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

Pulse rhythm01:30

Pulse rhythm

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 muscle...
Pulse Oximetry01:24

Pulse Oximetry

Pulse oximetry, or SpO2, is a non-invasive method for continuously monitoring arterial oxygen saturation (SaO2). This procedure involves attaching a probe or sensor to the patient's fingertip, forehead, earlobe, or nose bridge. The sensor works by detecting changes in oxygen saturation levels through light signals generated by the oximeter and reflected by the pulsing blood under the probe.
Purpose
Average SpO2 values are greater than 95%. If the readings fall below 90%, it indicates that...

You might also read

Related Articles

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

Sort by
Same author

Comparison of Ablation Index-Guided Lesion Size in nGEN and SMARTABLATE: An Ex Vivo Porcine Heart Study.

Pacing and clinical electrophysiology : PACE·2026
Same author

Effects of early continuous renal replacement therapy in critically ill patients requiring ECMO treatment: results of a randomised controlled trial.

Open heart·2026
Same author

Proteogenomics of Hypertrophic Cardiomyopathy Reveals Subtype-Specific Therapy.

Circulation research·2026
Same author

Ursodeoxycholic acid inhibits platelet activation and thrombosis via TREM2: Evidence from mouse models and human studies.

British journal of pharmacology·2026
Same author

Heart Failure Medication Withdrawal in Patients With Improved Cardiac Function After Atrial Fibrillation Ablation: The DEFINITION-AF Pilot Randomized Clinical Trial.

JAMA network open·2026
Same author

Trends in colorectal cancer mortality among younger versus older adults in 49 countries.

Journal of the National Cancer Institute·2026

Related Experiment Video

Updated: Jul 15, 2026

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

A Dual-Modal Wearable PPG Smartwatch with AI-Enhanced Correction for High-Accuracy and Continuous AF Burden

Song Zuo1, Jinglei Wang2, Xin Wang3

  • 1Department of Cardiology, Beijing Anzhen Hospital, Capital Medical University, National Clinical Research Center for Cardiovascular Diseases, Beijing, China.

Advanced Science (Weinheim, Baden-Wurttemberg, Germany)
|July 14, 2026
PubMed
Summary

An AI system combining smartwatch PPG and ECG improves atrial fibrillation burden monitoring. This dual-modal approach enhances accuracy for better patient management and cardiovascular screening.

Keywords:
AF burdenAI‐correctionconvolutional neural networkslong short‐term memoryphotoplethysmography

More Related Videos

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
05:51

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program
04:24

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program

Published on: April 19, 2019

Related Experiment Videos

Last Updated: Jul 15, 2026

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
05:03

Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function

Published on: December 11, 2019

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health
05:51

Assessing the Accuracy of Fitness Smartwatch Data for Cardiovascular and Physical Activity Monitoring: A Validation Study in Digital Health

Published on: February 21, 2025

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program
04:24

A Novel Digital Platform for a Monitored Home-based Cardiac Rehabilitation Program

Published on: April 19, 2019

Area of Science:

  • Cardiology
  • Biomedical Engineering
  • Artificial Intelligence

Background:

  • Atrial fibrillation (AF) significantly elevates stroke and heart failure risks.
  • Accurate, continuous AF burden monitoring in daily life is challenging.
  • Smartwatch photoplethysmography (PPG) offers continuous monitoring but struggles with signal noise and complex rhythms.

Purpose of the Study:

  • To develop and validate an AI-enhanced dual-modal framework for accurate AF burden quantification.
  • To improve AF burden estimation beyond PPG-only devices using intermittent ECG data.
  • To assess the clinical practicality and scalability of the system for long-term AF monitoring.

Main Methods:

  • Developed a hybrid convolutional neural network-long short-term memory model integrating watch-based PPG (W-PPG) and watch-based ECG (W-ECG).
  • Utilized high-fidelity W-ECG segments as dynamic anchors to correct W-PPG classifications.
  • Conducted a prospective validation study with 1,054 AF patients undergoing catheter ablation, comparing against patch-based ECG.

Main Results:

  • The AI-enhanced system achieved 98.60% sensitivity and 99.27% specificity post-ECG correction.
  • Mean absolute percentage error for AF burden decreased by 23.4% (from 1.11% to 0.85%).
  • High correlation (Pearson r=0.9988) was maintained between the system and reference standard.

Conclusions:

  • The dual-modal AI framework provides a scalable and clinically practical solution for long-term AF monitoring.
  • This approach significantly improves AF burden estimation accuracy compared to PPG-only devices.
  • The system holds potential for personalized AF management and large-scale cardiovascular screening.