Citation: Pifarré, M.; Tena, A.; Clarià,
F.; Solsona, F.; Vilaplana, J.;
Benavides, A.; Mas, L; Abella, F. A
Machine-Learning Model for Lung
Age Forecasting by Analyzing
Exhalations. Sensors 2022, 22, 1106.
https://doi.org/10.3390/s22031106
Academic Editors: M. Jamal Deen,
Subhas Mukhopadhyay, Yangquan
Chen, Simone Morais, Nunzio
Cennamo and Junseop Lee
Received: 29 December 2021
Accepted: 28 January 2022
Published: 1 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
A Machine-Learning Model for Lung Age Forecasting by
Analyzing Exhalations
Marc Pifarré
1
, Alberto Tena
2
, Francisco Clarià
1
, Francesc Solsona
1,
* , Jordi Vilaplana
1
,
Arnau Benavides
1
, Lluis Mas
1
and Francesc Abella
3
1
Department of Computer Science & INSPIRES, University of Lleida, Jaume II 69, 25001 Lleida, Spain;
mpm4@alumnes.udl.cat (M.P.); francisco.claria@udl.cat (F.C.); jordi@diei.udl.cat (J.V.);
arnaubenavides97@gmail.com (A.B.); lluis.mas@udl.cat (L.M.)
2
CIMNE, Building C1, North Campus, UPC, Gran Capità, 08034 Barcelona, Spain; atena@cimne.upc.edu
3
IRBLleida, Avda Alcalde Rovira Roure 80, 25198 Lleida, Spain; abellapons@gmail.com
* Correspondence: francesc@diei.udl.cat; Tel.: +34-973702735
Abstract:
Spirometers are important devices for following up patients with respiratory diseases.
These are mainly located only at hospitals, with all the disadvantages that this can entail. This limits
their use and consequently, the supervision of patients. Research efforts focus on providing digital
alternatives to spirometers. Although less accurate, the authors claim they are cheaper and usable by
many more people worldwide at any given time and place. In order to further popularize the use
of spirometers even more, we are interested in also providing user-friendly lung-capacity metrics
instead of the traditional-spirometry ones. The main objective, which is also the main contribution of
this research, is to obtain a person’s lung age by analyzing the properties of their exhalation by means
of a machine-learning method. To perform this study, 188 samples of blowing sounds were used.
These were taken from 91 males (48.4%) and 97 females (51.6%) aged between 17 and 67. A total of
42 spirometer and frequency-like features, including gender, were used. Traditional machine-learning
algorithms used in voice recognition applied to the most significant features were used. We found
that the best classification algorithm was the Quadratic Linear Discriminant algorithm when no
distinction was made between gender. By splitting the corpus into age groups of 5 consecutive years,
accuracy, sensitivity and specificity of, respectively, 94.69%, 94.45% and 99.45% were found. Features
in the audio of users’ expiration that allowed them to be classified by their corresponding lung age
group of 5 years were successfully detected. Our methodology can become a reliable tool for use
with mobile devices to detect lung abnormalities or diseases.
Keywords: exhalation; lung capacity forecasting; machine learning
1. Introduction
Respiratory diseases cause immense health, economic and social costs and are the
third cause of death worldwide [
1
] and a significant burden for public health systems [
2
].
Significant research efforts have been dedicated to improving early diagnosis and monitor-
ing of patients with respiratory diseases to allow for timely interventions [
3
]. Respiratory
sounds are important indicators of respiratory health and disorders [
4
]. Distinction between
normal respiratory sounds and adventitious ones (such as crackles, wheezes or squawks)
is important for an accurate medical diagnosis [5,6].
Spirometry is generally performed in care centres using conventional spirometers, but
home spirometry with portable devices is slowly gaining acceptance [
7
]. Home spirometry
has the potential to result for earlier treatment of exacerbations, more rapid recovery,
reduced health care costs, and improved outcomes [
8
]. Challenges currently faced by
home spirometry are cost, patient compliance and usability, and an integrated method
for uploading results to physicians [
9
]. Digital techniques applied to home spirometry
Sensors 2022, 22, 1106. https://doi.org/10.3390/s22031106 https://www.mdpi.com/journal/sensors
