Detection of EEG burst-suppression in neurocritical care patients using an unsupervised machine learning algorithm

•A novel burst suppression detection algorithm that doesn’t require annotated data.•The algorithm adapts to each patient, is fast and provides confidence scores.•We report competitive performance compared to supervised deep neural networks. The burst suppression pattern in clinical electroencephalog...

Full description

Saved in:
Bibliographic Details
Published in:Clinical neurophysiology Vol. 132; no. 10; pp. 2485 - 2492
Main Authors: Narula, G., Haeberlin, M., Balsiger, J., Strässle, C., Imbach, L.L., Keller, E.
Format: Journal Article
Language:English
Published: Elsevier B.V 01.10.2021
Subjects:
ISSN:1388-2457, 1872-8952, 1872-8952
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •A novel burst suppression detection algorithm that doesn’t require annotated data.•The algorithm adapts to each patient, is fast and provides confidence scores.•We report competitive performance compared to supervised deep neural networks. The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection. METHODS: We describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage. RESULTS: We report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38). CONCLUSION: We present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection. SIGNIFICANCE: Our algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.
AbstractList •A novel burst suppression detection algorithm that doesn’t require annotated data.•The algorithm adapts to each patient, is fast and provides confidence scores.•We report competitive performance compared to supervised deep neural networks. The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection. METHODS: We describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage. RESULTS: We report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38). CONCLUSION: We present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection. SIGNIFICANCE: Our algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.
The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection.OBJECTIVEThe burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of various etiologies, as with hypoxia, drug related intoxication or deep anesthesia. The detection of bursts and the calculation of burst/suppression ratio are often used to monitor the level of anesthesia during treatment of status epilepticus. However, manual counting of bursts is a laborious process open to inter-rater variation and motivates a need for automatic detection.We describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage.METHODSWe describe a novel unsupervised learning algorithm that detects bursts in EEG and generates burst-per-minute estimates for the purpose of monitoring sedation level in an intensive care unit (ICU). We validated the algorithm on 29 hours of burst annotated EEG data from 29 patients suffering from status epilepticus and hemorrhage.We report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38).RESULTSWe report competitive results in comparison to neural networks learned via supervised learning. The mean absolute error (SD) in bursts per minute was 0.93 (1.38).We present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection.CONCLUSIONWe present a novel burst suppression detection algorithm that adapts to each patient individually, reports bursts-per-minute quickly, and does not require manual fine-tuning unlike previous approaches to burst-suppression pattern detection.Our algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.SIGNIFICANCEOur algorithm for automatic burst suppression quantification can greatly reduce manual oversight in depth of sedation monitoring.
Highlights•A novel burst suppression detection algorithm that doesn’t require annotated data. •The algorithm adapts to each patient, is fast and provides confidence scores. •We report competitive performance compared to supervised deep neural networks.
Author Strässle, C.
Narula, G.
Imbach, L.L.
Haeberlin, M.
Keller, E.
Balsiger, J.
Author_xml – sequence: 1
  givenname: G.
  surname: Narula
  fullname: Narula, G.
  email: gagan.narula@uzh.ch
  organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, University Hospital Zürich, Zürich, Switzerland
– sequence: 2
  givenname: M.
  surname: Haeberlin
  fullname: Haeberlin, M.
  organization: Department of Epileptology, Neurology Clinic, University Hospital Zürich, Zürich, Switzerland
– sequence: 3
  givenname: J.
  surname: Balsiger
  fullname: Balsiger, J.
  organization: Department of Epileptology, Neurology Clinic, University Hospital Zürich, Zürich, Switzerland
– sequence: 4
  givenname: C.
  surname: Strässle
  fullname: Strässle, C.
  organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, University Hospital Zürich, Zürich, Switzerland
– sequence: 5
  givenname: L.L.
  surname: Imbach
  fullname: Imbach, L.L.
  organization: Department of Epileptology, Neurology Clinic, University Hospital Zürich, Zürich, Switzerland
– sequence: 6
  givenname: E.
  surname: Keller
  fullname: Keller, E.
