A Multi-Level Interpretable Sleep Stage Scoring System by Infusing Experts' Knowledge Into a Deep Network Architecture

In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is partic...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 46; no. 7; pp. 5044 - 5061
Main Authors:	Niknazar, Hamid, Mednick, Sara C.
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.07.2024 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Adult Algorithms Artificial neural networks Black-box problem Brain modeling Computer vision convolutional neural network Deep Learning electroencephalogram Electroencephalography Feature extraction Female Humans interpretable system Kernel Machine learning Male Neural Networks, Computer Polysomnography Signal processing Signal Processing, Computer-Assisted Sleep sleep stages Sleep Stages - physiology Time-frequency analysis Young Adult
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is particularly problematic for high-risk applications such as medical-related decision-making. The current study goal was to design an interpretable deep learning system for time series classification of electroencephalogram (EEG) for sleep stage scoring as a step toward designing a transparent system. We have developed an interpretable deep neural network that includes a kernel-based layer guided by a set of principles used for sleep scoring by human experts in the visual analysis of polysomnographic records. A kernel-based convolutional layer was defined and used as the first layer of the system and made available for user interpretation. The trained system and its results were interpreted in four levels from microstructure of EEG signals, such as trained kernels and effect of each kernel on the detected stages, to macrostructures, such as transitions between stages. The proposed system demonstrated greater performance than prior studies and the system learned information consistent with expert knowledge.
AbstractList	In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is particularly problematic for high-risk applications such as medical-related decision-making. The current study goal was to design an interpretable deep learning system for time series classification of electroencephalogram (EEG) for sleep stage scoring as a step toward designing a transparent system. We have developed an interpretable deep neural network that includes a kernel-based layer guided by a set of principles used for sleep scoring by human experts in the visual analysis of polysomnographic records. A kernel-based convolutional layer was defined and used as the first layer of the system and made available for user interpretation. The trained system and its results were interpreted in four levels from microstructure of EEG signals, such as trained kernels and effect of each kernel on the detected stages, to macrostructures, such as transitions between stages. The proposed system demonstrated greater performance than prior studies and the system learned information consistent with expert knowledge. In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is particularly problematic for high-risk applications such as medical-related decision-making. The current study goal was to design an interpretable deep learning system for time series classification of electroencephalogram (EEG) for sleep stage scoring as a step toward designing a transparent system. We have developed an interpretable deep neural network that includes a kernel-based layer guided by a set of principles used for sleep scoring by human experts in the visual analysis of polysomnographic records. A kernel-based convolutional layer was defined and used as the first layer of the system and made available for user interpretation. The trained system and its results were interpreted in four levels from microstructure of EEG signals, such as trained kernels and effect of each kernel on the detected stages, to macrostructures, such as transitions between stages. The proposed system demonstrated greater performance than prior studies and the system learned information consistent with expert knowledge.In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational challenges remain for user applications due to a lack of interpretability of algorithmic decisions and results. This black box problem is particularly problematic for high-risk applications such as medical-related decision-making. The current study goal was to design an interpretable deep learning system for time series classification of electroencephalogram (EEG) for sleep stage scoring as a step toward designing a transparent system. We have developed an interpretable deep neural network that includes a kernel-based layer guided by a set of principles used for sleep scoring by human experts in the visual analysis of polysomnographic records. A kernel-based convolutional layer was defined and used as the first layer of the system and made available for user interpretation. The trained system and its results were interpreted in four levels from microstructure of EEG signals, such as trained kernels and effect of each kernel on the detected stages, to macrostructures, such as transitions between stages. The proposed system demonstrated greater performance than prior studies and the system learned information consistent with expert knowledge.
