Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings

There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier t...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Brain (London, England : 1878) Ročník 140; číslo 6; s. 1680
Hlavní autori:	Baldassano, Steven N, Brinkmann, Benjamin H, Ung, Hoameng, Blevins, Tyler, Conrad, Erin C, Leyde, Kent, Cook, Mark J, Khambhati, Ankit N, Wagenaar, Joost B, Worrell, Gregory A, Litt, Brian
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	England 01.06.2017
Predmet:	Adult Algorithms Animals Crowdsourcing - methods Crowdsourcing - standards Disease Models, Animal Electrocorticography - methods Electrocorticography - standards Equipment Design - methods Equipment Design - standards Humans Prostheses and Implants Reproducibility of Results Seizures - diagnosis epilepsy crowdsourcing experimental models seizure detection intracranial EEG
ISSN:	1460-2156, 1460-2156
On-line prístup:	Zistit podrobnosti o prístupe
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care.
AbstractList	There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care. There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care.There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential in responsive neurostimulation devices and in automatic parsing of continuous intracranial electroencephalography data. An important barrier to developing accurate, validated algorithms for seizure detection is limited access to high-quality, expertly annotated seizure data from prolonged recordings. To overcome this, we hosted a kaggle.com competition to crowdsource the development of seizure detection algorithms using intracranial electroencephalography from canines and humans with epilepsy. The top three performing algorithms from the contest were then validated on out-of-sample patient data including standard clinical data and continuous ambulatory human data obtained over several years using the implantable NeuroVista seizure advisory system. Two hundred teams of data scientists from all over the world participated in the kaggle.com competition. The top performing teams submitted highly accurate algorithms with consistent performance in the out-of-sample validation study. The performance of these seizure detection algorithms, achieved using freely available code and data, sets a new reproducible benchmark for personalized seizure detection. We have also shared a 'plug and play' pipeline to allow other researchers to easily use these algorithms on their own datasets. The success of this competition demonstrates how sharing code and high quality data results in the creation of powerful translational tools with significant potential to impact patient care.
Author	Brinkmann, Benjamin H Ung, Hoameng Blevins, Tyler Conrad, Erin C Cook, Mark J Baldassano, Steven N Khambhati, Ankit N Litt, Brian Leyde, Kent Wagenaar, Joost B Worrell, Gregory A
Author_xml	– sequence: 1 givenname: Steven N surname: Baldassano fullname: Baldassano, Steven N organization: Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA 19104, USA – sequence: 2 givenname: Benjamin H surname: Brinkmann fullname: Brinkmann, Benjamin H organization: Department of Neurology, Mayo Clinic and Mayo Foundation, Rochester, MN 55905, USA – sequence: 3 givenname: Hoameng surname: Ung fullname: Ung, Hoameng organization: Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA 19104, USA – sequence: 4 givenname: Tyler surname: Blevins fullname: Blevins, Tyler organization: Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA 19104, USA – sequence: 5 givenname: Erin C surname: Conrad fullname: Conrad, Erin C organization: Department of Neurology, University of Pennsylvania, PA, USA – sequence: 6 givenname: Kent surname: Leyde fullname: Leyde, Kent organization: NeuroVista, Seattle, WA, USA – sequence: 7 givenname: Mark J surname: Cook fullname: Cook, Mark J organization: Department of Medicine, University of Melbourne, Melbourne, VIC, Australia – sequence: 8 givenname: Ankit N surname: Khambhati fullname: Khambhati, Ankit N organization: Center for Neuroengineering and Therapeutics, University of Pennsylvania, Philadelphia, PA 19104, USA – sequence: 9 givenname: Joost B surname: Wagenaar fullname: Wagenaar, Joost B organization: Department of Neurology, University of Pennsylvania, PA, USA – sequence: 10 givenname: Gregory A surname: Worrell fullname: Worrell, Gregory A organization: Department of Neurology, Mayo Clinic and Mayo Foundation, Rochester, MN 55905, USA – sequence: 11 givenname: Brian surname: Litt fullname: Litt, Brian organization: Department of Neurology, University of Pennsylvania, PA, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/28459961$$D View this record in MEDLINE/PubMed
BookMark	eNpNkN1LwzAUxYNM3Ie--Sx59KUuadPY-CbDLxj4os8lzb3dMtpkJu2m_vV2OEE4cA-HH4fLmZKR8w4JueTshjOVzaugrZvr_SdTxQmZcCFZkvJcjv75MZnGuGGMiyyVZ2ScFiJXSvIJ2SyC30P0fTDWrWhE-90HpIAdms56d0d1s_LBdut2CHfY-G2LrqPaAd3pxoI-UHTQum-1o7bdNtp1CAfaGqQBjQ8wdMdzclrrJuLF8c7I--PD2-I5Wb4-vSzul4kROesSQCkQaqEFAxC8qkRes6zmRZppperBG2RZIQGk4eYWOKtzCarIKxQ85XU6I9e_vdvgP3qMXdnaaLAZ_kLfx5IXSuRcSaEG9OqI9lWLUG6DbXX4Kv_2SX8AxnRs3g
CitedBy_id	crossref_primary_10_1088_1741_2552_aced21 crossref_primary_10_1111_epi_16555 crossref_primary_10_3389_fneur_2021_704170 crossref_primary_10_1515_bmt_2017_0233 crossref_primary_10_1016_j_artmed_2023_102754 crossref_primary_10_1016_j_nicl_2019_101684 crossref_primary_10_1088_1741_2552_ab094a crossref_primary_10_1016_j_neuropharm_2019_107751 crossref_primary_10_1038_s41440_019_0267_x crossref_primary_10_1088_1741_2552_abef8a crossref_primary_10_1111_epi_17044 crossref_primary_10_3389_fneur_2021_675728 crossref_primary_10_1111_epi_17047 crossref_primary_10_1109_JBHI_2020_3022211 crossref_primary_10_1016_j_neurol_2019_12_012 crossref_primary_10_1109_JTEHM_2018_2869398 crossref_primary_10_1088_1741_2552_aae5ab crossref_primary_10_1109_JETCAS_2018_2842761 crossref_primary_10_1186_s12911_018_0693_8 crossref_primary_10_1097_WNP_0000000000000819 crossref_primary_10_3390_s18061720 crossref_primary_10_3389_fvets_2022_1014269 crossref_primary_10_1093_brain_awad007 crossref_primary_10_1109_TBCAS_2024_3456825 crossref_primary_10_2196_42723 crossref_primary_10_1016_j_procs_2020_04_010 crossref_primary_10_1016_j_clinph_2020_12_009 crossref_primary_10_1016_j_ebiom_2021_103275 crossref_primary_10_1016_j_yebeh_2019_106456 crossref_primary_10_1016_j_yebeh_2019_106457 crossref_primary_10_1111_epi_17833 crossref_primary_10_3389_fnsys_2018_00043 crossref_primary_10_1016_j_neuroscience_2021_11_017 crossref_primary_10_1097_WCO_0000000000000658 crossref_primary_10_1111_epi_16541 crossref_primary_10_1002_epi4_12704 crossref_primary_10_1016_j_ebr_2021_100467 crossref_primary_10_1111_epi_16628 crossref_primary_10_1088_1741_2552_add76f crossref_primary_10_4049_jimmunol_1900033 crossref_primary_10_1038_s41598_021_03555_7 crossref_primary_10_1088_1741_2552_addd49 crossref_primary_10_1186_s12911_020_01307_7 crossref_primary_10_3389_fneur_2021_690404 crossref_primary_10_1016_j_compbiomed_2020_103671 crossref_primary_10_3389_fneur_2018_00639 crossref_primary_10_3390_bios11070203 crossref_primary_10_5698_1535_7597_18_2_89 crossref_primary_10_5698_1535_7597_18_1_37 crossref_primary_10_1097_WCO_0000000000000533 crossref_primary_10_1088_1361_6579_aca6ca crossref_primary_10_1186_s40249_020_0622_9 crossref_primary_10_1038_s41591_018_0103_x crossref_primary_10_1088_1741_2552_ac23bf crossref_primary_10_1093_nsr_nwaf086 crossref_primary_10_1088_1741_2552_abc1b7 crossref_primary_10_1155_2020_7902072 crossref_primary_10_3389_fneur_2021_728484 crossref_primary_10_3389_fphys_2018_01767 