  organization: Neurocritical Care Unit, Department of Neurosurgery and Institute of Intensive Care Medicine, University Hospital Zürich, Zürich, Switzerland
BookMark eNqVkk1rFTEUhgepYFv9By6ydDNjPmbyISJIvbZCwYXdh0zmTG-uc5MxyRT67028rgQpXSWQ93kDzzkXzZkPHprmLcEdwYS_P3R2cX7ddxRT0mHRYSJfNOdECtpKNdCzcmdStrQfxKvmIqUDxljgnp438QtksNkFj8KMdrtrNG4x5TZt6xohpfrgPPKwxWCjy86aBVkTAa0mO_A5oS05f4-MR5svFMQHl2BCR2P3zgNawET_J7Dch1KwP75uXs5mSfDm73nZ3H3d3V3dtLffr79dfb5tba9YbvuJ0xnLUUkCarJilsqYmc1kpIYxy6UYBwWG0t4oOoNhRqgRJgGUcd737LJ5d6pdY_i1Qcr66JKFZTEewpY0HTjHlKuhRvtT1MaQUoRZr9EdTXzUBOtqWB_0ybCuhjUWuhgu2Id_MOuyqS5zNG55Cv50gqEoeHAQdbLFp4XJxTIQPQX33IIaqvP5CY-QDmGLvujVRCeqsf5RN6AuACUYc8lwKfj4_4Kn__8NbzjIGA
CitedBy_id crossref_primary_10_3389_fmed_2023_1174429
crossref_primary_10_1213_ANE_0000000000006119
crossref_primary_10_1007_s12028_024_02140_w
crossref_primary_10_1016_j_seizure_2025_06_019
crossref_primary_10_1093_jamia_ocac064
crossref_primary_10_1016_j_neurot_2025_e00524
crossref_primary_10_1097_MCC_0000000000000940
crossref_primary_10_1109_ACCESS_2025_3581598
crossref_primary_10_1227_neu_0000000000002017
crossref_primary_10_1097_JHM_D_23_00252
crossref_primary_10_1213_ANE_0000000000007141
Cites_doi 10.1111/j.1651-2227.2009.01653.x
10.1016/S0013-4694(98)00009-1
10.1097/CCM.0b013e31825b94f0
10.1016/j.clinph.2016.02.001
10.1007/978-3-662-05296-9_31
10.1016/0303-8467(91)90015-H
10.1038/s41592-019-0686-2
10.1088/1741-2560/10/5/056017
10.1007/BF02551274
10.1109/10.661266
10.1016/0013-4694(85)91085-5
10.1016/j.jneumeth.2013.07.003
10.1016/j.yebeh.2015.06.012
10.1152/ajplegacy.1936.116.3.577
10.1023/A:1009990629797
10.1007/BF02332690
10.1152/jn.1949.12.2.137
10.1177/155005949903000305
10.1023/A:1016393904439
10.1109/TIT.1982.1056489
ContentType Journal Article
Copyright 2021 International Federation of Clinical Neurophysiology
Copyright © 2021 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.
Copyright_xml – notice: 2021 International Federation of Clinical Neurophysiology
– notice: Copyright © 2021 International Federation of Clinical Neurophysiology. Published by Elsevier B.V. All rights reserved.
DBID 6I.
AAFTH
AAYXX
CITATION
7X8
DOI 10.1016/j.clinph.2021.07.018
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
MEDLINE - Academic
DatabaseTitle CrossRef
MEDLINE - Academic
DatabaseTitleList

MEDLINE - Academic

Database_xml – sequence: 1
  dbid: 7X8
  name: MEDLINE - Academic
  url: https://search.proquest.com/medline
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1872-8952
EndPage 2492
ExternalDocumentID 10_1016_j_clinph_2021_07_018
S1388245721006830
1_s2_0_S1388245721006830
GroupedDBID ---
--K
--M
-~X
.1-
.55
.FO
.GJ
.~1
0R~
1B1
1P~
1RT
1~.
1~5
29B
4.4
457
4G.
