Citation: Kwon, J.-m.; Jo, Y.-Y.; Lee,
S.Y.; Kang, S.; Lim, S.-Y.; Lee, M.S.;
Kim, K.-H. Artificial Intelligence-
Enhanced Smartwatch ECG for Heart
Failure-Reduced Ejection Fraction
Detection by Generating 12-Lead ECG.
Diagnostics 2022, 12, 654. https://
doi.org/10.3390/diagnostics12030654
Academic Editors: Keun Ho Ryu and
Nipon Theera-Umpon
Received: 1 February 2022
Accepted: 2 March 2022
Published: 8 March 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
Artificial Intelligence-Enhanced Smartwatch ECG for Heart
Failure-Reduced Ejection Fraction Detection by Generating
12-Lead ECG
Joon-myoung Kwon
1,2,3,4,†
, Yong-Yeon Jo
1,†
, Soo Youn Lee
2,5
, Seonmi Kang
1
, Seon-Yu Lim
1
,
Min Sung Lee
1,2,3
and Kyung-Hee Kim
2,5,
*
1
Medical Research Team, Medical AI, Inc., San Francisco, CA 94103, USA; happywithhj@gmail.com (J.-m.K.);
yy.jo@medicalai.com (Y.-Y.J.); seonmikang@medicalai.com (S.K.); imsun211@medicalai.com (S.-Y.L.);
lylm@medicalai.com (M.S.L.)
2
Artificial Intelligence and Big Data Research Center, Sejong Medical Research Institute, Bucheon 14754, Korea;
leesy@sejongh.co.kr
3
Department of Critical Care and Emergency Medicine, Incheon Sejong Hospital, Incheon 21080, Korea
4
Medical R&D Center, Body Friend, Co., Ltd., Seoul 06302, Korea
5
Division of Cardiology, Cardiovascular Center, Incheon Sejong Hospital, Incheon 21080, Korea
* Correspondence: learnbyliving9@gmail.com; Tel.:+82-32-240-8568; Fax: +82-32-240-8094
† These authors contributed equally to this work.
Abstract:
Background: We developed and validated an artificial intelligence (AI)-enabled smartwatch
ECG to detect heart failure-reduced ejection fraction (HFrEF). Methods: This was a cohort study
involving two hospitals (A and B). We developed the AI in two steps. First, we developed an AI model
(ECGT2T) to synthesize ten-lead ECG from the asynchronized 2-lead ECG (Lead I and II). ECGT2T is
a deep learning model based on a generative adversarial network, which translates source ECGs to
reference ECGs by learning styles of the reference ECGs. For this, we included adult patients aged
≥
18 years from hospital A with at least one digitally stored 12-lead ECG. Second, we developed an
AI model to detect HFrEF using a 10 s 12-lead ECG. The AI model was based on convolutional neural
network. For this, we included adult patients who underwent ECG and echocardiography within
14 days. To validate the AI, we included adult patients from hospital B who underwent two-lead
smartwatch ECG and echocardiography on the same day. The AI model generates a 10 s 12-lead ECG
from a two-lead smartwatch ECG using ECGT2T and detects HFrEF using the generated 12-lead
ECG. Results: We included 137,673 patients with 458,745 ECGs and 38,643 patients with 88,900 ECGs
from hospital A for developing the ECGT2T and HFrEF detection models, respectively. The area
under the receiver operating characteristic curve of AI for detecting HFrEF using smartwatch ECG
was 0.934 (95% confidence interval 0.913–0.955) with 755 patients from hospital B. The sensitivity,
specificity, positive predictive value, and negative predictive value of AI were 0.897, 0.860, 0.258, and
0.994, respectively. Conclusions: An AI-enabled smartwatch 2-lead ECG could detect HFrEF with
reasonable performance.
Keywords: heart failure; electrocardiography; deep learning; artificial intelligence
1. Introduction
Heart failure (HF) is a significant healthcare burden worldwide, with an estimated
64.3 million people living with HF [
1
,
2
]. Despite advances in treatment, HF remains as a
high risk of morbidity and mortality and is the most common diagnosis in hospitalized
patients aged over 65 years, with a 5-year survival rate of only 57% [
3
–
5
]. In the United
States, HF affects ~$30.7 billion total annual costs and projection suggests that by 2030, the
total cost of HF will increase by 127%, to $69.8 billion [3,6].
Patients suffering with HF with reduced ejection fraction (HFrEF) become less active,
leading to repeated hospitalization, resulting in a poor quality of life, including a high
Diagnostics 2022, 12, 654. https://doi.org/10.3390/diagnostics12030654 https://www.mdpi.com/journal/diagnostics