crossref_primary_10_1038_s41582_024_00965_9 crossref_primary_10_1111_epi_13909 crossref_primary_10_1016_j_jneumeth_2021_109220 crossref_primary_10_1109_TBME_2019_2919137 crossref_primary_10_1111_epi_16818 crossref_primary_10_5698_1535_7597_18_4_236 crossref_primary_10_1088_1741_2552_aaf92e crossref_primary_10_1515_bmt_2018_0012 crossref_primary_10_1016_j_mri_2021_12_007 crossref_primary_10_1016_j_yebeh_2019_106556 crossref_primary_10_1111_epi_17415 crossref_primary_10_3389_fneur_2022_837893 crossref_primary_10_1016_j_compbiomed_2019_02_005 crossref_primary_10_1016_j_clinph_2024_09_017 crossref_primary_10_1109_TBME_2019_2921448 crossref_primary_10_1016_j_yebeh_2022_108806 crossref_primary_10_1097_CCE_0000000000000476 crossref_primary_10_1109_TBCAS_2023_3312300 crossref_primary_10_1016_j_seizure_2018_09_013 crossref_primary_10_1016_j_yebeh_2023_109518 crossref_primary_10_1016_S1474_4422_18_30038_3 crossref_primary_10_3389_fneur_2021_703797 crossref_primary_10_1016_j_neulet_2018_10_062 crossref_primary_10_1038_s44335_025_00025_5 crossref_primary_10_1088_1741_2552_ade402 crossref_primary_10_1016_j_compbiomed_2019_05_025 crossref_primary_10_1016_j_clinthera_2020_05_017 crossref_primary_10_1109_TMC_2018_2883451
ContentType	Journal Article
Copyright	The Author (2017). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
Copyright_xml	– notice: The Author (2017). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
DBID	CGR CUY CVF ECM EIF NPM 7X8
DOI	10.1093/brain/awx098
DatabaseName	Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic
DatabaseTitle	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	no_fulltext_linktorsrc
Discipline	Medicine
EISSN	1460-2156
ExternalDocumentID	28459961
Genre	Validation Studies Journal Article
GrantInformation_xml	– fundername: NINDS NIH HHS grantid: R01 NS092882 – fundername: NINDS NIH HHS grantid: UH2 NS095495
GroupedDBID	--- -E4 -~X .2P .I3 .XZ .ZR 0R~ 1TH 23N 2WC 4.4 482 48X 53G 5GY 5RE 5VS 5WA 5WD 6PF 70D AABZA AACZT AAIMJ AAJKP AAJQQ AAMDB AAMVS AAOGV AAPNW AAPQZ AAPXW AARHZ AAUAY AAUQX AAVAP AAVLN AAWTL ABDFA ABEJV ABEUO ABGNP ABIVO ABIXL ABJNI ABKDP ABLJU ABMNT ABNHQ ABNKS ABPTD ABQLI ABQNK ABVGC ABWST ABXVV ABZBJ ACGFS ACIWK ACPRK ACUFI ACUTJ ACUTO ACYHN ADBBV ADEYI ADEZT ADGKP ADGZP ADHKW ADHZD ADIPN ADJQC ADOCK ADQBN ADRIX ADRTK ADVEK ADYVW ADZXQ AEGPL AEJOX AEKSI AELWJ AEMDU AENEX AENZO AEPUE AETBJ AEWNT AFFZL AFGWE AFIYH AFOFC AFXAL AFXEN AGINJ AGKEF AGQXC AGSYK AGUTN AHMBA AHMMS AHXPO AIJHB AJEEA AKWXX ALMA_UNASSIGNED_HOLDINGS ALUQC APIBT APWMN ARIXL ATGXG AXUDD AYOIW BAWUL BAYMD BCRHZ BEYMZ BHONS BQDIO BR6 BSWAC BTRTY BVRKM C45 CDBKE CGR COF CS3 CUY CVF CZ4 DAKXR DIK DILTD DU5 D~K E3Z EBS ECM EE~ EIF EJD EMOBN ENERS F5P F9B FECEO FHSFR FLUFQ FOEOM FOTVD FQBLK GAUVT GJXCC GX1 H13 H5~ HAR HW0 HZ~ IOX J21 J5H JXSIZ KAQDR KBUDW KOP KQ8 KSI KSN L7B M-Z M49 MHKGH ML0 N9A NGC NLBLG NOMLY NOYVH NPM NU- NVLIB O9- OAUYM OAWHX OBOKY OCZFY ODMLO OHH OJQWA OJZSN OK1 OPAEJ OVD OWPYF P2P PAFKI PEELM PQQKQ Q1. Q5Y R44 RD5 RIG ROL ROX ROZ RUSNO RW1 RXO TCURE TEORI TJX TLC TR2 VVN W8F WH7 WOQ X7H YAYTL YKOAZ YSK YXANX ZKX ~91 7X8 ABPQP ABUFD ABXZS ADNBA AEMQT AFYAG AJBYB AJNCP ALXQX
ID	FETCH-LOGICAL-c450t-de64edf4a40dd41bb45f03f1823a99ff03ce0386dd6c1c7d10f56d985be4121f2
IEDL.DBID	7X8
ISICitedReferencesCount	145
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000402726600022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1460-2156
IngestDate	Sun Nov 09 13:51:50 EST 2025 Wed Feb 19 02:43:48 EST 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	6
Keywords	epilepsy crowdsourcing experimental models seizure detection intracranial EEG
Language	English
License	The Author (2017). Published by Oxford University Press on behalf of the Guarantors of Brain. All rights reserved. For Permissions, please email: journals.permissions@oup.com.