53G
5GY
5RE
5VS
6J9
7-5
71M
8P~
AABNK
AAEDT
AAEDW
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAXKI
AAXLA
AAXUO
AAYWO
ABBQC
ABCQJ
ABFNM
ABFRF
ABIVO
ABJNI
ABLJU
ABMAC
ABMZM
ABTEW
ABWVN
ABXDB
ACDAQ
ACGFO
ACIEU
ACIUM
ACLOT
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
ADVLN
AEBSH
AEFWE
AEIPS
AEKER
AENEX
AEUPX
AEVXI
AFJKZ
AFPUW
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGWIK
AGYEJ
AI.
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
APXCP
ASPBG
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
BNPGV
CS3
DU5
EBS
EFJIC
EFKBS
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
HVGLF
HX~
HZ~
IHE
J1W
K-O
KOM
L7B
M41
MO0
MOBAO
MVM
N9A
O-L
O9-
OAUVE
OHT
OP~
OZT
P-8
P-9
P2P
PC.
Q38
R2-
ROL
RPZ
SCC
SDF
SDG
SDP
SEL
SES
SEW
SPCBC
SSH
SSN
SSZ
T5K
UAP
UNMZH
UV1
VH1
X7M
XOL
XPP
Z5R
ZGI
~G-
~HD
AACTN
AFCTW
AFKWA
AJOXV
AMFUW
PKN
RIG
VQA
6I.
AADPK
AAFTH
AAIAV
ABLVK
ABYKQ
AFMIJ
AHPSJ
AJBFU
LCYCR
ZA5
9DU
AAYXX
CITATION
7X8
ID FETCH-LOGICAL-c493t-4d62f08b981e9dc7f89aaf3f1b2a33c687b59ea224a92fea3a79bed7e2366443
ISICitedReferencesCount 10
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000704914800020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1388-2457
1872-8952
IngestDate Sun Sep 28 00:47:55 EDT 2025
Tue Nov 18 22:23:36 EST 2025
Sat Nov 29 07:02:51 EST 2025
Fri Feb 23 02:43:37 EST 2024
Tue Feb 25 20:10:14 EST 2025
Tue Oct 14 19:38:53 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 10
Keywords Burst suppression
Unsupervised
Neurocritical care
EEG
Machine learning
machine learning
unsupervised
neurocritical care
Language English
License This is an open access article under the CC BY license.
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c493t-4d62f08b981e9dc7f89aaf3f1b2a33c687b59ea224a92fea3a79bed7e2366443
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
OpenAccessLink https://dx.doi.org/10.1016/j.clinph.2021.07.018
PQID 2566026954
PQPubID 23479
PageCount 8
ParticipantIDs proquest_miscellaneous_2566026954
crossref_primary_10_1016_j_clinph_2021_07_018
crossref_citationtrail_10_1016_j_clinph_2021_07_018
elsevier_sciencedirect_doi_10_1016_j_clinph_2021_07_018
elsevier_clinicalkeyesjournals_1_s2_0_S1388245721006830
elsevier_clinicalkey_doi_10_1016_j_clinph_2021_07_018
PublicationCentury 2000
PublicationDate 2021-10-01
PublicationDateYYYYMMDD 2021-10-01
PublicationDate_xml – month: 10
  year: 2021
  text: 2021-10-01
  day: 01
PublicationDecade 2020
PublicationTitle Clinical neurophysiology
PublicationYear 2021
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Hallberg, Grossmann, Bartocci, Blennow (b0050) 2010; 99
Pedregosa, Varoquaux, Gramfort, Michel, Thirion, Grisel (b0090) 2011; 12
Chemali, Ching, Purdon, Solt, Brown (b0020) 2013; 10
Weissenborn, Wilkens, Hausmann, Degen (b0115) 1991; 93
Agarwal, Gotman, Flanagan, Rosenblatt (b0005) 1998; 107
Derbyshire, Rempel, Forbes, Lambert (b0035) 1936; 116
Särkelä, Mustola, Seppänen, Koskinen, Lepola, Suominen (b0095) 2002; 17
Pagni, Courjon (b0085) 1964; 13
Shi, Malik (b0100) 2000; 22
Ba JL, Kiros JR, Hinton GE. Layer Normalization. ArXiv160706450 Cs Stat 2016.
