• Je něco špatně v tomto záznamu ?

Iterative expert-in-the-loop classification of sleep PSG recordings using a hierarchical clustering

V. Gerla, V. Kremen, M. Macas, D. Dudysova, A. Mladek, P. Sos, L. Lhotska,

. 2019 ; 317 (-) : 61-70. [pub] 20190207

Jazyk angličtina Země Nizozemsko

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/bmc20025900

BACKGROUND: The classification of sleep signals is a subjective and time consuming task. A large number of automatic classifiers have been published in the past decade but a sleep community has no strong confidence to use them in clinical practice and still remains using a standard manual scoring according standardized rules. NEW METHOD: We developed a semi-supervised data-driven approach for objective and efficient evaluation of polysomnographic (PSG) data. The proposed algorithm finds a representative set of signal segments that are subsequently scored by a sleep neurologist. The remaining part of the recording is then automatically classified using these templates. RESULTS: The method was evaluated on 36 PSG recordings (18 chronic insomniacs, 18 healthy controls). We show a faster and objective evaluation of PSG data compared to the manual scoring that is over-performing automated classifiers (accuracy increases ∼14%). The classification results are comparable on both datasets. COMPARISON WITH EXISTING METHOD(S): The methodology that we propose has not yet been published in the area of sleep PSG data processing. The performance of our method is comparable to various published automated approaches (a typical published classification accuracy is ∼75-95%). The method allows the evaluation of PSG recordings in more general terms and across different recording devices and standards. CONCLUSIONS: The proposed solution is not based on a single-purpose rules or heuristics and training model is not trained on other patient's sleep recordings. The method is applicable to wide range of similar tasks and various types of physiological signals.

Citace poskytuje Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc20025900
003      
CZ-PrNML
005      
20210108110358.0
007      
ta
008      
201125s2019 ne f 000 0|eng||
009      
AR
024    7_
$a 10.1016/j.jneumeth.2019.01.013 $2 doi
035    __
$a (PubMed)30738880
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a ne
100    1_
$a Gerla, V $u Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic. Electronic address: vaclav.gerla@cvut.cz.
245    10
$a Iterative expert-in-the-loop classification of sleep PSG recordings using a hierarchical clustering / $c V. Gerla, V. Kremen, M. Macas, D. Dudysova, A. Mladek, P. Sos, L. Lhotska,
520    9_
$a BACKGROUND: The classification of sleep signals is a subjective and time consuming task. A large number of automatic classifiers have been published in the past decade but a sleep community has no strong confidence to use them in clinical practice and still remains using a standard manual scoring according standardized rules. NEW METHOD: We developed a semi-supervised data-driven approach for objective and efficient evaluation of polysomnographic (PSG) data. The proposed algorithm finds a representative set of signal segments that are subsequently scored by a sleep neurologist. The remaining part of the recording is then automatically classified using these templates. RESULTS: The method was evaluated on 36 PSG recordings (18 chronic insomniacs, 18 healthy controls). We show a faster and objective evaluation of PSG data compared to the manual scoring that is over-performing automated classifiers (accuracy increases ∼14%). The classification results are comparable on both datasets. COMPARISON WITH EXISTING METHOD(S): The methodology that we propose has not yet been published in the area of sleep PSG data processing. The performance of our method is comparable to various published automated approaches (a typical published classification accuracy is ∼75-95%). The method allows the evaluation of PSG recordings in more general terms and across different recording devices and standards. CONCLUSIONS: The proposed solution is not based on a single-purpose rules or heuristics and training model is not trained on other patient's sleep recordings. The method is applicable to wide range of similar tasks and various types of physiological signals.
650    _2
$a dospělí $7 D000328
650    _2
$a algoritmy $7 D000465
650    _2
$a mozek $x fyziologie $7 D001921
650    _2
$a mozkové vlny $7 D058256
650    _2
$a shluková analýza $7 D016000
650    12
$a elektroencefalografie $7 D004569
650    _2
$a ženské pohlaví $7 D005260
650    _2
$a lidé $7 D006801
650    _2
$a strojové učení $7 D000069550
650    _2
$a mužské pohlaví $7 D008297
650    _2
$a lidé středního věku $7 D008875
650    _2
$a polysomnografie $x metody $7 D017286
650    _2
$a počítačové zpracování signálu $7 D012815
650    _2
$a spánek $x fyziologie $7 D012890
650    _2
$a poruchy iniciace a udržování spánku $x patofyziologie $7 D007319
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Kremen, V $u Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic. Electronic address: vaclav.kremen@cvut.cz.
700    1_
$a Macas, M $u Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic.
700    1_
$a Dudysova, D $u National Institute of Mental Health, Klecany, Czech Republic; Third Faculty of Medicine, Charles University, Prague, Czech Republic.
700    1_
$a Mládek, Arnošt $7 xx0255112 $u Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic; Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic; Neurosurgical Department, 1st Faculty of Medicine, Charles University, Czech Republic.
700    1_
$a Sos, P $u National Institute of Mental Health, Klecany, Czech Republic.
700    1_
$a Lhotska, L $u Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University in Prague, Czech Republic; Faculty of Biomedical Engineering, Czech Technical University in Prague, Czech Republic.
773    0_
$w MED00002841 $t Journal of neuroscience methods $x 1872-678X $g Roč. 317, č. - (2019), s. 61-70
856    41
$u https://pubmed.ncbi.nlm.nih.gov/30738880 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20201125 $b ABA008
991    __
$a 20210108110320 $b ABA008
999    __
$a ok $b bmc $g 1600045 $s 1116586
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2019 $b 317 $c - $d 61-70 $e 20190207 $i 1872-678X $m Journal of neuroscience methods $n J Neurosci Methods $x MED00002841
LZP    __
$a Pubmed-20201125

Najít záznam

Citační ukazatele

Možnosti archivace