Author	Mednick, Sara C. Niknazar, Hamid
Author_xml	– sequence: 1 givenname: Hamid orcidid: 0000-0003-0413-9133 surname: Niknazar fullname: Niknazar, Hamid email: hniknaza@uci.edu organization: Department of Cognitive Sciences, University of California, Irvine, CA, USA – sequence: 2 givenname: Sara C. orcidid: 0000-0002-0906-3097 surname: Mednick fullname: Mednick, Sara C. organization: Department of Cognitive Sciences, University of California, Irvine, CA, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/38358869$$D View this record in MEDLINE/PubMed
BookMark	eNp9kU1v1DAQhi1URLeFP4AQssQBLln8Fcc-rkoLK7aAtOUcOc6kuGTj1HZa9t_Xyy4I9cDJI-t5ZkbznqCjwQ-A0EtK5pQS_f7q2-JyOWeEiTnnUtKKPEEzRiUpNNPsCM0IlaxQiqljdBLjDSFUlIQ_Q8dc8VIpqWfoboEvpz65YgV30OPlkCCMAZJpesDrHmDE62Suc219cMM1Xm9jgg1utpntprj7Ov81QkjxLf48-Pse2kznPh4b_GHnf4F078NPvAj2h0tg0xTgOXramT7Ci8N7ir5fnF-dfSpWXz8uzxarwvKSpcIwaRsBpq1azTW1jJdcCqoa01lOpQQN1raqIcJqpTVVAkphuoq0VrdNC_wUvdv3HYO_nSCmeuOihb43A_gp1vlOigmmKMvom0fojZ_CkLerOZGiIoyxKlOvD9TUbKCtx-A2JmzrPxfNANsDNvgYA3R_EUrqXWz179jqXWz1IbYsqUeSdckk54cUjOv_r77aqw4A_pkluKwI5Q-vWqVF
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1016_j_bbe_2024_06_004 crossref_primary_10_1088_1361_6501_ade327 crossref_primary_10_3390_bioengineering11121226
Cites_doi	10.1016/j.neunet.2020.07.010 10.1371/journal.pone.0216456 10.1016/S1389-9457(01)00115-0 10.1177/074873048600100404 10.1016/j.bspc.2022.103486 10.1109/TBME.2015.2510365 10.1523/JNEUROSCI.2604-11.2011 10.1016/j.physa.2020.125685 10.1109/JBHI.2020.2978004 10.1016/j.jneumeth.2019.108320 10.1142/s0129183113500174 10.1109/TNSRE.2017.2721116 10.1016/j.neuroimage.2017.07.018 10.1111/j.1439-054X.2006.00101.x 10.1016/j.dt.2019.12.002 10.3389/fphys.2021.628502 10.1109/ACCESS.2022.3163250 10.1016/j.jneumeth.2016.07.012 10.1016/j.cub.2008.06.033 10.1007/s10439-015-1444-y 10.1016/j.jneumeth.2011.12.022 10.1016/j.bbe.2020.01.010 10.5664/jcsm.2350 10.1161/01.CTR.101.23.e215 10.3390/s20174677 10.1007/s10916-014-0018-0 10.1016/j.artmed.2021.102038 10.1371/journal.pone.0144720 10.1159/000441975 10.1016/j.nbscr.2019.01.001 10.1109/TNSRE.2016.2552539 10.1109/CVPR.2017.354 10.1109/CVPR.2018.00920 10.1111/jsr.12169 10.1109/TCBB.2019.2912955 10.1016/j.bspc.2020.102037 10.1109/10.966600 10.1016/j.bspc.2019.101576 10.1016/j.bspc.2020.102326 10.1109/TNSRE.2017.2733220 10.1145/3233547.3233725 10.1111/j.1365-2869.2008.00700.x 10.1053/smrv.2002.0252 10.1016/j.eswa.2018.03.020 10.1016/j.smrv.2011.06.003 10.1016/j.bspc.2017.12.001 10.1007/978-3-030-28954-6_9 10.1109/TBME.2018.2872652 10.1093/sleep/zsx139 10.3414/ME09-01-0054 10.1109/TNSRE.2015.2465177 10.1109/tnsre.2023.3243589 10.1016/j.cmpb.2019.105089 10.1038/s41467-018-07229-3 10.1016/j.cmpb.2016.09.008 10.1016/j.neucom.2016.04.049 10.1016/j.bbe.2015.11.003 10.1109/TIP.2020.2993098 10.3389/fpsyg.2014.00099 10.1109/TNSRE.2018.2813138 10.1109/TCYB.2017.2788081 10.1093/sleep/32.2.139 10.3389/fnins.2021.614182 10.1016/j.eswa.2016.07.004 10.1088/1361-6579/ab921e
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2024
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2024.3366170
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEL CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	Technology Research Database MEDLINE - Academic MEDLINE
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: RIE name: IEL url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	5061
ExternalDocumentID	38358869 10_1109_TPAMI_2024_3366170 10436701
Genre	orig-research Journal Article Research Support, N.I.H., Extramural
GrantInformation_xml	– fundername: NIH grantid: R01-AG062288 – fundername: NIA NIH HHS grantid: R01 AG062288
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION AAYOK CGR CUY CVF ECM EIF NPM RIG 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c352t-a26cb4ead7d9391c23536418bafc3166e9eccd8b04c9899184e54af70dc9dbde3
IEDL.DBID	RIE