Cloostermans, van Meulen, Eertman, Hom, van Putten (b0025) 2012; 40
Fürbass, Herta, Koren, Westover, Hartmann, Gruber, Baumgartner, Kluge (b0045) 2016; 127
Lloyd (b0070) 1982; 28
Swank, Watson (b0105) 1949; 12
Amzica (b0010) 2015; 49
Lipping, Jäntti, Yli-Hankala, Hartikainen (b0065) 1995; 12
Niedermeyer, Sherman, Geocadin, Hansen, Hanley (b0080) 1999; 30
Westover, Shafi, Ching, Chemali, Purdon, Cash, Brown (b0120) 2013; 219
Virtanen, Gommers, Oliphant, Haberland, Reddy, Cournapeau (b0110) 2020; 17
Leistritz, Jäger, Schelenz, Witte, Putsche, Specht (b0060) 1999; 15
Zaret (b0130) 1985; 61
Young, Wang, Connolly (b0125) 2004; 21
Förstner W, Moonen B. A metric for covariance matrices. In: Grafarend EW, Krumm FW, Schwarze VS (editors). Geod.- Chall. 3rd Millenn. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003, p. 299–309. https://doi.org/10.1007/978-3-662-05296-9_31.
Mukhopadhyay, Ray (b0075) 1998; 45
Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Int. Conf. Mach. Learn., PMLR; 2015, p. 448–56.
Cybenko (b0030) 1989; 2
Mukhopadhyay (10.1016/j.clinph.2021.07.018_b0075) 1998; 45
Young (10.1016/j.clinph.2021.07.018_b0125) 2004; 21
Weissenborn (10.1016/j.clinph.2021.07.018_b0115) 1991; 93
Fürbass (10.1016/j.clinph.2021.07.018_b0045) 2016; 127
Agarwal (10.1016/j.clinph.2021.07.018_b0005) 1998; 107
10.1016/j.clinph.2021.07.018_b0015
Lipping (10.1016/j.clinph.2021.07.018_b0065) 1995; 12
Derbyshire (10.1016/j.clinph.2021.07.018_b0035) 1936; 116
10.1016/j.clinph.2021.07.018_b0040
Westover (10.1016/j.clinph.2021.07.018_b0120) 2013; 219
Hallberg (10.1016/j.clinph.2021.07.018_b0050) 2010; 99
Chemali (10.1016/j.clinph.2021.07.018_b0020) 2013; 10
Leistritz (10.1016/j.clinph.2021.07.018_b0060) 1999; 15
Lloyd (10.1016/j.clinph.2021.07.018_b0070) 1982; 28
Zaret (10.1016/j.clinph.2021.07.018_b0130) 1985; 61
Amzica (10.1016/j.clinph.2021.07.018_b0010) 2015; 49
Niedermeyer (10.1016/j.clinph.2021.07.018_b0080) 1999; 30
Cybenko (10.1016/j.clinph.2021.07.018_b0030) 1989; 2
Pagni (10.1016/j.clinph.2021.07.018_b0085) 1964; 13
10.1016/j.clinph.2021.07.018_b0055
Virtanen (10.1016/j.clinph.2021.07.018_b0110) 2020; 17
Swank (10.1016/j.clinph.2021.07.018_b0105) 1949; 12
Särkelä (10.1016/j.clinph.2021.07.018_b0095) 2002; 17
Shi (10.1016/j.clinph.2021.07.018_b0100) 2000; 22
Pedregosa (10.1016/j.clinph.2021.07.018_b0090) 2011; 12
Cloostermans (10.1016/j.clinph.2021.07.018_b0025) 2012; 40
References_xml – volume: 17
  start-page: 261
  year: 2020
  end-page: 272
  ident: b0110
  article-title: SciPy 1.0: fundamental algorithms for scientific computing in Python
  publication-title: Nat Methods
– volume: 40
  start-page: 2867
  year: 2012
  end-page: 2875
  ident: b0025
  article-title: Continuous electroencephalography monitoring for early prediction of neurological outcome in postanoxic patients after cardiac arrest: A prospective cohort study
  publication-title: Crit Care Med
– volume: 17
  start-page: 125
  year: 2002
  end-page: 134
  ident: b0095
  article-title: Automatic analysis and monitoring of burst suppression in Anesthesia
  publication-title: J Clin Monit Comput
– reference: Förstner W, Moonen B. A metric for covariance matrices. In: Grafarend EW, Krumm FW, Schwarze VS (editors). Geod.- Chall. 3rd Millenn. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003, p. 299–309. https://doi.org/10.1007/978-3-662-05296-9_31.
