EUVIMEDSkopri EUVIMED
Open access

Prediction of Atrial Fibrillation Occurrence With Handheld Mobile Electrocardiogram: Deep Learning Model Development Using Real-World Data

Minje Park iD, Hyun Jin Ahn iD, Yeongyeon Na iD, Sunghoon Joo iD, Young Ho Lee iD, Seongwoo Han iD, Myung Soo Park iD, Dae Young Cheon iD, Jeen Hwa Lee iD, Ki Hong Lee iD

JMIR Medical Informatics · 2026-08-20 · 14 · e87142-e87142

DOI: 10.2196/87142 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2026-08-20. Written by Minje Park and 9 co-authors. Institution: VUNO Inc., Seoul, Republic of Korea. Major MEDLINE topics: Atrial Fibrillation, Deep Learning, Electrocardiography. 40 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Atrial fibrillation (AF) is a common arrhythmia associated with an increased risk of stroke and heart failure. To improve prevention, recent studies have used deep learning models to identify at-risk individuals early from normal sinus rhythm (NSR). However, studies using mobile electrocardiogram (mECG) in outpatient, real-world settings remain underexplored.

Objective

The study aimed to develop and evaluate deep learning models using a real-world limb-lead mECG database to predict the short-term occurrence of AF from NSR recordings. Methods mECG data were collected from real-world users of commercially available handheld mECG devices capable of capturing 6 limb leads. AF occurrence was defined as an AF event within a predefined time window (7, 14, or 31 d) from the date of the NSR recording. Transformer-based prediction models were developed for limb-lead and lead I input configurations using a multistage training approach with self-supervised pretraining and domain adaptation, drawing on both open, large-scale clinical 12-lead ECG and proprietary real-world mECG databases. The models were evaluated in an internal real-world cohort and explored in an external cohort as a proof of concept via time-to-event analysis.

Results

Between March 2023 and November 2024, 386,519 mECGs were acquired from 8206 users. There were 18,949, 25,206, and 33,524 AF incidences within the 7-, 14-, and 31-day time windows. The models were pretrained with 787,257 12-lead ECGs and 202,689 mECGs, then fine-tuned to predict AF occurrence using 97,447 labeled mECGs. The limb-lead models achieved areas under the receiver operating characteristic curves (AUROCs) of 0.793, 0.785, and 0.787 for 7-, 14-, and 31-day predictions on the internal cohort, respectively, with a user-level AUROC of 0.702 for the 31-day prediction. These models significantly outperformed the lead I models ( P

Subjects

MeSH terms (MEDLINE)

Atrial FibrillationDeep LearningElectrocardiographyHumansFemaleMaleMiddle AgedPredictive Learning ModelsAged

Author keywords

AIatrial fibrillationdeep learningdigital healthdomain adaptationelectrocardiogrammobile healthnormal sinus rhythmreal-world dataself-supervised learning

Authors and institutions

  • VUNO Inc., Seoul, Republic of Korea.
  • Department of Biomedical Sciences, Chonnam National University Graduate School, Gwangju, Republic of Korea.
  • Department of Cardiovascular Medicine, Chonnam National University Hospital, The Heart Center of Chonnam National University Hospital, 42 Jaebongro, Dong-gu, Gwangju, 61469, Republic of Korea, 82 62-220-6242, 82 62-223-…
  • Division of Cardiology, Hallym University Dongtan Sacred Heart Hospital, Hwaseong, Republic of Korea.
  • Department of Internal Medicine, Chonnam National University Medical School, Gwangju, Republic of Korea.

ORCID profiles: Minje Park, Hyun Jin Ahn, Yeongyeon Na, Sunghoon Joo, Young Ho Lee, Seongwoo Han, Myung Soo Park, Dae Young Cheon, Jeen Hwa Lee, Ki Hong Lee

Cite

APA

Park, M., Ahn, H. J., Na, Y., Joo, S., Lee, Y. H., Han, S., Park, M. S., Cheon, D. Y., Lee, J. H., & Lee, K. H. (2026). Prediction of Atrial Fibrillation Occurrence With Handheld Mobile Electrocardiogram: Deep Learning Model Development Using Real-World Data. JMIR Medical Informatics, 14, e87142-e87142. https://doi.org/10.2196/87142

Vancouver

Park M, Ahn HJ, Na Y, Joo S, Lee YH, Han S, et al. Prediction of Atrial Fibrillation Occurrence With Handheld Mobile Electrocardiogram: Deep Learning Model Development Using Real-World Data. JMIR Medical Informatics. 2026;14:e87142-e87142. doi:10.2196/87142

BibTeX
@article{Park2026,
  author = {Park, Minje and Ahn, Hyun Jin and Na, Yeongyeon and Joo, Sunghoon and Lee, Young Ho and Han, Seongwoo and Park, Myung Soo and Cheon, Dae Young and Lee, Jeen Hwa and Lee, Ki Hong},
  title = {Prediction of Atrial Fibrillation Occurrence With Handheld Mobile Electrocardiogram: Deep Learning Model Development Using Real-World Data},
  journal = {JMIR Medical Informatics},
  year = {2026},
  volume = {14},
  pages = {e87142--e87142},
  doi = {10.2196/87142}
}
Start for free →