial Sensing: A Practical Demonstration of Sensing and Ease of Implantation

Published on: February 28, 2012

26.7K
High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
09:17

High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation

Published on: July 29, 2011

15.2K

Related Experiment Videos

Last Updated: Jan 2, 2026

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
08:10

Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation

Published on: July 20, 2022

2.0K
A New Single Chamber Implantable Defibrillator with Atrial Sensing: A Practical Demonstration of Sensing and Ease of Implantation
16:40

A New Single Chamber Implantable Defibrillator with Atrial Sensing: A Practical Demonstration of Sensing and Ease of Implantation

Published on: February 28, 2012

26.7K
High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation
09:17

High-Resolution Endocardial and Epicardial Optical Mapping in a Sheep Model of Stretch-Induced Atrial Fibrillation

Published on: July 29, 2011

15.2K

Area of Science:

  • Biomedical Engineering
  • Machine Learning
  • Cardiology

Background:

  • Atrial fibrillation (AF) is a prevalent arrhythmia requiring accurate detection.
  • Existing automatic AF detection models need continuous improvement, but updates are costly.
  • Developing low-cost methods for updating AF detection models is crucial.

Purpose of the Study:

  • To develop a low-cost method for selecting learning samples for AF detection.
  • To create an incremental learning system for continuous AF model improvement.
  • To reduce the overall cost associated with updating AF detection models.

Main Methods:

  • A loop-locked framework integrating AF diagnosis, label query, and model fine-tuning was proposed.
  • A novel multiple-input deep neural network (MIDNN) was pre-trained using transfer learning.
  • An active learning strategy combining feature information and prediction uncertainty was used for incremental learning.

Main Results:

  • The system achieved high initial performance (Acc: 87.40%, Sen: 97.46%, PPV: 81.11%) on the MIT-BIH database.
  • Performance improved to (Acc: 97.53%, Sen: 100.00%, PPV: 95.29%) after 14 iterations.
  • Labeling cost was reduced by 90.67% through efficient sample selection.

Conclusions:

  • The proposed system enables continuous model updates for AF detection with over 90% cost reduction.
  • The MIDNN model and the novel active learning strategy are effective for AF detection.
  • The framework shows potential for extension to other biomedical applications.