Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques

M. Piorecky, M. Bartoň, V. Koudelka, J. Buskova, J. Koprivova, M. Brunovsky, V. Piorecka

. 2021 ; 11 (12) : . [pub] 20211208

Language English Country Switzerland

Document type Journal Article

Persistent link   https://www.medvik.cz/link/bmc22001088

Grant support
SGS20/146/OHK4/2T/17 Grant Agency of the Czech Technical University in Prague
SGS21/140/OHK4/2T/17 Grant Agency of the Czech Technical University in Prague
NV18-07-00272 MH CZ---DRO (National Institute of Mental Health-NIMH, IN: 00023752), by project LO1611 under the NPU I program, by Ministry of Health of the Czech Republic

Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO2 channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used k-nearest neighbors (k-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the k-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22001088
003      
CZ-PrNML
005      
20220112153458.0
007      
ta
008      
220107s2021 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3390/diagnostics11122302 $2 doi
035    __
$a (PubMed)34943539
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Piorecky, Marek $u National Institute of Mental Health, 25067 Klecany, Czech Republic $u Faculty of Biomedical Engineering, Czech Technical University in Prague, 27201 Kladno, Czech Republic
245    10
$a Apnea Detection in Polysomnographic Recordings Using Machine Learning Techniques / $c M. Piorecky, M. Bartoň, V. Koudelka, J. Buskova, J. Koprivova, M. Brunovsky, V. Piorecka
520    9_
$a Sleep disorders are diagnosed in sleep laboratories by polysomnography, a multi-parameter examination that monitors biological signals during sleep. The subsequent evaluation of the obtained records is very time-consuming. The goal of this study was to create an automatic system for evaluation of the airflow and SpO2 channels of polysomnography records, through the use of machine learning techniques and a large database, for apnea and desaturation detection (which is unusual in other studies). To that end, a convolutional neural network (CNN) was designed using hyperparameter optimization. It was then trained and tested for apnea and desaturation. The proposed CNN was compared with the commonly used k-nearest neighbors (k-NN) method. The classifiers were designed based on nasal airflow and blood oxygen saturation signals. The final neural network accuracy for apnea detection reached 84%, and that for desaturation detection was 74%, while the k-NN classifier reached accuracies of 83% and 64% for apnea detection and desaturation detection, respectively.
655    _2
$a časopisecké články $7 D016428
700    1_
$a Bartoň, Martin $u National Institute of Mental Health, 25067 Klecany, Czech Republic $u Faculty of Biomedical Engineering, Czech Technical University in Prague, 27201 Kladno, Czech Republic
700    1_
$a Koudelka, Vlastimil $u National Institute of Mental Health, 25067 Klecany, Czech Republic
700    1_
$a Buskova, Jitka $u National Institute of Mental Health, 25067 Klecany, Czech Republic
700    1_
$a Koprivova, Jana $u National Institute of Mental Health, 25067 Klecany, Czech Republic
700    1_
$a Brunovsky, Martin $u National Institute of Mental Health, 25067 Klecany, Czech Republic $u Third Faculty of Medicine, Charles University, 10000 Prague, Czech Republic
700    1_
$a Piorecka, Vaclava $u National Institute of Mental Health, 25067 Klecany, Czech Republic $u Faculty of Biomedical Engineering, Czech Technical University in Prague, 27201 Kladno, Czech Republic
773    0_
$w MED00195450 $t Diagnostics (Basel, Switzerland) $x 2075-4418 $g Roč. 11, č. 12 (2021)
856    41
$u https://pubmed.ncbi.nlm.nih.gov/34943539 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20220107 $b ABA008
991    __
$a 20220112153454 $b ABA008
999    __
$a ind $b bmc $g 1745356 $s 1152235
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2021 $b 11 $c 12 $e 20211208 $i 2075-4418 $m Diagnostics $n Diagnostics $x MED00195450
GRA    __
$a SGS20/146/OHK4/2T/17 $p Grant Agency of the Czech Technical University in Prague
GRA    __
$a SGS21/140/OHK4/2T/17 $p Grant Agency of the Czech Technical University in Prague
GRA    __
$a NV18-07-00272 $p MH CZ---DRO (National Institute of Mental Health-NIMH, IN: 00023752), by project LO1611 under the NPU I program, by Ministry of Health of the Czech Republic
LZP    __
$a Pubmed-20220107

Find record

Citation metrics

Archiving options