Article
Wearable Devices, Smartphones, and Interpretable Artificial
Intelligence in Combating COVID-19
Haytham Hijazi
1,2
, Manar Abu Talib
3,
*, Ahmad Hasasneh
4
, Ali Bou Nassif
3
, Nafisa Ahmed
3
and Qassim Nasir
3
Citation: Hijazi, H.; Abu Talib, M.;
Hasasneh, A.; Bou Nassif, A.; Ahmed,
N.; Nasir, Q. Wearable Devices,
Smartphones, and Interpretable
Artificial Intelligence in Combating
COVID-19. Sensors 2021, 21, 8424.
https://doi.org/10.3390/s21248424
Academic Editors: Yangquan Chen,
Subhas Mukhopadhyay,
Nunzio Cennamo, M. Jamal Deen,
Junseop Lee and Simone Morais
Received: 28 November 2021
Accepted: 15 December 2021
Published: 17 December 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 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/).
1
Department of Informatics Engineering, CISUC-Centre for Informatics and Systems of the University of
Coimbra, University of Coimbra, P-3030-790 Coimbra, Portugal; haytham@dei.uc.pt
2
Intelligent Systems Department, Palestine Ahliya University, Bethlehem P-150-199, Palestine
3
College of Computing and Informatics, University of Sharjah, Sharjah P-27272, United Arab Emirates;
anassif@sharjah.ac.ae (A.B.N.); nafisa.ahmed@sharjah.ac.ae (N.A.); nasir@sharjah.ac.ae (Q.N.)
4
Department of Natural, Engineering, and Technology Sciences, Arab American University,
Ramallah P-600-699, Palestine; Ahmad.Hasasneh@aaup.edu
* Correspondence: mtalib@sharjah.ac.ae
Abstract:
Physiological measures, such as heart rate variability (HRV) and beats per minute (BPM),
can be powerful health indicators of respiratory infections. HRV and BPM can be acquired through
widely available wrist-worn biometric wearables and smartphones. Successive abnormal changes
in these indicators could potentially be an early sign of respiratory infections such as COVID-19.
Thus, wearables and smartphones should play a significant role in combating COVID-19 through
the early detection supported by other contextual data and artificial intelligence (AI) techniques.
In this paper, we investigate the role of the heart measurements (i.e., HRV and BPM) collected
from wearables and smartphones in demonstrating early onsets of the inflammatory response to the
COVID-19. The AI framework consists of two blocks: an interpretable prediction model to classify the
HRV measurements status (as normal or affected by inflammation) and a recurrent neural network
(RNN) to analyze users’ daily status (i.e., textual logs in a mobile application). Both classification
decisions are integrated to generate the final decision as either “potentially COVID-19 infected” or
“no evident signs of infection”. We used a publicly available dataset, which comprises 186 patients
with more than 3200 HRV readings and numerous user textual logs. The first evaluation of the
approach showed an accuracy of 83.34
±
1.68% with 0.91, 0.88, 0.89 precision, recall, and F1-Score,
respectively, in predicting the infection two days before the onset of the symptoms supported by a
model interpretation using the local interpretable model-agnostic explanations (LIME).
Keywords:
artificial intelligence; decision fusion; COVID-19 detection; heart rate variability; natural
language processing; wearables
1. Introduction
SARS-COV-2 (COVID-19) was first reported in Wuhan, China, at the end of 2019 [
1
]
and then spread across China and many countries globally in a few months, leading to
a continuous pandemic throughout the world. As of March 2020, the World Health Or-
ganization (WHO) [
2
] has declared that this virus is a global epidemic and is spreading
exponentially, as the number of infected people up to the date of preparing this research
paper has exceeded 260 million cases. More than 5 million have died in more than 200 dif-
ferent countries worldwide [3].
The ability to quickly identify, monitor, and isolate COVID-19 patients is one of the
most significant challenges that persist even after nearly two years following the first
announcement of the virus. Thus, the early detection of COVID-19 is predominant to
minimize the widespread of the infection, particularly for asymptotic patients, and take
responsible isolation measures.
Sensors 2021, 21, 8424. https://doi.org/10.3390/s21248424 https://www.mdpi.com/journal/sensors
