Received: 24 July 2015 Revised: 11 February 2017 Accepted: 11 July 2017
DOI: 10.1111/coin.12138
ORIGINAL ARTICLE
Detection and classification of sleep apnea
using genetic algorithms and SVM-based
classification of thoracic respiratory effort and
oximetric signal features
Zahra Abedi
1
Nadia Naghavi
1
Fariborz Rezaeitalab
2
1
Department of Electrical
Engineering, Ferdowsi University of
Mashhad, Mashhad, Iran
2
Department of Neurology, School of
Medicine, Mashhad University of
Medical Sciences, Mashhad, Iran
Correspondence
Nadia Naghavi, Department of
Electrical Engineering, Ferdowsi
University of Mashhad, Azadi Square,
PO Box 91779 48974, Mashhad,
Khorasan Razavi, Iran.
Email: n.naghavi@um.ac.ir
Abstract
Sleep apnea is a relatively prevalent breathing disorder char-
acterized by temporary interruptions in airflow during sleep.
There are 2 major types of sleep apnea. Obstructive sleep
apnea occurs when air cannot flow through the upper airway
despite efforts to breathe. Central sleep apnea occurs when
the brain fails to signal to the muscles to maintain breath-
ing. The standard diagnostic test is polysomnography, which
is expensive and time consuming. The aim of this study was
to design an automatic diagnostic and classifying algorithm
for sleep apneas employing thoracic respiratory effort and oxi-
metric signals. This algorithm was trained and tested applying
a database of 54 subjects who had undergone polysomnog-
raphy. A feature extraction stage was conducted to compute
features. An optimal genetic algorithm was applied to select
optimal features of these 2 kinds of signals. The classification
technique was based on the support vector machine classi-
fier to classify the selected features in 3 classes as healthy,
obstructive, and central sleep apnea events. The results show
that our automated classification algorithm can diagnose
sleep apnea and its types with an average accuracy level of
90.2% (87.5-95.8) in the test set and 90.9% in the validation set
with high acceptable accuracy.
KEYWORDS
genetic algorithm, oximetric signal, sleep apnea, support vector machine,
thoracic respiratory effort signal
1 INTRODUCTION
Until the mid-twentieth century, it was generally believed that sleep is an inactive period in the
membrane physiology. However, nowadays, through the development of technology, it is believed
Computational Intelligence. 2017;1–14. wileyonlinelibrary.com/journal/coin © 2017 Wiley Periodicals, Inc. 1