Standardized image-based polysomnography database and deep learning algorithm for sleep-stage classification

Abstract Study Objectives Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a s...

Full description

Saved in:

Bibliographic Details
Published in:	Sleep (New York, N.Y.) Vol. 46; no. 12; p. 1
Main Authors:	Jeong, Jaemin, Yoon, Wonhyuck, Lee, Jeong-Gun, Kim, Dongyoung, Woo, Yunhee, Kim, Dong-Kyu, Shin, Hyun-Woo
Format:	Journal Article
Language:	English
Published:	US Oxford University Press 11.12.2023
Subjects:	Algorithms Data mining Deep Learning Medical colleges Neural networks Polysomnography - methods Sleep - physiology Sleep apnea syndromes Sleep Stages - physiology South Korea deep learning computer neural network polysomnography sleep stages dataset
ISSN:	0161-8105, 1550-9109, 1550-9109
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Abstract Study Objectives Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments. Methods All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset Results We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance. Conclusions Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases. Graphical Abstract
AbstractList	Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments. All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset. We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance. Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases. Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments.STUDY OBJECTIVESPolysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments.All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset.METHODSAll individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset.We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance.RESULTSWe constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance.Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases.CONCLUSIONSOur main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases. Abstract Study Objectives Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments. Methods All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset Results We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance. Conclusions Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases. Graphical Abstract Study Objectives: Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments. Methods: All individually exported European data format files containing raw signals were converted into images with an annotation file, which contained the demographics, diagnoses, and sleep statistics. An image-based DL model for automatic sleep staging was developed, compared with a signal-based model, and validated in an external dataset Results: We constructed 10253 image-based PSG datasets using a standardized format. Among these, 7745 diagnostic PSG data were used to develop our DL model. The DL model using the image dataset showed similar performance to the signal-based dataset for the same subject. The overall DL accuracy was greater than 80%, even with severe obstructive sleep apnea. Moreover, for the first time, we showed explainable DL in the field of sleep medicine as visualized key inference regions using Eigen-class activation maps. Furthermore, when a DL model for sleep scoring performs external validation, we achieved a relatively good performance. Conclusions: Our main contribution demonstrates the availability of a standardized image-based dataset, and highlights that