– volume: 127
  start-page: 2038
  year: 2016
  end-page: 2046
  ident: b0045
  article-title: Monitoring burst suppression in critically ill patients: Multi-centric evaluation of a novel method
  publication-title: Clin Neurophysiol
– volume: 22
  start-page: 18
  year: 2000
  ident: b0100
  article-title: Normalized Cuts and Image Segmentation
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 30
  start-page: 99
  year: 1999
  end-page: 105
  ident: b0080
  article-title: The Burst-Suppression Electroencephalogram
  publication-title: Clin Electroencephalogr
– volume: 13
  start-page: 35
  year: 1964
  end-page: 49
  ident: b0085
  article-title: Electroencephalographic modifications induced by moderate and deep hypothermia in man
  publication-title: Acta Neurochir
– volume: 219
  start-page: 131
  year: 2013
  end-page: 141
  ident: b0120
  article-title: Real-time segmentation of burst suppression patterns in critical care EEG monitoring
  publication-title: J Neurosci Methods
– volume: 116
  start-page: 577
  year: 1936
  end-page: 596
  ident: b0035
  article-title: The effects of anesthetics on action potentials in the cerebral cortex of the cat
  publication-title: Am J Physiol
– volume: 45
  start-page: 180
  year: 1998
  end-page: 187
  ident: b0075
  article-title: A new interpretation of nonlinear energy operator and its efficacy in spike detection
  publication-title: IEEE Trans Biomed Eng
– reference: Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. Int. Conf. Mach. Learn., PMLR; 2015, p. 448–56.
– volume: 93
  start-page: 77
  year: 1991
  end-page: 80
  ident: b0115
  article-title: Burst suppression EEG with baclofen overdose
  publication-title: Clin Neurol Neurosurg
– volume: 28
  start-page: 129
  year: 1982
  end-page: 137
  ident: b0070
  article-title: Least squares quantization in PCM
  publication-title: IEEE Trans Inf Theory
– volume: 10
  year: 2013
  ident: b0020
  article-title: Burst suppression probability algorithms: state-space methods for tracking EEG burst suppression
  publication-title: J Neural Eng
– volume: 12
  start-page: 2825
  year: 2011
  end-page: 2830
  ident: b0090
  article-title: Scikit-learn: Machine Learning in Python
  publication-title: J Mach Learn Res
– volume: 12
  start-page: 161
  year: 1995
  end-page: 167
  ident: b0065
  article-title: Adaptive segmentation of burst-suppression pattern in isoflurane and enflurane anesthesia
  publication-title: Int J Clin Monit Comput
– volume: 21
  start-page: 379
  year: 2004
  end-page: 390
  ident: b0125
  article-title: Prognostic determination in anoxic-ischemic and traumatic encephalopathies
  publication-title: J Clin Neurophysiol
– volume: 2
  start-page: 303
  year: 1989
  end-page: 314
  ident: b0030
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Math Control Signals Syst
– volume: 61
  start-page: 199
  year: 1985
  end-page: 209
  ident: b0130
  article-title: Prognostic and neurophysiological implications of concurrent burst suppression and alpha patterns in the EEG of post-anoxic coma
  publication-title: Electroencephalogr Clin Neurophysiol
– volume: 49
  start-page: 234
  year: 2015
  end-page: 237
  ident: b0010
  article-title: What does burst suppression really mean?