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001240147800029&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Sun Sep 28 02:07:42 EDT 2025 Sun Nov 30 04:52:55 EST 2025 Thu Apr 03 07:02:31 EDT 2025 Sat Nov 29 02:58:26 EST 2025 Tue Nov 18 22:13:16 EST 2025 Wed Aug 27 01:58:05 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	7
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c352t-a26cb4ead7d9391c23536418bafc3166e9eccd8b04c9899184e54af70dc9dbde3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0003-0413-9133 0000-0002-0906-3097
PMID	38358869
PQID	3064702227
PQPubID	85458
PageCount	18
ParticipantIDs	pubmed_primary_38358869 crossref_primary_10_1109_TPAMI_2024_3366170 proquest_miscellaneous_2928242812 proquest_journals_3064702227 ieee_primary_10436701 crossref_citationtrail_10_1109_TPAMI_2024_3366170
PublicationCentury	2000
PublicationDate	2024-07-01
PublicationDateYYYYMMDD	2024-07-01
PublicationDate_xml	– month: 07 year: 2024 text: 2024-07-01 day: 01
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationTitleAlternate	IEEE Trans Pattern Anal Mach Intell
PublicationYear	2024
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref59 Phan (ref91) 2020; 41 Seo (ref54) 2020; 61 Iber (ref10) 2007 Phan (ref52) Sokolovsky (ref33) 2020; 17 Zhang (ref36) 2020; 183 Ghimatgar (ref81) 2019; 324 Rodenbeck (ref94) 2006; 10 ref45 ref48 ref47 Liu (ref78) 2020; 55 ref8 Diykh (ref17) 2016; 24 Hassan (ref20) 2016; 36 Hassan (ref28) 2016; 137 Zeiler (ref64) Stephansen (ref38) 2018; 9 Dao (ref58) Seifpour (ref84) 2018; 104 Liang (ref87) 2016; 63 ref39 Hu (ref43) 2020; 16 Kingma (ref75) 2017 Seeliger (ref30) 2018; 180 Cai (ref93) 2021; 68 Sanders (ref21) Gillick (ref31) Koh (ref5) Vilamala (ref66) Sattari (ref9) 2019; 6 Agarwal (ref25) 2001; 48 Liang (ref85) 2012; 205 Zhang (ref3) Jozefowicz (ref32) 2016 Diykh (ref16) 2016; 63 Chen (ref29) Jadhav (ref92) 2020; 40 Hassan (ref86) 2016; 271 Noé (ref46) 2002 Li (ref35) 2020; 1678 Acharya (ref18) 2015; 74 ref14 Radha (ref19) Şen (ref22) 2014; 38 Hinterberger (ref98) 2014; 5 Danker-Hopfe (ref13) 2009; 18 Ronzhina (ref24) 2012; 16 Peker (ref23) 2016; 207 Allada (ref7) 2008; 18 Devuyst (ref74) 2005 Phan (ref37) 2019; 66 Zhang (ref34) 2019; 49 ref95 Humayun (ref90) Chambon (ref51) 2018; 26 ref89 Phan (ref49) 2022; 44 Qu (ref79) 2020; 24 Fu (ref80) 2021; 12 Sors (ref56) 2018; 42 Rahuja (ref41) Selvaraju (ref63) Pathak (ref65) 2021; 114 Phan (ref57) Chang (ref42) Tsinalis (ref88) 2016 Tsinalis (ref76) 2016; 44 Simonyan (ref60) 2013 Al-Hussaini (ref68) Yang (ref82) 2022; 71 Angelov (ref2) 2020; 130 Kales (ref11) 1968 Liu (ref44) 2021; 567 Dong (ref55) 2018; 26 Ioffe (ref72) Supratak (ref77) 2017; 25 Doshi-Velez (ref1) 2017 Baek (ref69) 2022; 10 Andrillon (ref97) 2011; 31 Wang (ref6) 2020; 29 Bau (ref4) 2017 Sundararajan (ref61) 2017 Zhou (ref62) ref71 ref70 ref73 Shen (ref83) 2020; 20 Fraiwan (ref15) 2010; 49 ref67 De Gennaro (ref96) 2003; 7 Enshaeifar (ref26) 2016; 24 Hassan (ref27) 2016; 2 Wang (ref50) 2022; 74 Eltrass (ref40) 2021; 65 Collop (ref12) 2002; 3 Sun (ref53) 2017; 40
References_xml	– volume: 130 start-page: 185 year: 2020 ident: ref2 article-title: Towards explainable deep neural networks (xDNN) publication-title: Neural Netw. doi: 10.1016/j.neunet.2020.07.010 – start-page: 721 volume-title: Proc. 4th Mach. Learn. Healthcare Conf. ident: ref68 article-title: SLEEPER: Interpretable sleep staging via prototypes from expert rules – start-page: 1 volume-title: Proc. IEEE EMBS Int. Conf. Biomed. Health Inform. ident: ref90 article-title: End-to-end sleep staging with raw single channel EEG using deep residual ConvNets – start-page: 1 volume-title: Proc. IEEE Int. Conf. Intell. Technol. ident: ref41 article-title: A deep neural network approach to automatic multi-class classification of electrocardiogram signals – ident: ref89 doi: 10.1371/journal.pone.0216456 – start-page: 3549 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref3 article-title: MDNet: A semantically and