changing the data sampling rate or number of sensors may not require retraining, although performance decreases slightly as the number of sensors decreases. Key words: sleep stages; polysomnography; dataset; deep learning; computer neural network Study Objectives: Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have been developed, they are tied to a fixed amount of input channels and resolution. In this study, we constructed a standardized image-based PSG dataset in order to overcome the heterogeneity of raw signal data obtained from various PSG devices and various sleep laboratory environments.
Audience	Academic
Author	Shin, Hyun-Woo Kim, Dongyoung Lee, Jeong-Gun Kim, Dong-Kyu Jeong, Jaemin Yoon, Wonhyuck Woo, Yunhee
Author_xml	– sequence: 1 givenname: Jaemin orcidid: 0000-0003-4252-4665 surname: Jeong fullname: Jeong, Jaemin – sequence: 2 givenname: Wonhyuck orcidid: 0000-0001-7942-4196 surname: Yoon fullname: Yoon, Wonhyuck – sequence: 3 givenname: Jeong-Gun orcidid: 0000-0001-6218-4560 surname: Lee fullname: Lee, Jeong-Gun – sequence: 4 givenname: Dongyoung surname: Kim fullname: Kim, Dongyoung – sequence: 5 givenname: Yunhee surname: Woo fullname: Woo, Yunhee – sequence: 6 givenname: Dong-Kyu orcidid: 0000-0003-4917-0177 surname: Kim fullname: Kim, Dong-Kyu email: doctordk@naver.com – sequence: 7 givenname: Hyun-Woo orcidid: 0000-0002-4038-9992 surname: Shin fullname: Shin, Hyun-Woo email: charlie@snu.ac.kr
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/37703391$$D View this record in MEDLINE/PubMed
BookMark	eNqFkc1v1DAQxS3Uim4LR67IEhcuae042cTHqoIWqVIPLWdrYo9TI8cOdvaw_evxfvQAAiEf_DG_9zx6c05OQgxIyAfOLjmT4ip7xPnqJYOpm_oNWfG2ZZUspROyYnzNq56z9oyc5_yDlXsjxVtyJrqOCSH5ivjHBYKBZNwLGuomGLEaIJfzHP02xynEMcH8vKUGFthVaOGpKZ9Sj5CCCyMFP8bklueJ2pjovqMqL8WKag85O-s0LC6Gd-TUgs_4_rhfkO9fvzzd3FX3D7ffbq7vKy2kWCrUwnLdih4azhkHtCBb0QCrmR1kO_S1wWHApl6XOhiAdd2KWmLXasBOgLggnw--c4o_N5gXNbms0XsIGDdZ1X3JoaTRiYJ-OqAjeFQu2Lgk0DtcXXddL5qeSV6oy79QZRmcnC4Dsa68_yb4eOxgM0xo1JxKtGmrXoMvgDgAOsWcE1ql3bIPqTg7rzhTu_GqfZjqON6iqv5QvRr_iz8GETfzf9BfFMe4tg
CitedBy_id	crossref_primary_10_1038_s41746_024_01378_0 crossref_primary_10_1186_s12911_025_03129_x crossref_primary_10_1093_sleep_zsad268 crossref_primary_10_2147_NSS_S463897 crossref_primary_10_1111_jsr_14115 crossref_primary_10_1111_jsr_14379
Cites_doi	10.1088/1361-6579/ac6049 10.1038/s41467-020-17431-x 10.1093/jamia/ocy131 10.3390/healthcare7010001 10.1038/s41746-018-0029-1 10.21053/ceo.2020.01599 10.1093/sleep/zsaa112 10.1109/10.867928 10.1161/01.CIR.101.23.e215 10.1186/s40537-021-00444-8 10.1016/j.cmpb.2019.04.032 10.2147/NSS.S355702 10.1111/jsr.12169 10.1007/s42979-021-00815-1 10.1007/s11325-019-01801-x 10.1093/jamia/ocaa053 10.1109/TNSRE.2017.2721116 10.1038/s41467-018-07229-3 10.21037/qims.2019.05.15 10.1111/j.1365-2869.2008.00700.x 10.1093/sleep/zsy041 10.1093/sleep/22.7.916 10.5665/sleep.4804 10.5664/jcsm.9538 10.5664/jcsm.5894 10.1038/s41746-020-0291-x 10.1371/journal.pone.0233079 10.1093/sleep/23.7.1e 10.1007/s11325-021-02527-5 10.1016/S1389-9457(01)00115-0 10.1109/TNSRE.2021.3098968 10.1093/sleep/zsz159 10.5664/jcsm.2172 10.1109/RBME.2022.3185953 10.3390/ijerph19106322
ContentType	Journal Article
Copyright	The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com 2023 The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com. COPYRIGHT 2023 Oxford University Press
