Graph-based learning for sleep microarchitecture: a hybrid graph autoencoder and graph attention network approach

Background: Sleep plays a vital role in cognitive function, memory consolidation, and overall neurological health. Analysis of sleep microarchitecture including features such as sleep spindles, K-complexes, slow waves, and EEG bandpower components provides critical insights into sleep disorders and...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of research in medical sciences Ročník 13; číslo 11; s. 4696 - 4702
Hlavní autori: Kurisinkal Augustine, Amala Ann, Vaidhehi
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: 30.10.2025
ISSN:2320-6071, 2320-6012
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract Background: Sleep plays a vital role in cognitive function, memory consolidation, and overall neurological health. Analysis of sleep microarchitecture including features such as sleep spindles, K-complexes, slow waves, and EEG bandpower components provides critical insights into sleep disorders and genetic diseases. However, the complex interactions between sleep architecture and underlying genetic abnormalities remain underexplored. This study aims to investigate these interactions by leveraging advanced graph-based deep learning methods to uncover hidden relationships within EEG signals. Methods: We developed a graph autoencoder (GAE) combined with a Graph attention network (GAT) to analyze polysomnography (PSG) data from the National Children's Hospital (NCH) dataset. EEG epochs were modelled as graph nodes, while edges were constructed based on bandpower similarity between epochs, enabling dynamic representation of sleep activity. The GAE learned latent embeddings that capture subtle patterns in sleep microarchitecture, and the GAT applied attention mechanisms to classify and interpret relationships between EEG events, sleep disorders, and genetic abnormalities. Three core analyses were conducted: (1) identifying differences in sleep microarchitecture across sleep disorders, (2) detecting EEG event changes associated with genetic disorders, and (3) exploring shared patterns linking sleep and genetic abnormalities. Results: The model achieved classification accuracies of 92.4%, 91.2%, and 88.6% across the three tasks, respectively. The approach successfully identified distinct EEG event patterns in subjects with co-occurring sleep disorders. Conclusions: This work presents a scalable, automated, and interpretable framework for analyzing the interplay between sleep microarchitecture, sleep disorders, and genetic disorders.
AbstractList Background: Sleep plays a vital role in cognitive function, memory consolidation, and overall neurological health. Analysis of sleep microarchitecture including features such as sleep spindles, K-complexes, slow waves, and EEG bandpower components provides critical insights into sleep disorders and genetic diseases. However, the complex interactions between sleep architecture and underlying genetic abnormalities remain underexplored. This study aims to investigate these interactions by leveraging advanced graph-based deep learning methods to uncover hidden relationships within EEG signals. Methods: We developed a graph autoencoder (GAE) combined with a Graph attention network (GAT) to analyze polysomnography (PSG) data from the National Children's Hospital (NCH) dataset. EEG epochs were modelled as graph nodes, while edges were constructed based on bandpower similarity between epochs, enabling dynamic representation of sleep activity. The GAE learned latent embeddings that capture subtle patterns in sleep microarchitecture, and the GAT applied attention mechanisms to classify and interpret relationships between EEG events, sleep disorders, and genetic abnormalities. Three core analyses were conducted: (1) identifying differences in sleep microarchitecture across sleep disorders, (2) detecting EEG event changes associated with genetic disorders, and (3) exploring shared patterns linking sleep and genetic abnormalities. Results: The model achieved classification accuracies of 92.4%, 91.2%, and 88.6% across the three tasks, respectively. The approach successfully identified distinct EEG event patterns in subjects with co-occurring sleep disorders. Conclusions: This work presents a scalable, automated, and interpretable framework for analyzing the interplay between sleep microarchitecture, sleep disorders, and genetic disorders.