visually interpretable medical image diagnosis network – volume: 3 start-page: 43 issue: 1 year: 2002 ident: ref12 article-title: Scoring variability between polysomnography technologists in different sleep laboratories publication-title: Sleep Med. doi: 10.1016/S1389-9457(01)00115-0 – start-page: 1 volume-title: Proc. IEEE 27th Int. Workshop Mach. Learn. Signal Process. ident: ref66 article-title: Deep convolutional neural networks for interpretable analysis of EEG sleep stage scoring – ident: ref95 doi: 10.1177/074873048600100404 – volume: 74 year: 2022 ident: ref50 article-title: A novel sleep staging network based on multi-scale dual attention publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2022.103486 – volume: 63 start-page: 2108 issue: 10 year: 2016 ident: ref87 article-title: Combination of expert knowledge and a genetic fuzzy inference system for automatic sleep staging publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2015.2510365 – volume: 31 start-page: 17821 issue: 49 year: 2011 ident: ref97 article-title: Sleep spindles in humans: Insights from intracranial EEG and unit recordings publication-title: J. Neurosci. doi: 10.1523/JNEUROSCI.2604-11.2011 – volume: 567 year: 2021 ident: ref44 article-title: Automatic sleep staging with a single-channel EEG based on ensemble empirical mode decomposition publication-title: Physica A: Stat. Mech. Appl. doi: 10.1016/j.physa.2020.125685 – volume: 24 start-page: 2833 issue: 10 year: 2020 ident: ref79 article-title: A residual based attention model for EEG based sleep staging publication-title: IEEE J. Biomed. Health Inform. doi: 10.1109/JBHI.2020.2978004 – volume: 324 year: 2019 ident: ref81 article-title: An automatic single-channel EEG-based sleep stage scoring method based on hidden Markov model publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2019.108320 – start-page: 448 volume-title: Proc. 32nd Int. Conf. Mach. Learn. ident: ref72 article-title: Batch normalization: Accelerating deep network training by reducing internal covariate shift – start-page: 818 volume-title: Proc. 13th Eur. Conf. Comput. Vis. ident: ref64 article-title: Visualizing and understanding convolutional networks – year: 2017 ident: ref75 article-title: Adam: A method for stochastic optimization – year: 2017 ident: ref61 article-title: Axiomatic attribution for deep networks – ident: ref59 doi: 10.1142/s0129183113500174 – volume: 25 start-page: 1998 issue: 11 year: 2017 ident: ref77 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 – year: 2017 ident: ref1 article-title: Towards a rigorous science of interpretable machine learning – volume: 180 start-page: 253 year: 2018 ident: ref30 article-title: Convolutional neural network-based encoding and decoding of visual object recognition in space and time publication-title: NeuroImage doi: 10.1016/j.neuroimage.2017.07.018 – volume: 10 start-page: 159 issue: 4 year: 2006 ident: ref94 article-title: A review of sleep EEG patterns part I: A compilation of amended rules for their visual recognition according to Rechtschaffen and Kales publication-title: Somnologie doi: 10.1111/j.1439-054X.2006.00101.x – volume: 16 start-page: 1116 issue: 6 year: 2020 ident: ref43 article-title: Gabor-CNN for object detection based on small samples publication-title: Defence Technol. doi: 10.1016/j.dt.2019.12.002 – start-page: 618 volume-title: Proc. IEEE Int. Conf. Comput. Vis. ident: ref63 article-title: Grad-CAM: Visual explanations from deep networks via gradient-based localization – volume: 12 year: 2021 ident: ref80 article-title: Deep learning in automatic sleep staging with a single channel electroencephalography publication-title: Front. Physiol. doi: 10.3389/fphys.2021.628502 – volume: 10 start-page: 36895 year: 2022 ident: ref69 article-title: Automatic sleep scoring using intrinsic mode based on interpretable deep neural networks publication-title: IEEE Access doi: 