Category Ranking
98%
Total Visits
921
Avg Visit Duration
2 minutes
Citations
20
Article Abstract
Background: Paroxysmal atrial fibrillation (AF) often eludes early diagnosis, resulting in significant morbidity and mortality. Artificial intelligence (AI) has been used to predict AF from sinus rhythm electrocardiograms (ECGs), but AF prediction using sinus rhythm mobile electrocardiograms (mECG) remains unexplored.
Objective: The purpose of this study was to investigate the utility of AI to predict AF events prospectively and retrospectively using sinus rhythm mECG data.
Methods: We trained a neural network to predict AF events from sinus rhythm mECGs obtained from users of the Alivecor KardiaMobile 6L device. We tested our model on sinus rhythm mECGs within ±0-2 days, ±3-7 days, and ±8-30 days from AF events to determine the optimal screening window. Finally, we tested our model on mECGs from before an AF event to determine whether AF can be predicted prospectively.
Results: We included 73,861 users with 267,614 mECGs (mean age 58.14 years; 35% women). Users with paroxysmal AF contributed 60.15% of mECGs. Model performance on the test set comprising control and study samples across all windows of interest showed an area under the curve (AUC) score of 0.760 (95% confidence interval [CI] 0.759-0.760), sensitivity of 0.703 (95% CI 0.700-0.705), specificity of 0.684 (95% CI 0.678-0.685), and accuracy of 69.4% (95% CI 0.692-0.700). Model performance was better on ±0-2 day samples (sensitivity 0.711; 95% CI 0.709-0.713) and worse on the ±8-30 day window (sensitivity 0.688; 95% CI 0.685-0.690), with performance on the ±3-7 day window falling in between (sensitivity 0.708; 95% CI 0.704-0.710).
Conclusion: Neural networks can predict AF using a widely scalable and cost-effective mobile technology prospectively and retrospectively.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC9971999 | PMC |
| http://dx.doi.org/10.1016/j.cvdhj.2023.01.002 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Clinical consequences of smartwatch implementation in a cardiology outpatient clinic.
Dan Med J
August 2025
Department of Cardiology, Copenhagen University Hospital - Herlev and Gentofte Hospital.
Introduction: Long-term cardiac monitoring has become more accessible with the advent of consumer-oriented wearable devices. Smartwatches (SWs) hold promise for extended rhythm monitoring owing to their availability and direct electronic health record (EHR) integration. We studied the clinical consequences of SW implementation in patients with palpitations.
View Article and Find Full Text PDFBaricitinib Combination Therapy Demonstrates Significant Improvement in Cardiac Conduction Defects in Rapidly Progressive Systemic Sclerosis: A Case Report.
Open Access Rheumatol
August 2025
Department of Rheumatology and Immunology, the First Affiliated Hospital, Jinan University, Guangzhou, 510632, People's Republic of China.
Objective: To evaluate the efficacy of baricitinib in combination therapy for managing refractory, rapidly progressive systemic sclerosis (SSc) with severe cardiac conduction defects and interstitial lung disease (ILD).
Methods: A 48-year-old male patient with SSc complicated by significant cardiac enlargement, third-degree atrioventricular block, heart failure, progressive ILD, and partial intestinal obstruction was included in the study. Prior treatments with mycophenolate mofetil (MMF), tacrolimus, and cyclophosphamide (CTX) had shown limited efficacy.
Dual-atria rotor modification: A comparative analysis of rotor modification and posterior wall isolation in patients with persistent and long-standing persistent atrial fibrillation.
Heart Rhythm O2
August 2025
Division of Cardiology, Tokyo Metropolitan Ohkubo Hospital, Shinjyuku-ku, Tokyo, Japan.
Background: Various methods have been devised for catheter ablation of persistent atrial fibrillation (AF). However, it remains difficult to understand the mechanism of AF and to determine the optimal method.
Objective: This study aimed to evaluate the effectiveness of rotor modification (RM) compared to posterior wall isolation (PWI) in the treatment of persistent AF.
High-power short-duration vs conventional radiofrequency ablation for atrial fibrillation in patients over 80 years of age: A propensity-score matched cohort analysis.
Heart Rhythm O2
August 2025
Department of Electrophysiology, TUM University Hospital German Heart Center, Munich, Germany.
Background: Data on atrial fibrillation (AF) ablation using high-power short-duration (HPSD) ablation in patients over 80 years are lacking.
Objective: This study aimed to compare the safety and efficacy of paroxysmal and persistent AF ablation using an HPSD (60-90 W/4-8 sec) vs conventional ablation (30-40 W/30 sec) in a propensity score-matched cohort of patients older than 80 years.
Methods: Overall, 232 consecutive patients aged over 80 years undergoing AF ablation were included.
How Often is Multifocal Atrial Tachycardia Mistaken for Atrial Fibrillation in the Emergency Department?
Am J Med Sci
September 2025
The Ruth and Bruce Rappaport Faculty of Medicine, Technion, Israel Institute of Technology, Haifa, Israel; Department of Internal Medicine, Lady Davis Carmel Medical Center, Haifa, Israel.
Objective: Multifocal atrial tachycardia (MAT), characterized by an irregularly irregular rhythm, is often regarded as a clinical imitator of atrial fibrillation (AF). We aimed to evaluate the prevalence of MAT misclassification as AF in the emergency department (ED) setting.
Methods: A retrospective analysis of 1,828 ECGs from patients discharged with AF diagnoses over five years.