Copyright_xml	– notice: The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com 2023 – notice: The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com. – notice: COPYRIGHT 2023 Oxford University Press
DBID	AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1093/sleep/zsad242
DatabaseName	CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic
DatabaseTitleList	MEDLINE MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Anatomy & Physiology
EISSN	1550-9109
ExternalDocumentID	A778348091 37703391 10_1093_sleep_zsad242 10.1093/sleep/zsad242
Genre	Journal Article
GeographicLocations	South Korea
GeographicLocations_xml	– name: South Korea
GrantInformation_xml	– fundername: SNUH Research Fund grantid: 0320202090
GroupedDBID	--- -DZ -ET ..I .55 .GJ 0R~ 123 1TH 2WC 48X 53G 5RE 5WD 6PF 7X7 88E 8FI 8FJ 8G5 AABZA AACZT AAJQQ AAPQZ AAPXW AARHZ AAUAY AAUQX AAVAP AAWTL ABDFA ABEJV ABGNP ABJNI ABLJU ABNHQ ABPTD ABQNK ABUWG ABVGC ABXVV ACFRR ACGFS ACUTJ ACVCV ACYHN ADBBV ADGZP ADHKW ADIPN ADQBN ADRTK ADVEK AEMDU AEMQT AENEX AENZO AETBJ AEWNT AFFNX AFFZL AFKRA AFOFC AFXAL AGINJ AGMDO AGORE AGUTN AHGBF AHMBA AHMMS AJBYB AJEEA AJNCP ALIPV ALMA_UNASSIGNED_HOLDINGS ALXQX APIBT APJGH AQKUS ATGXG AZQEC BAWUL BAYMD BCRHZ BENPR BEYMZ BPHCQ BTRTY BVXVI C45 CCPQU CDBKE DAKXR DIK DWQXO E3Z EBS EJD ENERS F5P FECEO FLUFQ FOEOM FOTVD FYUFA GAUVT GJXCC GNUQQ GUQSH H13 HMCUK IAO IHR ITC J5H JXSIZ KBUDW KOP KSI KSN M1P M2M M2O MBLQV MHKGH MVM NOMLY NOYVH NU- O9- OAUYM OCZFY ODMLO OJZSN OK1 OPAEJ OVD OWPYF P2P PAFKI PEELM PHGZM PHGZT PQQKQ PROAC PSQYO PSYQQ ROX ROZ RUSNO SJN TEORI TJX TR2 TWZ UKHRP UMC WOQ X7M YAYTL YKOAZ YXANX ZGI ZXP AAYXX AFFHD CITATION PJZUB PPXIY CGR CUY CVF ECM EIF NPM 7X8 PUEGO
ID	FETCH-LOGICAL-c393t-ec3f1c538a41101aefa9534a020fb95b82debbe426411adaa625329e75cae73a3
ISICitedReferencesCount	6
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001074727700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0161-8105 1550-9109
IngestDate	Thu Oct 02 05:47:54 EDT 2025 Tue Nov 11 11:17:20 EST 2025 Tue Nov 04 18:35:00 EST 2025 Thu Apr 03 06:57:08 EDT 2025 Sat Nov 29 02:46:34 EST 2025 Tue Nov 18 20:12:33 EST 2025 Fri May 23 09:42:26 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Keywords	deep learning computer neural network polysomnography sleep stages dataset
Language	English
License	This article is published and distributed under the terms of the Oxford University Press, Standard Journals Publication Model (https://academic.oup.com/pages/standard-publication-reuse-rights) https://academic.oup.com/pages/standard-publication-reuse-rights The Author(s) 2023. Published by Oxford University Press on behalf of Sleep Research Society. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c393t-ec3f1c538a41101aefa9534a020fb95b82debbe426411adaa625329e75cae73a3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
ORCID	0000-0001-7942-4196 0000-0001-6218-4560 0000-0003-4252-4665 0000-0003-4917-0177 0000-0002-4038-9992
PMID	37703391
PQID	2864900173
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_2864900173 gale_infotracmisc_A778348091 gale_infotracacademiconefile_A778348091 pubmed_primary_37703391 crossref_citationtrail_10_1093_sleep_zsad242 crossref_primary_10_1093_sleep_zsad242 oup_primary_10_1093_sleep_zsad242
PublicationCentury	2000
PublicationDate	2023-12-11
PublicationDateYYYYMMDD	2023-12-11
PublicationDate_xml	– month: 12 year: 2023 text: 2023-12-11 day: 11
PublicationDecade	2020
PublicationPlace	US
PublicationPlace_xml	– name: US – name: United States
PublicationTitle	Sleep (New York, N.Y.)