10.1109/ACCESS.2022.3163250 – volume: 68 start-page: 777 issue: 2 year: 2021 ident: ref93 article-title: A graph-temporal fused dual-input convolutional neural network for detecting sleep stages from EEG signals publication-title: IEEE Trans. Circuits Syst. II: Express Briefs – volume: 2 issue: 3 year: 2016 ident: ref27 article-title: Computer-aided obstructive sleep apnea identification using statistical features in the EMD domain and extreme learning machine publication-title: Biomed. Phys. Eng. Exp. – volume: 271 start-page: 107 year: 2016 ident: ref86 article-title: A decision support system for automatic sleep staging from EEG signals using tunable Q-factor wavelet transform and spectral features publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2016.07.012 – volume: 18 start-page: R670 issue: 15 year: 2008 ident: ref7 article-title: Unearthing the phylogenetic roots of sleep publication-title: Curr. Biol. doi: 10.1016/j.cub.2008.06.033 – volume: 44 start-page: 1587 issue: 5 year: 2016 ident: ref76 article-title: Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders publication-title: Ann. Biomed. Eng. doi: 10.1007/s10439-015-1444-y – volume: 205 start-page: 169 issue: 1 year: 2012 ident: ref85 article-title: A rule-based automatic sleep staging method publication-title: J. Neurosci. Methods doi: 10.1016/j.jneumeth.2011.12.022 – volume: 40 start-page: 494 issue: 1 year: 2020 ident: ref92 article-title: Automatic sleep stage classification using time–frequency images of CWT and transfer learning using convolution neural network publication-title: Biocybernetics Biomed. Eng. doi: 10.1016/j.bbe.2020.01.010 – start-page: 1296 volume-title: Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol. ident: ref31 article-title: Multilingual language processing from bytes – ident: ref14 doi: 10.5664/jcsm.2350 – ident: ref71 doi: 10.1161/01.CTR.101.23.e215 – volume: 20 issue: 17 year: 2020 ident: ref83 article-title: An automatic sleep stage classification algorithm using improved model based essence features publication-title: Sensors doi: 10.3390/s20174677 – volume: 38 issue: 3 year: 2014 ident: ref22 article-title: A comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms publication-title: J. Med. Syst. doi: 10.1007/s10916-014-0018-0 – volume: 114 year: 2021 ident: ref65 article-title: STQS: Interpretable multi-modal spatial-temporal-sequential model for automatic sleep scoring publication-title: Artif. Intell. Med. doi: 10.1016/j.artmed.2021.102038 – ident: ref8 doi: 10.1371/journal.pone.0144720 – volume: 74 start-page: 268 issue: 5/6 year: 2015 ident: ref18 article-title: Nonlinear dynamics measures for automated EEG-Based sleep stage detection publication-title: Eur. Neurol. doi: 10.1159/000441975 – start-page: 2921 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref62 article-title: Learning deep features for discriminative localization – volume: 6 start-page: 53 year: 2019 ident: ref9 article-title: Does working memory improvement benefit from sleep in older adults? publication-title: Neurobiol. Sleep Circadian Rhythms doi: 10.1016/j.nbscr.2019.01.001 – volume: 1678 year: 2020 ident: ref35 article-title: A computationally efficient single-channel EEG sleep stage scoring approach using simple structured CNN publication-title: J. Phys.: Conf. Ser. – volume: 24 start-page: 1159 issue: 11 year: 2016 ident: ref17 article-title: EEG sleep stages classification based on time domain features and structural graph similarity publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2016.2552539 – year: 2017 ident: ref4 article-title: Network dissection: Quantifying interpretability of deep visual representations doi: 10.1109/CVPR.2017.354 – ident: ref70 doi: 10.1109/CVPR.2018.00920 – year: 2005 ident: ref74 article-title: The DREAMS databases and assessment algorithm – ident: ref47 doi: 10.1111/jsr.12169 – volume: 17 start-page: 1835 issue: 6 year: 2020 ident: ref33 