Citation: Lee, K.-S.; Park, H.-J.; Kim,
J.E.; Kim, H.J.; Chon, S.; Kim, S.; Jang,
J.; Kim, J.-K.; Jang, S.; Gil, Y.; et al.
Compressed Deep Learning to
Classify Arrhythmia in an Embedded
Wearable Device. Sensors 2022, 22,
1776. https://doi.org/10.3390/
s22051776
Academic Editor: Andrea Cataldo
Received: 27 January 2022
Accepted: 21 February 2022
Published: 24 February 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
Compressed Deep Learning to Classify Arrhythmia
in an Embedded Wearable Device
Kwang-Sig Lee
1
, Hyun-Joon Park
2
, Ji Eon Kim
3
, Hee Jung Kim
3
, Sangil Chon
4
, Sangkyu Kim
4
,
Jaesung Jang
4
, Jin-Kook Kim
4
, Seongbin Jang
4
, Yeongjoon Gil
4
and Ho Sung Son
3,
*
1
AI Center, Korea University Anam Hospital, Seoul 02841, Korea; ecophy@korea.ac.kr
2
Institute for Health Service Innovation, Korea University College of Medicine, Seoul 02841, Korea;
hyunjun21@korea.ac.kr
3
Department of Thoracic and Cardiovascular Surgery, Korea University College of Medicine,
Korea University Anam Hospital, Seoul 02841, Korea; jieonkim82@gmail.com (J.E.K.);
heejung440@daum.net (H.J.K.)
4
HUINNO Co., Ltd., Seoul 06011, Korea; chons@huinno.com (S.C.); kimsk6015@huinno.com (S.K.);
jaeseongjang@huinno.com (J.J.); jinkook@huinno.com (J.-K.K.); sbjang@huinno.com (S.J.);
kyzoon@huinno.com (Y.G.)
* Correspondence: hssonmd@korea.ac.kr; Tel.: +82-2-920-5528
Abstract:
The importance of an embedded wearable device with automatic detection and alarming
cannot be overstated, given that 15–30% of patients with atrial fibrillation are reported to be asymp-
tomatic. These asymptomatic patients do not seek medical care, hence traditional diagnostic tools
including Holter are not effective for the further prevention of associated stroke or heart failure.
This is likely to be more so in the era of COVID-19, in which patients become more reluctant on
hospitalization and checkups. However, little literature is available on this important topic. For this
reason, this study developed efficient deep learning with model compression, which is designed to
use ECG data and classify arrhythmia in an embedded wearable device. ECG-signal data came from
Korea University Anam Hospital in Seoul, Korea, with 28,308 unique patients (15,412 normal and
12,896 arrhythmia). Resnets and Mobilenets with model compression (TensorFlow Lite) were applied
and compared for the diagnosis of arrhythmia in an embedded wearable device. The weight size of
the compressed model registered a remarkable decrease from 743 MB to 76 KB (1/10000), whereas
its performance was almost the same as its original counterpart. Resnet and Mobilenet were similar
in terms of accuracy, i.e., Resnet-50 Hz (97.3) vs. Mo-bilenet-50 Hz (97.2), Resnet-100 Hz (98.2) vs.
Mobilenet-100 Hz (97.9). Here, 50 Hz/100 Hz denotes the down-sampling rate. However, Resnets
took more flash memory and longer inference time than did Mobilenets. In conclusion, Mobilenet
would be a more efficient model than Resnet to classify arrhythmia in an embedded wearable device.
Keywords: arrhythmia; compressed deep learning; embedded wearable device; Resnet; Mobilenet
1. Introduction
Heart disease is a major contributor for disease burden on the globe [
1
–
6
]. The
estimated number of deaths from cardiovascular disease was 17.9 million in the world for
Y2019 (Y2019 hereafter), which was 32% of global deaths [
1
]. The age-standardized death
rate from atrial fibrillation, the most common arrhythmia, showed a great increase from
0.8 to 1.6 per 100,000 for men (or 0.9 to 1.7 per 100,000 for women) in the world during
1990–2010 [
2
]. This worldwide trend agrees with its Korean counterpart. Heart disease
ranked second in Korea as the cause of death for Y2020 (63.0 per 100,000) [
3
] and as the
source of disease burden for Y2015 (3475 disease-adjusted life years per 100,000) [
4
]. In
addition, the number of hospitalizations for atrial fibrillation registered a rapid growth of
420% from 767 to 3986 per 1 million during 2006–2015 [5].
For this reason, emerging literature has focused on the early diagnosis of arrhythmia,
using deep neural networks for their better performance measures than those of other
Sensors 2022, 22, 1776. https://doi.org/10.3390/s22051776 https://www.mdpi.com/journal/sensors