PublicationTitleAlternate	Sleep
PublicationYear	2023
Publisher	Oxford University Press
Publisher_xml	– name: Oxford University Press
References	Phan (2023121103384111600_CIT0003) 2022; 43 Lee (2023121103384111600_CIT0008) 2022; 18 Yoon (2023121103384111600_CIT0009) 2020; 13 Sarker (2023121103384111600_CIT0030) 2021; 2 Selvaraju (2023121103384111600_CIT0016) 2017 Rajkomar (2023121103384111600_CIT0035) 2018; 1 Younes (2023121103384111600_CIT0018) 2016; 12 Zhang (2023121103384111600_CIT0022) 2019; 42 Goldberger (2023121103384111600_CIT0025) 2000; 101 O’Reilly (2023121103384111600_CIT0026) 2014; 23 Norman (2023121103384111600_CIT0006) 2000; 23 Muhammad (2023121103384111600_CIT0014) 2021; 2 Giuste (2023121103384111600_CIT0033) 2022; 16 Supratak (2023121103384111600_CIT0013) 2017; 25 Kemp (2023121103384111600_CIT0028) 2000; 47 Guillot (2023121103384111600_CIT0036) 2021; 29 Deng (2023121103384111600_CIT0007) 2019; 23 Kim (2023121103384111600_CIT0039) 2019; 9 Berry (2023121103384111600_CIT0001) 2012; 8 Loredo (2023121103384111600_CIT0005) 1999; 22 Di Pumpo (2023121103384111600_CIT0010) 2022; 26 Abou Jaoude (2023121103384111600_CIT0023) 2020; 43 Li (2023121103384111600_CIT0029) 2022; 19 Zhou (2023121103384111600_CIT0015) 2016 Faust (2023121103384111600_CIT0012) 2019; 176 Kim (2023121103384111600_CIT0011) 2015; 38 Lauritsen (2023121103384111600_CIT0034) 2020; 11 Xu (2023121103384111600_CIT0024) 2022; 14 Biswal (2023121103384111600_CIT0021) 2018; 25 Danker-Hopfe (2023121103384111600_CIT0037) 2009; 18 Stephansen (2023121103384111600_CIT0019) 2018; 9 Alzubaidi (2023121103384111600_CIT0031) 2021; 8 Quan (2023121103384111600_CIT0027) 1997; 20 Patanaik (2023121103384111600_CIT0020) 2018; 41 Collop (2023121103384111600_CIT0004) 2002; 3 Payrovnaziri (2023121103384111600_CIT0032) 2020; 27 Chattu (2023121103384111600_CIT0002) 2018; 7 Sridhar (2023121103384111600_CIT0017) 2020; 3 Ko (2023121103384111600_CIT0038) 2020; 15 37843473 - Sleep. 2023 Dec 11;46(12)
References_xml	– volume: 43 start-page: 04TR01 issue: 4 year: 2022 ident: 2023121103384111600_CIT0003 article-title: , Automatic sleep staging of EEG signals: recent development, challenges, and future directions publication-title: Physiol Meas. doi: 10.1088/1361-6579/ac6049 – volume: 20 start-page: 1077 issue: 12 year: 1997 ident: 2023121103384111600_CIT0027 article-title: The Sleep Heart Health Study: design, rationale, and methods publication-title: Sleep. – volume: 11 start-page: 3852 issue: 1 year: 2020 ident: 2023121103384111600_CIT0034 article-title: Explainable artificial intelligence model to predict acute critical illness from electronic health records publication-title: Nat Commun. doi: 10.1038/s41467-020-17431-x – volume: 25 start-page: 1643 issue: 12 year: 2018 ident: 2023121103384111600_CIT0021 article-title: Expert-level sleep scoring with deep neural networks publication-title: J Am Med Inform Assoc. doi: 10.1093/jamia/ocy131 – volume: 7 start-page: 1 issue: 1 year: 2018 ident: 2023121103384111600_CIT0002 article-title: The global problem of insufficient sleep and its serious public health implications publication-title: Healthcare (Basel) doi: 10.3390/healthcare7010001 – volume: 1 start-page: 18 issue: 1 year: 2018 ident: 2023121103384111600_CIT0035 article-title: Scalable and accurate deep learning with electronic health records publication-title: NPJ Digit Med doi: 10.1038/s41746-018-0029-1 – volume: 13 start-page: 318 issue: 4 year: 2020 ident: 2023121103384111600_CIT0009 article-title: Sleep tests in the non-contact era of the COVID-19 pandemic: home sleep tests versus in-laboratory polysomnography publication-title: Clin Exp Otorhinolaryngol doi: 10.21053/ceo.2020.01599 – volume: 43 issue: 11 year: 2020 ident: 2023121103384111600_CIT0023 article-title: Expert-level automated sleep staging of long-term scalp electroencephalography recordings using deep learning publication-title: Sleep. doi: 10.1093/sleep/zsaa112 – volume: 47 start-page: 1185 issue: 9 year: 2000 ident: 2023121103384111600_CIT0028 article-title: Analysis of a sleep-dependent neuronal