  publication-title: Epilepsy Behav
– volume: 107
  start-page: 44
  year: 1998
  end-page: 58
  ident: b0005
  article-title: Automatic EEG analysis during long-term monitoring in the ICU
  publication-title: Electroencephalogr Clin Neurophysiol
– volume: 12
  start-page: 137
  year: 1949
  end-page: 160
  ident: b0105
  article-title: Effects of barbiturates and ether on spontaneous electrical activity of dog brain
  publication-title: J Neurophysiol
– volume: 99
  start-page: 531
  year: 2010
  end-page: 536
  ident: b0050
  article-title: The prognostic value of early aEEG in asphyxiated infants undergoing systemic hypothermia treatment
  publication-title: Acta Paediatr
– reference: Ba JL, Kiros JR, Hinton GE. Layer Normalization. ArXiv160706450 Cs Stat 2016.
– volume: 15
  start-page: 357
  year: 1999
  end-page: 367
  ident: b0060
  article-title: New approaches for the detection and analysis of electroencephalographic burst-suppression patterns in patients under sedation
  publication-title: J Clin Monit Comput
– volume: 99
  start-page: 531
  year: 2010
  ident: 10.1016/j.clinph.2021.07.018_b0050
  article-title: The prognostic value of early aEEG in asphyxiated infants undergoing systemic hypothermia treatment
  publication-title: Acta Paediatr
  doi: 10.1111/j.1651-2227.2009.01653.x
– volume: 107
  start-page: 44
  issue: 1
  year: 1998
  ident: 10.1016/j.clinph.2021.07.018_b0005
  article-title: Automatic EEG analysis during long-term monitoring in the ICU
  publication-title: Electroencephalogr Clin Neurophysiol
  doi: 10.1016/S0013-4694(98)00009-1
– ident: 10.1016/j.clinph.2021.07.018_b0015
– volume: 22
  start-page: 18
  year: 2000
  ident: 10.1016/j.clinph.2021.07.018_b0100
  article-title: Normalized Cuts and Image Segmentation
  publication-title: IEEE Trans Pattern Anal Mach Intell
– volume: 40
  start-page: 2867
  issue: 10
  year: 2012
  ident: 10.1016/j.clinph.2021.07.018_b0025
  article-title: Continuous electroencephalography monitoring for early prediction of neurological outcome in postanoxic patients after cardiac arrest: A prospective cohort study
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0b013e31825b94f0
– volume: 127
  start-page: 2038
  issue: 4
  year: 2016
  ident: 10.1016/j.clinph.2021.07.018_b0045
  article-title: Monitoring burst suppression in critically ill patients: Multi-centric evaluation of a novel method
  publication-title: Clin Neurophysiol
  doi: 10.1016/j.clinph.2016.02.001
– ident: 10.1016/j.clinph.2021.07.018_b0040
  doi: 10.1007/978-3-662-05296-9_31
– volume: 13
  start-page: 35
  year: 1964
  ident: 10.1016/j.clinph.2021.07.018_b0085
  article-title: Electroencephalographic modifications induced by moderate and deep hypothermia in man
  publication-title: Acta Neurochir
– volume: 93
  start-page: 77
  issue: 1
  year: 1991
  ident: 10.1016/j.clinph.2021.07.018_b0115
  article-title: Burst suppression EEG with baclofen overdose
  publication-title: Clin Neurol Neurosurg
  doi: 10.1016/0303-8467(91)90015-H
– volume: 17
  start-page: 261
  issue: 3
  year: 2020
  ident: 10.1016/j.clinph.2021.07.018_b0110
  article-title: SciPy 1.0: fundamental algorithms for scientific computing in Python
  publication-title: Nat Methods
  doi: 10.1038/s41592-019-0686-2
– volume: 10
  issue: 5
  year: 2013
  ident: 10.1016/j.clinph.2021.07.018_b0020
  article-title: Burst suppression probability algorithms: state-space methods for tracking EEG burst suppression
  publication-title: J Neural Eng
  doi: 10.1088/1741-2560/10/5/056017
– volume: 2
  start-page: 303
  issue: 4
  year: 1989
  ident: 10.1016/j.clinph.2021.07.018_b0030
  article-title: Approximation by superpositions of a sigmoidal function