article-title: Deep learning for automated feature discovery and classification of sleep stages publication-title: IEEE/ACM Trans. Comput. Biol. Bioinf. doi: 10.1109/TCBB.2019.2912955 – volume: 61 year: 2020 ident: ref54 article-title: Intra- and inter-epoch temporal context network (IITNet) using sub-epoch features for automatic sleep scoring on raw single-channel EEG publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2020.102037 – volume: 48 start-page: 1412 issue: 12 year: 2001 ident: ref25 article-title: Computer-assisted sleep staging publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/10.966600 – volume: 55 year: 2020 ident: ref78 article-title: Diffuse to fuse EEG spectra–Intrinsic geometry of sleep dynamics for classification publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2019.101576 – volume: 65 year: 2021 ident: ref40 article-title: A new automated CNN deep learning approach for identification of ECG congestive heart failure and arrhythmia using constant-Q non-stationary Gabor transform publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2020.102326 – volume: 26 start-page: 324 issue: 2 year: 2018 ident: ref55 article-title: Mixed neural network approach for temporal sleep stage classification publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2017.2733220 – ident: ref48 doi: 10.1145/3233547.3233725 – volume: 18 start-page: 74 issue: 1 year: 2009 ident: ref13 article-title: Interrater reliability for sleep scoring according to the Rechtschaffen and Kales and the new AASM standard publication-title: J. Sleep Res. doi: 10.1111/j.1365-2869.2008.00700.x – start-page: 1885 volume-title: Proc. 34th Int. Conf. Mach. Learn. ident: ref5 article-title: Understanding black-box predictions via influence functions – volume: 7 start-page: 423 issue: 5 year: 2003 ident: ref96 article-title: Sleep spindles: An overview publication-title: Sleep Med. Rev. doi: 10.1053/smrv.2002.0252 – volume: 104 start-page: 277 year: 2018 ident: ref84 article-title: A new automatic sleep staging system based on statistical behavior of local extrema using single channel EEG signal publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2018.03.020 – volume: 16 start-page: 251 issue: 3 year: 2012 ident: ref24 article-title: Sleep scoring using artificial neural networks publication-title: Sleep Med. Rev. doi: 10.1016/j.smrv.2011.06.003 – year: 2016 ident: ref88 article-title: Automatic sleep stage scoring with single-channel EEG using convolutional neural networks – volume: 42 start-page: 107 year: 2018 ident: ref56 article-title: A convolutional neural network for sleep stage scoring from raw single-channel EEG publication-title: Biomed. Signal Process. Control doi: 10.1016/j.bspc.2017.12.001 – ident: ref73 doi: 10.1007/978-3-030-28954-6_9 – volume: 66 start-page: 1285 issue: 5 year: 2019 ident: ref37 article-title: Joint classification and prediction CNN framework for automatic sleep stage classification publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2018.2872652 – volume: 40 issue: 10 year: 2017 ident: ref53 article-title: Large-scale automated sleep staging publication-title: Sleep doi: 10.1093/sleep/zsx139 – volume: 49 start-page: 230 issue: 3 year: 2010 ident: ref15 article-title: Classification of sleep stages using multi-wavelet time frequency entropy and LDA publication-title: Methods Inf. Med. doi: 10.3414/ME09-01-0054 – volume: 24 start-page: 57 issue: 1 year: 2016 ident: ref26 article-title: Quaternion singular spectrum analysis of electroencephalogram with application in sleep analysis publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2015.2465177 – ident: ref67 doi: 10.1109/tnsre.2023.3243589 – volume: 183 year: 2020 ident: ref36 article-title: Orthogonal convolutional neural networks for automatic sleep stage classification based on single-channel EEG publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2019.105089 – year: 2016 ident: ref32 article-title: Exploring the limits of language modeling – year: 2002 ident: ref46 article-title: CGCNN: Complex Gabor convolutional neural network on raw speech – volume: 9 issue: 1 year: 2018 ident: ref38 article-title: Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy publication-title: Nature Commun. doi: 10.1038/s41467-018-07229-3 – volume: 71 year: 2022 ident: ref82 article-title: A novel sleep stage contextual refinement algorithm leveraging conditional random fields publication-title: IEEE Trans. Instrum. Meas. – volume-title: The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications year: 2007 ident: ref10 – start-page: 1452 volume-title: Proc. IEEE 40th Annu. Int. Conf. Eng. Med. Biol. Soc. ident: ref52 article-title: Automatic sleep stage classification using single-channel EEG: Learning sequential features with attention-based recurrent neural networks – start-page: 4579 volume-title: Proc. 36th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. ident: ref21 article-title: Sleep stage classification with cross frequency coupling – volume: 44 start-page: 5903 issue: 9 year: 2022 ident: ref49 article-title: XSleepNet: Multi-view sequential model for automatic sleep staging publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 137 start-page: 247 year: 2016 ident: ref28 article-title: Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating publication-title: Comput. Methods Programs Biomed. doi: 10.1016/j.cmpb.2016.09.008 – volume: 207 start-page: 165 year: 2016 ident: ref23 article-title: An efficient sleep scoring system based on EEG signal using complex-valued machine learning algorithms publication-title: Neurocomputing doi: 10.1016/j.neucom.2016.04.049 – volume: 36 start-page: 256 issue: 1 year: 2016 ident: ref20 article-title: Computer-aided obstructive sleep apnea screening from single-lead electrocardiogram using statistical and spectral features and bootstrap aggregating publication-title: Biocybernetics Biomed. Eng. doi: 10.1016/j.bbe.2015.11.003 – volume-title: A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects year: 1968 ident: ref11 – year: 2013 ident: ref60 article-title: Deep inside convolutional networks: Visualising image classification models and saliency maps – volume: 29 start-page: 6707 year: 2020 ident: ref6 article-title: Interpret neural networks by extracting critical subnetworks publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2020.2993098 – start-page: 3108 volume-title: Proc. 40th Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. ident: ref58 article-title: Compressed sensing of EEG with gabor dictionary: Effect of time and frequency resolution – volume: 5 year: 2014 ident: ref98 article-title: Decreased electrophysiological activity represents the conscious state of emptiness in meditation publication-title: Front. Psychol. doi: 10.3389/fpsyg.2014.00099 – start-page: 3640 volume-title: Proc. IEEE Conf. Comput. Vis. Pattern Recognit. ident: ref29 article-title: Attention to scale: Scale-aware semantic image segmentation – volume: 26 start-page: 758 issue: 4 year: 2018 ident: ref51 article-title: A deep learning architecture for temporal sleep stage classification using multivariate and multimodal time series publication-title: IEEE Trans. Neural Syst. Rehabil. Eng. doi: 10.1109/TNSRE.2018.2813138 – start-page: 905 volume-title: Proc. Interspeech ISCA: ISCA ident: ref42 article-title: Robust CNN-based speech recognition with Gabor filter kernels – volume: 49 start-page: 839 issue: 3 year: 2019 ident: ref34 article-title: Spatial–temporal recurrent neural network for emotion recognition publication-title: IEEE Trans. Cybern. doi: 10.1109/TCYB.2017.2788081 – start-page: 1876 volume-title: Proc. IEEE 36th Annu. Int. Conf. Eng. Med. Biol. Soc. ident: ref19 article-title: Comparison of feature and classifier algorithms for online automatic sleep staging based on a single