feedback loop: the slow-wave microcontinuity of the EEG publication-title: IEEE Trans Biomed Eng. doi: 10.1109/10.867928 – volume: 101 start-page: E215 issue: 23 year: 2000 ident: 2023121103384111600_CIT0025 article-title: PhysioBank, PhysioToolkit, and Physionet: components of a new research resource for complex physiologic signals publication-title: Circulation. doi: 10.1161/01.CIR.101.23.e215 – volume: 8 start-page: 53 issue: 1 year: 2021 ident: 2023121103384111600_CIT0031 article-title: Review of deep learning: concepts, CNN architectures, challenges, applications, future directions publication-title: J Big Data doi: 10.1186/s40537-021-00444-8 – volume: 176 start-page: 81 year: 2019 ident: 2023121103384111600_CIT0012 article-title: A review of automated sleep stage scoring based on physiological signals for the new millennia publication-title: Comput Methods Programs Biomed. doi: 10.1016/j.cmpb.2019.04.032 – volume: 14 start-page: 995 year: 2022 ident: 2023121103384111600_CIT0024 article-title: Sleep stage classification based on multi-centers: comparison between different ages, mental health conditions and acquisition devices publication-title: Nat Sci Sleep doi: 10.2147/NSS.S355702 – volume: 23 start-page: 628 issue: 6 year: 2014 ident: 2023121103384111600_CIT0026 article-title: Montreal Archive of Sleep Studies: an open-access resource for instrument benchmarking and exploratory research publication-title: J Sleep Res. doi: 10.1111/jsr.12169 – volume: 2 start-page: 420 issue: 6 year: 2021 ident: 2023121103384111600_CIT0030 article-title: Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions publication-title: SN Comput Sci doi: 10.1007/s42979-021-00815-1 – volume: 23 start-page: 719 issue: 2 year: 2019 ident: 2023121103384111600_CIT0007 article-title: Interrater agreement between American and Chinese sleep centers according to the 2014 AASM standard publication-title: Sleep Breath. doi: 10.1007/s11325-019-01801-x – start-page: 618 year: 2017 ident: 2023121103384111600_CIT0016 article-title: Grad-CAM: visual explanations from deep networks via gradient-based localization publication-title: Proceedings of the IEEE international conference on computer vision – volume: 27 start-page: 1173 issue: 7 year: 2020 ident: 2023121103384111600_CIT0032 article-title: Explainable artificial intelligence models using real-world electronic health record data: a systematic scoping review publication-title: J Am Med Inform Assoc. doi: 10.1093/jamia/ocaa053 – volume: 25 start-page: 1998 issue: 11 year: 2017 ident: 2023121103384111600_CIT0013 article-title: DeepSleepNet: a model for automatic sleep stage scoring based on raw single-channel EEG publication-title: IEEE Trans Neural Syst Rehabil Eng. doi: 10.1109/TNSRE.2017.2721116 – volume: 9 start-page: 5229 issue: 1 year: 2018 ident: 2023121103384111600_CIT0019 article-title: Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy publication-title: Nat Commun. doi: 10.1038/s41467-018-07229-3 – start-page: 2921 year: 2016 ident: 2023121103384111600_CIT0015 article-title: Learning deep features for discriminative localization publication-title: In Proceedings of the IEEE conference on computer vision and pattern recognition – volume: 2 issue: 1 year: 2021 ident: 2023121103384111600_CIT0014 article-title: Eigen-CAM: visual explanations for deep convolutional neural network publication-title: SN Computer Science – volume: 9 start-page: 942 issue: 6 year: 2019 ident: 2023121103384111600_CIT0039 article-title: Improvement diagnostic accuracy of sinusitis recognition in paranasal sinus X-ray using multiple deep learning models publication-title: Quant Imaging Med Surg doi: 10.21037/qims.2019.05.15 – volume: 18 start-page: 74 issue: 1 year: 2009 ident: 2023121103384111600_CIT0037 article-title: Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard publication-title: J Sleep Res. doi: 10.1111/j.1365-2869.2008.00700.x – volume: 41 issue: 5 year: 2018 ident: 2023121103384111600_CIT0020 article-title: An end-to-end framework for real-time automatic sleep stage classification