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

Predicting Sex From EEG: Validity and Generalizability of Deep-Learning-Based Interpretable Classifier

B. Bučková, M. Brunovský, M. Bareš, J. Hlinka,

. 2020 ; 14 (-) : 589303. [pub] 20201027

Language English Country Switzerland

Document type Journal Article

Persistent link   https://www.medvik.cz/link/bmc21001891

Grant support
NV17-28427A MZ0 CEP Register

Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc21001891
003      
CZ-PrNML
005      
20210126092728.0
007      
ta
008      
210105s2020 sz f 000 0|eng||
009      
AR
024    7_
$a 10.3389/fnins.2020.589303 $2 doi
035    __
$a (PubMed)33192274
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a sz
100    1_
$a Bučková, Barbora $u Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Prague, Czechia. Department of Complex Systems, Institute of Computer Science of the Czech Academy of Sciences, Prague, Czechia.
245    10
$a Predicting Sex From EEG: Validity and Generalizability of Deep-Learning-Based Interpretable Classifier. / $c B. Bučková, M. Brunovský, M. Bareš, J. Hlinka,
520    9_
$a Explainable artificial intelligence holds a great promise for neuroscience and plays an important role in the hypothesis generation process. We follow-up a recent machine learning-oriented study that constructed a deep convolutional neural network to automatically identify biological sex from EEG recordings in healthy individuals and highlighted the discriminative role of beta-band power. If generalizing, this finding would be relevant not only theoretically by pointing to some specific neurobiological sexual dimorphisms, but potentially also as a relevant confound in quantitative EEG diagnostic practice. To put this finding to test, we assess whether the automatic identification of biological sex generalizes to another dataset, particularly in the presence of a psychiatric disease, by testing the hypothesis of higher beta power in women compared to men on 134 patients suffering from Major Depressive Disorder. Moreover, we construct ROC curves and compare the performance of the classifiers in determining sex both before and after the antidepressant treatment. We replicate the observation of a significant difference in beta-band power between men and women, providing classification accuracy of nearly 77%. The difference was consistent across the majority of electrodes, however multivariate classification models did not generally improve the performance. Similar results were observed also after the antidepressant treatment (classification accuracy above 70%), further supporting the robustness of the initial finding.
655    _2
$a časopisecké články $7 D016428
700    1_
$a Brunovský, Martin $u National Institute of Mental Health, Klecany, Czechia. Third Faculty of Medicine, Charles University, Prague, Czechia.
700    1_
$a Bareš, Martin $u National Institute of Mental Health, Klecany, Czechia. Third Faculty of Medicine, Charles University, Prague, Czechia.
700    1_
$a Hlinka, Jaroslav $u Department of Complex Systems, Institute of Computer Science of the Czech Academy of Sciences, Prague, Czechia. National Institute of Mental Health, Klecany, Czechia.
773    0_
$w MED00163313 $t Frontiers in neuroscience $x 1662-4548 $g Roč. 14, č. - (2020), s. 589303
856    41
$u https://pubmed.ncbi.nlm.nih.gov/33192274 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y - $z 0
990    __
$a 20210105 $b ABA008
991    __
$a 20210126092723 $b ABA008
999    __
$a ind $b bmc $g 1614057 $s 1122175
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2020 $b 14 $c - $d 589303 $e 20201027 $i 1662-4548 $m Frontiers in neuroscience $n Front Neurosci $x MED00163313
GRA    __
$a NV17-28427A $p MZ0
LZP    __
$a Pubmed-20210105

Find record

Citation metrics

Archiving options