Author Vaidhehi
Kurisinkal Augustine, Amala Ann
Author_xml – sequence: 1
  givenname: Amala Ann
  surname: Kurisinkal Augustine
  fullname: Kurisinkal Augustine, Amala Ann
– sequence: 2
  surname: Vaidhehi
  fullname: Vaidhehi
BookMark eNpVkNFKAzEQRYMoWGv_IT-wNZnsbja-SdEqFHzp-5JNZrupbbImKdK_t1Up-DTDXO5hOHfk2gePhFDO5rwBJh5AACtqxmHutnGfgEElqkZekcklub7skt-SWUpbxhgXJVelmpDPZdTjUHQ6oaU71NE7v6F9iDTtEEe6dyYGHc3gMpp8iPhINR2OXXSWbs5Vqg85oDfBYqTaX645o88ueOoxf4X4QfU4nkhmuCc3vd4lnP3NKVm_PK8Xr8Xqffm2eFoVRilZVAqF1bKrjQJbaqs0B9bUArqy6sEqVldKgOGslmUFYHsUUoCVWHPNG6zFlDS_2NP_KUXs2zG6vY7HlrP2R1571tKeFbX_5Ilv9XdndQ
Cites_doi 10.1007/s11910-019-0968-1
10.1093/sleep/zsac079.656
10.1109/TNSRE.2024.3355750
10.21608/cjmss.2024.290167.1053
10.1016/j.biopsycho.2007.01.004
10.1111/j.1439-054X.2006.00101.x
10.23919/JSC.2023.0018
10.1016/j.heliyon.2025.e43576
10.1093/jamia/ocy064
10.3390/s22083079
10.1093/sleepadvances/zpac029.002
10.3389/fpsyt.2023.1115374
10.1016/j.sleep.2019.01.050
10.1186/s13643-024-02449-9
10.5815/ijisa.2015.06.05
10.1093/sleep/zsad077.0907
10.1109/BigData62323.2024.10825687
10.1101/2024.12.11.24318815
10.1016/j.cell.2011.07.004
ContentType Journal Article
DBID AAYXX
CITATION
DOI 10.18203/2320-6012.ijrms20253587
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 2320-6012
EndPage 4702
ExternalDocumentID 10_18203_2320_6012_ijrms20253587
GroupedDBID 5VS
AAYXX
ALMA_UNASSIGNED_HOLDINGS
CITATION
KQ8
M~E
RNS
ID FETCH-LOGICAL-c997-59e3da7b6c92d4ad9a1208632b45f2d9065932c10674522dfe3732d7e61a18e63
ISSN 2320-6071
IngestDate Wed Nov 05 20:41:28 EST 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Issue 11
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c997-59e3da7b6c92d4ad9a1208632b45f2d9065932c10674522dfe3732d7e61a18e63
OpenAccessLink https://www.msjonline.org/index.php/ijrms/article/download/15584/10019
PageCount 7
ParticipantIDs crossref_primary_10_18203_2320_6012_ijrms20253587
PublicationCentury 2000
PublicationDate 2025-10-30
PublicationDateYYYYMMDD 2025-10-30
PublicationDate_xml – month: 10
  year: 2025
  text: 2025-10-30
  day: 30
PublicationDecade 2020
PublicationTitle International journal of research in medical sciences
PublicationYear 2025
References 383060
383050
383061
383051
383062
383052
383063
383046
383057
383047
383058
383048
383059
383049
383053
383064
383054
383065
383055
383066
383056
383067
References_xml – ident: 383054
  doi: 10.1007/s11910-019-0968-1
– ident: 383050
  doi: 10.1093/sleep/zsac079.656
– ident: 383067
  doi: 10.1109/TNSRE.2024.3355750
– ident: 383049
  doi: 10.21608/cjmss.2024.290167.1053
– ident: 383056
  doi: 10.1016/j.biopsycho.2007.01.004
– ident: 383065
  doi: 10.1111/j.1439-054X.2006.00101.x
– ident: 383058
  doi: 10.23919/JSC.2023.0018
– ident: 383046
  doi: 10.1016/j.heliyon.2025.e43576
– ident: 383062
  doi: 10.1093/jamia/ocy064
– ident: 383057
– ident: 383059
– ident: 383066
  doi: 10.3390/s22083079
– ident: 383051
  doi: 10.1093/sleepadvances/zpac029.002
– ident: 383060
  doi: 10.3389/fpsyt.2023.1115374
– ident: 383053
  doi: 10.1016/j.sleep.2019.01.050
– ident: 383048
  doi: 10.1186/s13643-024-02449-9
– ident: 383055
  doi: 10.5815/ijisa.2015.06.05
– ident: 383052
  doi: 10.1093/sleep/zsad077.0907
– ident: 383047
  doi: 10.1109/BigData62323.2024.10825687
– ident: 383063
– ident: 383061
  doi: 10.1101/2024.12.11.24318815
– ident: 383064
  doi: 10.1016/j.cell.2011.07.004
SSID ssj0001341949
Score 2.307803
Snippet Background: Sleep plays a vital role in cognitive function, memory consolidation, and overall neurological health. Analysis of sleep microarchitecture...