publication-title: Sleep. doi: 10.1093/sleep/zsy041 – volume: 22 start-page: 916 issue: 7 year: 1999 ident: 2023121103384111600_CIT0005 article-title: Night-to-night arousal variability and interscorer reliability of arousal measurements publication-title: Sleep. doi: 10.1093/sleep/22.7.916 – volume: 38 start-page: 1027 issue: 7 year: 2015 ident: 2023121103384111600_CIT0011 article-title: An economic evaluation of home versus laboratory-based diagnosis of obstructive sleep apnea publication-title: Sleep. doi: 10.5665/sleep.4804 – volume: 18 start-page: 193 issue: 1 year: 2022 ident: 2023121103384111600_CIT0008 article-title: Interrater reliability of sleep stage scoring: a meta-analysis publication-title: J Clin Sleep Med. doi: 10.5664/jcsm.9538 – volume: 12 start-page: 885 issue: 6 year: 2016 ident: 2023121103384111600_CIT0018 article-title: Staging sleep in polysomnograms: analysis of inter-scorer variability publication-title: J Clin Sleep Med. doi: 10.5664/jcsm.5894 – volume: 3 start-page: 106 issue: 1 year: 2020 ident: 2023121103384111600_CIT0017 article-title: Deep learning for automated sleep staging using instantaneous heart rate publication-title: npj Digital Med. doi: 10.1038/s41746-020-0291-x – volume: 15 start-page: e0233079 issue: 5 year: 2020 ident: 2023121103384111600_CIT0038 article-title: Deep learning assisted detection of glaucomatous optic neuropathy and potential designs for a generalizable model publication-title: PLoS One. doi: 10.1371/journal.pone.0233079 – volume: 23 start-page: 901 issue: 7 year: 2000 ident: 2023121103384111600_CIT0006 article-title: Interobserver agreement among sleep scorers from different centers in a large dataset publication-title: Sleep. doi: 10.1093/sleep/23.7.1e – volume: 26 start-page: 1641 issue: 4 year: 2022 ident: 2023121103384111600_CIT0010 article-title: Multiple-access versus telemedicine home-based sleep apnea testing for obstructive sleep apnea (OSA) diagnosis: a cost-minimization study publication-title: Sleep Breath. doi: 10.1007/s11325-021-02527-5 – volume: 3 start-page: 43 issue: 1 year: 2002 ident: 2023121103384111600_CIT0004 article-title: Scoring variability between polysomnography technologists in different sleep laboratories publication-title: Sleep Med. doi: 10.1016/S1389-9457(01)00115-0 – volume: 29 start-page: 1441 year: 2021 ident: 2023121103384111600_CIT0036 article-title: RobustSleepNet: transfer learning for automated sleep staging at scale publication-title: IEEE Trans Neural Syst Rehabil Eng. doi: 10.1109/TNSRE.2021.3098968 – volume: 42 issue: 11 year: 2019 ident: 2023121103384111600_CIT0022 article-title: Automated sleep stage scoring of the Sleep Heart Health Study using deep neural networks publication-title: Sleep. doi: 10.1093/sleep/zsz159 – volume: 8 start-page: 597 issue: 5 year: 2012 ident: 2023121103384111600_CIT0001 article-title: Rules for scoring respiratory events in sleep: update of the 2007 AASM Manual for the Scoring of Sleep and Associated Events. Deliberations of the sleep apnea definitions task force of the American Academy of Sleep Medicine publication-title: J Clin Sleep Med. doi: 10.5664/jcsm.2172 – volume: 16 start-page: 5 year: 2022 ident: 2023121103384111600_CIT0033 article-title: Explainable artificial intelligence methods in combating pandemics: a systematic review publication-title: IEEE Rev Biomed Eng. doi: 10.1109/RBME.2022.3185953 – volume: 19 start-page: 6322 issue: 10 year: 2022 ident: 2023121103384111600_CIT0029 article-title: A deep learning method approach for sleep stage classification with EEG spectrogram publication-title: Int J Environ Res Public Health. doi: 10.3390/ijerph19106322 – reference: 37843473 - Sleep. 2023 Dec 11;46(12):
SSID	ssj0016493
Score	2.4644504
Snippet	Abstract Study Objectives Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for... Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated sleep scoring have... Study Objectives: Polysomnography (PSG) scoring is labor-intensive, subjective, and often ambiguous. Recently several deep learning (DL) models for automated...
SourceID	proquest gale pubmed crossref oup
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1
SubjectTerms	Algorithms Data mining Deep Learning Medical colleges Neural networks Polysomnography - methods Sleep - physiology Sleep apnea syndromes Sleep Stages - physiology
Title	Standardized image-based polysomnography database and deep learning algorithm for sleep-stage classification
URI	https://www.ncbi.nlm.nih.gov/pubmed/37703391 https://www.proquest.com/docview/2864900173
Volume	46
WOSCitedRecordID	wos001074727700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVPQU databaseName: Health & Medical Collection customDbUrl: eissn: 1550-9109 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0016493 issn: 0161-8105 databaseCode: 7X7 dateStart: 20161001 isFulltext: true titleUrlDefault: https://search.proquest.com/healthcomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1550-9109 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0016493 issn: 0161-8105 databaseCode: BENPR dateStart: 20161001 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: Psychology Database customDbUrl: eissn: 1550-9109 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0016493 issn: 0161-8105 databaseCode: M2M dateStart: 20161001 isFulltext: true titleUrlDefault: https://www.proquest.com/psychology providerName: ProQuest – providerCode: PRVPQU databaseName: Research Library customDbUrl: eissn: 1550-9109 dateEnd: 20241207 omitProxy: false ssIdentifier: ssj0016493 issn: 0161-8105 databaseCode: M2O dateStart: 20161001 isFulltext: true titleUrlDefault: https://search.proquest.com/pqrl providerName: ProQuest
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELe6DaG9IGB8FMbkSWg8lGiN3czxY0EDhFiZ2IC-RY7jdJWapOrHtE7if-cucdIENgEPvLht_JXmfrk72_dByEtPRox1Y-aoMO46vdjrOkqYI4d7IIz9GARiblX57ZMYDPzhUJ62Wj9KX5jLiUhT_-pKTv8rqeEaEBtdZ_-B3NWgcAG-A9GhBLJD-VeEP7ObA-Nr0CXHCfALB0VVhPkYVvMsSW2Q6g4ah2JNfn4QGTMtU0iMOmoyymbjxUWSWyHOJ1DpgBo5Mh2N2jaaF60palXbM2x1U3Kf2mbDR1NaACsMarJmOcXZ__csvVgtdeU8VFoJYS_n_bJmMJAUyn86WiG3qm9dMI5mIJa1GstuARugsMg6P7ZbkhZ37EY-b2Ng4R-Dz-u5iliv0RJoMk1yCnMBTI1Ldy3wKjPEsmqDbDHhSWCKW2-OB6dfqmOoo57kNjArzHiYz3doZ9smd8v-DZ3GSvaGu-Rvq5Zcezm_T-7ZZQftF3B5QFomfUh2-qlaZMmKHtDcEDg_YdkhkzqCaA1B9BcE0RJBFNpTRBAtEUQrBFFAEK0hiDYR9Ih8fXd8_vaDY5NyOJpLvnCM5rGrQUyqHmiOrjKxkh7vKVh2xKH0Qp9FJgwNKtquqyKlYIHNmTTC08oIrvhjsplmqXlKaNiF5xfywr1ZebESsBbRwgchLHBp3Cavy8caaBuxHhOnTILCcoIH-d0HliBtclA1nxahWm5r-AppFCBOYDytrCcK3BUGQwv6ArPP-KBJt8luoyWwXt2o3gcq_2my_RIDAXZHm8bUZMt5wHyAF2qJvE2eFOCohiqR9ezWmudke_1K7ZLNxWxpXpA7-nIxns_2yIYYirz09yyo4dcJO8nLzz8B6CbGXg
linkProvider	ProQuest
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=Standardized+image-based+polysomnography+database+and+deep+learning+algorithm+for+sleep-stage+classification&rft.jtitle=Sleep+%28New+York%2C+N.Y.%29&rft.au=Jeong%2C+Jaemin&rft.au=Yoon%2C+Wonhyuck&rft.au=Lee%2C+Jeong-Gun&rft.au=Kim%2C+Dongyoung&rft.date=2023-12-11&rft.eissn=1550-9109&rft.volume=46&rft.issue=12&rft_id=info:doi/10.1093%2Fsleep%2Fzsad242&rft_id=info%3Apmid%2F37703391&rft.externalDocID=37703391
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0161-8105&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0161-8105&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0161-8105&client=summon