EEG signal – start-page: 453 volume-title: Proc. IEEE 40th Annu. Int. Conf. Eng. Med. Biol. Soc. ident: ref57 article-title: DNN filter bank improves 1-Max pooling CNN for single-channel EEG automatic sleep stage classification – ident: ref39 doi: 10.1093/sleep/32.2.139 – ident: ref45 doi: 10.3389/fnins.2021.614182 – volume: 63 start-page: 241 year: 2016 ident: ref16 article-title: Complex networks approach for EEG signal sleep stages classification publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2016.07.004 – volume: 41 issue: 6 year: 2020 ident: ref91 article-title: Personalized automatic sleep staging with single-night data: A pilot study with Kullback–Leibler divergence regularization publication-title: Physiol. Meas. doi: 10.1088/1361-6579/ab921e
SSID	ssj0014503
Score	2.4875913
Snippet	In recent years, deep learning has shown potential and efficiency in a wide area including computer vision, image and signal processing. Yet, translational...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	5044
SubjectTerms	Adult Algorithms Artificial neural networks Black-box problem Brain modeling Computer vision convolutional neural network Deep Learning electroencephalogram Electroencephalography Feature extraction Female Humans interpretable system Kernel Machine learning Male Neural Networks, Computer Polysomnography Signal processing Signal Processing, Computer-Assisted Sleep sleep stages Sleep Stages - physiology Time-frequency analysis Young Adult
Title	A Multi-Level Interpretable Sleep Stage Scoring System by Infusing Experts' Knowledge Into a Deep Network Architecture
URI	https://ieeexplore.ieee.org/document/10436701 https://www.ncbi.nlm.nih.gov/pubmed/38358869 https://www.proquest.com/docview/3064702227 https://www.proquest.com/docview/2928242812
Volume	46
WOSCitedRecordID	wos001240147800029&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: PRVIEE databaseName: IEL customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dS9xAEB9aKaIP2lo_ola2IPShRJPNJpt9PPygpfYQ1HJvYT8mh3DciXcn-N87u0nOe7Hg20JmNwszw85v9zczAMeyFspJLuJcp3ksKMKNjeY6lrkpnEuUTUPZxX9Xst8vBwN13Sarh1wYRAzkMzzxw_CW7yZ27q_KyMOFrzdGYOejlEWTrLV4MhB5aINMIQy5OOGILkMmUae3172_vwkLcnGSZYUvQb4GqwTN8rL0ROelAyl0WHk72AyHzuXmO7f7GTba6JL1GnP4Ah9wvAWbXecG1jryFqwvlSH8Ck89FvJw4yvPIGKvPEQzQnYzQnxgFJMOaWwDXY81Zc6ZeSbZ2jPnhyyUTJ5Nf7A_3SWdX2fCNDv38_sN25z1lt4ttuHu8uL27Ffc9mOILYVps1jzwhpBpiedylRqeZZnhUhLo2ubpUWBiuzBlSYRVhGMI-yIudC1TJxVzjjMdmBlPBnjHjAKlgWKmivte6CRtEyQFzVmuROlLU0EaaeUyrbFyn3PjFEVQEuiqqDTyuu0anUawc_FnIemVMd_pbe9xpYkG2VFcNgpv2rdeVp5mCZD2nAE3xefyRH964oe42Q-rbgi9EpgLuUR7DZGs1i8s7X9N356AGt-bw0N-BBWZo9z_Aaf7NPsfvp4RNY-KI-Ctb8Ac3T4Ig
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3dSxwxEB-KitUHv2p1ra0pFPpQVnez2Y88HrWieB5Cr8W3kI9ZKRx34t0J_vdOsrvXe7HQt8BOsoGZIfNLZn4D8KWshXQlF3Gu0zwWFOHGRnMdl7kpnEukTQPt4u9-ORhUd3fyti1WD7UwiBiSz_DUD8NbvpvYub8qIw8Xnm-MwM6qb53VlmstHg1EHhohUxBDTk5IoquRSeTZ8LZ3c0VokIvTLCs8CfkGrBM4y6vKpzovHUmhx8rr4WY4di62_3PDO7DVxpes1xjELrzB8R5sd70bWOvKe7C5RET4Dp56LFTixn2fQ8T-ZiKaEbKfI8QHRlHpPY1tSNhjDdE5M88kW_vc-XsWSJNn06_surum8-tMmGbnfv6gyTdnvaWXi334dfFj-P0ybjsyxJYCtVmseWGNIOMrncxkanmWZ4VIK6Nrm6VFgZIswlUmEVYSkCP0iLnQdZk4K51xmL2HlfFkjIfAKFwWKGoutVclSZcJ8qLGLHeispWJIO2UomxLV-67ZoxUgC2JVEGnyutUtTqN4NtizkND1vFP6X2vsSXJRlkRHHfKV61DT5UHamUoHI7g8-IzuaJ_X9FjnMynikvCrwTnUh7BQWM0i8U7Wzt65acn8PZyeNNX_avB9QfY8PtskoKPYWX2OMePsGafZn-mj5-Czb8Aq2f6gw
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=A+Multi-Level+Interpretable+Sleep+Stage+Scoring+System+by+Infusing+Experts%E2%80%99+Knowledge+Into+a+Deep+Network+Architecture&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Niknazar%2C+Hamid&rft.au=Mednick%2C+Sara+C.&rft.date=2024-07-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=46&rft.issue=7&rft.spage=5044&rft.epage=5061&rft_id=info:doi/10.1109%2FTPAMI.2024.3366170&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2024_3366170
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon