Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Nov;53(11):758-771.
doi: 10.4070/kcj.2023.0009.

Identifying Atrial Fibrillation With Sinus Rhythm Electrocardiogram in Embolic Stroke of Undetermined Source: A Validation Study With Insertable Cardiac Monitors

Ki-Hyun Jeon #  1 , Jong-Hwan Jang #  2 , Sora Kang  2 , Hak Seung Lee  2 , Min Sung Lee  2 , Jeong Min Son  2 , Yong-Yeon Jo  2 , Tae Jun Park  2 , Il-Young Oh  1 , Joon-Myoung Kwon  2   3 , Ji Hyun Lee  4
Affiliations

Identifying Atrial Fibrillation With Sinus Rhythm Electrocardiogram in Embolic Stroke of Undetermined Source: A Validation Study With Insertable Cardiac Monitors

Ki-Hyun Jeon et al. Korean Circ J. 2023 Nov.

Abstract

Background and objectives: Paroxysmal atrial fibrillation (AF) is a major potential cause of embolic stroke of undetermined source (ESUS). However, identifying AF remains challenging because it occurs sporadically. Deep learning could be used to identify hidden AF based on the sinus rhythm (SR) electrocardiogram (ECG). We combined known AF risk factors and developed a deep learning algorithm (DLA) for predicting AF to optimize diagnostic performance in ESUS patients.

Methods: A DLA was developed to identify AF using SR 12-lead ECG with the database consisting of AF patients and non-AF patients. The accuracy of the DLA was validated in 221 ESUS patients who underwent insertable cardiac monitor (ICM) insertion to identify AF.

Results: A total of 44,085 ECGs from 12,666 patient were used for developing the DLA. The internal validation of the DLA revealed 0.862 (95% confidence interval, 0.850-0.873) area under the curve (AUC) in the receiver operating curve analysis. In external validation data from 221 ESUS patients, the diagnostic accuracy of DLA and AUC were 0.811 and 0.827, respectively, and DLA outperformed conventional predictive models, including CHARGE-AF, C2HEST, and HATCH. The combined model, comprising atrial ectopic burden, left atrial diameter and the DLA, showed excellent performance in AF prediction with AUC of 0.906.

Conclusions: The DLA accurately identified paroxysmal AF using 12-lead SR ECG in patients with ESUS and outperformed the conventional models. The DLA model along with the traditional AF risk factors could be a useful tool to identify paroxysmal AF in ESUS patients.

Keywords: Artificial intelligence; Atrial fibrillation; Electrocardiogram; Embolic stroke.

PubMed Disclaimer

Conflict of interest statement

Medical AI Inc. provided support in the form of salaries for authors (Jong-Hwan Jang, Sora Kang, Hak Seung Lee, Min Sung Lee, Jeong Min Son, Yong-Yeon Jo, Tae Jun Park, and Joon-myoung Kwon). Joon-myoung Kwon is the founder and stakeholder in Medical AI Inc., a medical artificial intelligence company. There are no patents, products in development of marketed products to declare. This does not alter our adherence to Korean Circulation Journal policies. Ki-Hyun Jeon, Il-Young Oh and Ji Hyun Lee have no financial conflict of interest.

Figures

Figure 1
Figure 1. Study flow.
AF = atrial fibrillation; DLA = deep learning algorithm; ECG = electrocardiogram; ESUS = embolic stroke of undetermined source; ICM = implantable cardiac monitoring.
Figure 2
Figure 2. Architecture of the deep learning algorithm model.
AF = atrial fibrillation; ECG = electrocardiogram; BatchNorm1D = one-dimensional batch normalization; Conv1D = one-dimensional convolutional neural network; ReLU = rectified linear unit activation.
Figure 3
Figure 3. Receiver operating characteristic curves in external validation cohort.
AEB = atrial ectopic burden; AF = atrial fibrillation; AUC = area under the curve; DLA = deep learning algorithm; ESUS = embolic stroke of undetermined source; LAD = left atrium diameter.
Figure 4
Figure 4. Three-dimensional scatter plot of DLA and clinical features according to AF occurrence.
AF = atrial fibrillation; DLA = deep learning algorithm.
Figure 5
Figure 5. Explainable deep learning algorithm providing synthesized paroxysmal AF ECG by ShapeExplainer.
AF = atrial fibrillation; ECG = electrocardiogram.
See this image and copyright information in PMC

References

    1. Ntaios G. Embolic stroke of undetermined source: JACC review topic of the week. J Am Coll Cardiol. 2020;75:333–340. - PubMed
    1. Kirchhof P, Benussi S, Kotecha D, et al. 2016 ESC Guidelines for the management of atrial fibrillation developed in collaboration with EACTS. Europace. 2016;18:1609–1678. - PubMed
    1. Ziegler PD, Rogers JD, Ferreira SW, et al. Long-term detection of atrial fibrillation with insertable cardiac monitors in a real-world cryptogenic stroke population. Int J Cardiol. 2017;244:175–179. - PubMed
    1. Li YG, Pastori D, Farcomeni A, et al. A simple clinical risk score (C2HEST) for predicting incident atrial fibrillation in Asian subjects: derivation in 471,446 Chinese subjects, with internal validation and external application in 451,199 Korean subjects. Chest. 2019;155:510–518. - PMC - PubMed
    1. Suenari K, Chao TF, Liu CJ, Kihara Y, Chen TJ, Chen SA. Usefulness of HATCH score in the prediction of new-onset atrial fibrillation for Asians. Medicine (Baltimore) 2017;96:e5597. - PMC - PubMed