SourceID crossref
SourceType Index Database
StartPage 4696
Title Graph-based learning for sleep microarchitecture: a hybrid graph autoencoder and graph attention network approach
Volume 13
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVHPJ
  databaseName: ROAD: Directory of Open Access Scholarly Resources
  customDbUrl:
  eissn: 2320-6012
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001341949
  issn: 2320-6071
  databaseCode: M~E
  dateStart: 20130101
  isFulltext: true
  titleUrlDefault: https://road.issn.org
  providerName: ISSN International Centre
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LbxMxELZCi1AviPJQebTyobdoobb3ZW4VovTSqocI9bay114SlGxDsqnaCz-OX8aM17t4qRAPicsqspTRJvNp3vOZkEOp88SYzOJ2u4liFutIHyU6guBDKaFxm1K5yyay8_P88lJejEbful2Y63lW1_nNjVz-V1XDGSgbV2f_Qt29UDiAz6B0eILa4flHiv-AFNQReifT3QnRzkqu59YuxwucwAvbB-268_QWV7fGjr96rDbNFRJcIs8EFtb9adP42ci6nR3vCcnDCHdYYgyIKTytkKuwLHx7yPvfQUNpDdkx4mbzCS8a8wXXhZqr8XHdI_mjmpmpnc7CogV3ZKe-_-JsG8fFbaS2a91QeMaGxlmEIGSBqYW8Pg3cdpy5ze27LgFCHOSm6KW_nn1eLdb4UiLxvn7Awv2Td-xnFjFbQlkFSipQUjGQdI9s8yyRaFnPvgZ1PiTMc1lY_5v9QBkKe_OL1wqipCDcmTwiD32eQo9bfO2Ska0fkwdnfhLjCfkSwIx2MKMAM-pgRu_A7C1VtAUZdXCiAcgogKw77UBGPchoB7KnZHLyfvLuNPLXd0QlUvwm0gqjMp2WkptYGakYh_xZcB0nFTcSG_qCl0hhiKz-prIiExzMRsoUy20qnpGt-qq2e4SaLE9ZldujUtpY5VqmNoG4m2lZmURX9jlh3b9VLFuSluJ36nrxD995SXZ-gPkV2WpWG7tP7pfXzWy9OnB6_w7fEZC9
linkProvider ISSN International Centre
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Graph-based+learning+for+sleep+microarchitecture%3A+a+hybrid+graph+autoencoder+and+graph+attention+network+approach&rft.jtitle=International+journal+of+research+in+medical+sciences&rft.au=Kurisinkal+Augustine%2C+Amala+Ann&rft.au=Vaidhehi&rft.date=2025-10-30&rft.issn=2320-6071&rft.eissn=2320-6012&rft.volume=13&rft.issue=11&rft.spage=4696&rft.epage=4702&rft_id=info:doi/10.18203%2F2320-6012.ijrms20253587&rft.externalDBID=n%2Fa&rft.externalDocID=10_18203_2320_6012_ijrms20253587
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2320-6071&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2320-6071&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2320-6071&client=summon