  publication-title: Math Control Signals Syst
  doi: 10.1007/BF02551274
– ident: 10.1016/j.clinph.2021.07.018_b0055
– volume: 12
  start-page: 2825
  year: 2011
  ident: 10.1016/j.clinph.2021.07.018_b0090
  article-title: Scikit-learn: Machine Learning in Python
  publication-title: J Mach Learn Res
– volume: 45
  start-page: 180
  year: 1998
  ident: 10.1016/j.clinph.2021.07.018_b0075
  article-title: A new interpretation of nonlinear energy operator and its efficacy in spike detection
  publication-title: IEEE Trans Biomed Eng
  doi: 10.1109/10.661266
– volume: 61
  start-page: 199
  issue: 4
  year: 1985
  ident: 10.1016/j.clinph.2021.07.018_b0130
  article-title: Prognostic and neurophysiological implications of concurrent burst suppression and alpha patterns in the EEG of post-anoxic coma
  publication-title: Electroencephalogr Clin Neurophysiol
  doi: 10.1016/0013-4694(85)91085-5
– volume: 219
  start-page: 131
  issue: 1
  year: 2013
  ident: 10.1016/j.clinph.2021.07.018_b0120
  article-title: Real-time segmentation of burst suppression patterns in critical care EEG monitoring
  publication-title: J Neurosci Methods
  doi: 10.1016/j.jneumeth.2013.07.003
– volume: 49
  start-page: 234
  year: 2015
  ident: 10.1016/j.clinph.2021.07.018_b0010
  article-title: What does burst suppression really mean?
  publication-title: Epilepsy Behav
  doi: 10.1016/j.yebeh.2015.06.012
– volume: 116
  start-page: 577
  issue: 3
  year: 1936
  ident: 10.1016/j.clinph.2021.07.018_b0035
  article-title: The effects of anesthetics on action potentials in the cerebral cortex of the cat
  publication-title: Am J Physiol
  doi: 10.1152/ajplegacy.1936.116.3.577
– volume: 15
  start-page: 357
  year: 1999
  ident: 10.1016/j.clinph.2021.07.018_b0060
  article-title: New approaches for the detection and analysis of electroencephalographic burst-suppression patterns in patients under sedation
  publication-title: J Clin Monit Comput
  doi: 10.1023/A:1009990629797
– volume: 12
  start-page: 161
  issue: 3
  year: 1995
  ident: 10.1016/j.clinph.2021.07.018_b0065
  article-title: Adaptive segmentation of burst-suppression pattern in isoflurane and enflurane anesthesia
  publication-title: Int J Clin Monit Comput
  doi: 10.1007/BF02332690
– volume: 12
  start-page: 137
  issue: 2
  year: 1949
  ident: 10.1016/j.clinph.2021.07.018_b0105
  article-title: Effects of barbiturates and ether on spontaneous electrical activity of dog brain
  publication-title: J Neurophysiol
  doi: 10.1152/jn.1949.12.2.137
– volume: 30
  start-page: 99
  issue: 3
  year: 1999
  ident: 10.1016/j.clinph.2021.07.018_b0080
  article-title: The Burst-Suppression Electroencephalogram
  publication-title: Clin Electroencephalogr
  doi: 10.1177/155005949903000305
– volume: 17
  start-page: 125
  year: 2002
  ident: 10.1016/j.clinph.2021.07.018_b0095
  article-title: Automatic analysis and monitoring of burst suppression in Anesthesia
  publication-title: J Clin Monit Comput
  doi: 10.1023/A:1016393904439
– volume: 21
  start-page: 379
  year: 2004
  ident: 10.1016/j.clinph.2021.07.018_b0125
  article-title: Prognostic determination in anoxic-ischemic and traumatic encephalopathies
  publication-title: J Clin Neurophysiol
– volume: 28
  start-page: 129
  issue: 2
  year: 1982
  ident: 10.1016/j.clinph.2021.07.018_b0070
  article-title: Least squares quantization in PCM
  publication-title: IEEE Trans Inf Theory
  doi: 10.1109/TIT.1982.1056489
SSID ssj0007042
Score 2.4490335
Snippet •A novel burst suppression detection algorithm that doesn’t require annotated data.•The algorithm adapts to each patient, is fast and provides confidence...
Highlights•A novel burst suppression detection algorithm that doesn’t require annotated data. •The algorithm adapts to each patient, is fast and provides...
The burst suppression pattern in clinical electroencephalographic (EEG) recordings is an important diagnostic tool because of its association with comas of...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Enrichment Source
Index Database
Publisher
StartPage 2485
SubjectTerms Burst suppression
EEG
Machine learning
Neurocritical care
Neurology
Unsupervised
Title Detection of EEG burst-suppression in neurocritical care patients using an unsupervised machine learning algorithm
URI https://www.clinicalkey.com/#!/content/1-s2.0-S1388245721006830
https://www.clinicalkey.es/playcontent/1-s2.0-S1388245721006830
https://dx.doi.org/10.1016/j.clinph.2021.07.018
https://www.proquest.com/docview/2566026954
Volume 132
WOSCitedRecordID wos000704914800020&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-8952
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0007042
  issn: 1388-2457
  databaseCode: AIEXJ
  dateStart: 20180601
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLa6DiFeEFcxLpOREC9VpsRJ6vhxjG6ASkGiSH2znMQenbq0NMm0n8LP5dix05YOrTzwElWWnVQ-n48_H58LQm_yFPZEyWClsZR4AAq95jIKAtHLUupNwSRxHdLRKJlM2NdO55eLhbma0aJIrq_Z4r-KGtpA2Dp09h_E3b4UGuA3CB2eIHZ47iT497KSmeOBg8FZD6atrLyyXlifV-PbaPJYZq7OgfH_silWy15dNpGLvbqAUVqZlEBLL43bpXR1JqDD7HwOL_hxuU5wT1ykpfmAsZtsGO5HYlnPDGE9Wyk_EPHSFo5vDUHvYKKm5w2gVldXVXOzHwE9lisbr7VakKD1f3OKNqEaH0322iN5Q5vTzivzZ926wFplGzXVfrZ2gcYgcXGkg0sX-saJBCZDq9X0G0m3R1_46ffhkI8Hk_HbxU9P1yPT9_a2OMse2ic0ZkkX7R9_HEw-tbs89U1hpvY_u7BM4zu4_eG_0Z4_CIBhNeMH6L49juDjBkYPUUcWj9Ddz9bh4jFatmjCc4UBTXgLTXha4A00YY0m7NCEDZqwKPA6mrBFE3Zowi2anqDx6WB88sGzZTq8LGJh5UV5nyg_SVkSSJZnVCVMCBWqICUiDLN-QtOYSQFcUTCipAgFZanMQRGEfWDj4VPULeaFfIawEFlMfJGlSmZRTuAwo3Kgl8pXKlUqYAcodJPIM5vCXldSmXHnq3jBm6nneuq5TzlM_QHy2lGLJoXLLf1jJx_uwpNhQ-WArlvG0ZvGydIqh5IHvCTc59-CEM61UUxJoCO0Qn99pCW-DaHd4ZuvHYA47Av6sk8Ucl6XHI4yuroci6PnO_R5ge6tVulL1K2WtXyF7mRX1bRcHqI9OkkO7Qr4DTbs4Dw
linkProvider Elsevier
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=Detection+of+EEG+burst-suppression+in+neurocritical+care+patients+using+an+unsupervised+machine+learning+algorithm&rft.jtitle=Clinical+neurophysiology&rft.au=Narula%2C+G&rft.au=Haeberlin%2C+M&rft.au=Balsiger%2C+J&rft.au=Str%C3%A4ssle%2C+C&rft.date=2021-10-01&rft.issn=1872-8952&rft.eissn=1872-8952&rft.volume=132&rft.issue=10&rft.spage=2485&rft_id=info:doi/10.1016%2Fj.clinph.2021.07.018&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1388-2457&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1388-2457&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1388-2457&client=summon