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c450t-de64edf4a40dd41bb45f03f1823a99ff03ce0386dd6c1c7d10f56d985be4121f2
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 ObjectType-Undefined-3
OpenAccessLink	https://academic.oup.com/brain/article-pdf/140/6/1680/25417270/awx098.pdf
PMID	28459961
PQID	1894519649
PQPubID	23479
ParticipantIDs	proquest_miscellaneous_1894519649 pubmed_primary_28459961
PublicationCentury	2000
PublicationDate	2017-06-01
PublicationDateYYYYMMDD	2017-06-01
PublicationDate_xml	– month: 06 year: 2017 text: 2017-06-01 day: 01
PublicationDecade	2010
PublicationPlace	England
PublicationPlace_xml	– name: England
PublicationTitle	Brain (London, England : 1878)
PublicationTitleAlternate	Brain
PublicationYear	2017
SSID	ssj0014326
Score	2.5773847
Snippet	There exist significant clinical and basic research needs for accurate, automated seizure detection algorithms. These algorithms have translational potential...
SourceID	proquest pubmed
SourceType	Aggregation Database Index Database
StartPage	1680
SubjectTerms	Adult Algorithms Animals Crowdsourcing - methods Crowdsourcing - standards Disease Models, Animal Electrocorticography - methods Electrocorticography - standards Equipment Design - methods Equipment Design - standards Humans Prostheses and Implants Reproducibility of Results Seizures - diagnosis
Title	Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings
URI	https://www.ncbi.nlm.nih.gov/pubmed/28459961 https://www.proquest.com/docview/1894519649
Volume	140
WOSCitedRecordID	wos000402726600022&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText
inHoldings	1
isFullTextHit
isPrint
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS8MwEA_qRHzx-2N-EcHXsKZN08YXkeHwZWMPCnsrSZNoZevm2qn413tpO_YkCEIpfUhLyV3uLr-73A-hG-e0REoNUdRKwnjAiAJdItyCuZQsElbKimwiGgzi0UgMG8CtaMoqlzaxMtR6mjqMvENj4TqhcCbuZu_EsUa57GpDobGOWgGEMm5hRqNVFoEFfnO6yCPg2nhT-A6b-I5yBAwd-fnlifj34LJyMr3d__7eHtppwkt8X-vDPloz-QHa6jcJ9EP01oVtt64Qe_BZuDDZ92JusDZlVZKV32I5foHvlq8TrFf1RFjmGoNOZjUDE4arIvfD2WQ2drLRbjTYHFyDPg5-P0LPvYen7iNp6BZIykKvJNpwZrRlknlaM6oUC0FgFjYggRTCwrPjFou51jylaaSpZ0OuRRwqw6hPrX-MNvJpbk4RDkLLOIxUHkSXUaSUZ2KIy3hgHEmRDtvoejmLCaizy1HI3EwXRbKaxzY6qUWRzOq-Gwl4UtdMhp794e1ztO07B1zhJReoZWExm0u0mX6UWTG_qvQE7oNh_wcbs8sf
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=Crowdsourcing+seizure+detection%3A+algorithm+development+and+validation+on+human+implanted+device+recordings&rft.jtitle=Brain+%28London%2C+England+%3A+1878%29&rft.au=Baldassano%2C+Steven+N&rft.au=Brinkmann%2C+Benjamin+H&rft.au=Ung%2C+Hoameng&rft.au=Blevins%2C+Tyler&rft.date=2017-06-01&rft.issn=1460-2156&rft.eissn=1460-2156&rft.volume=140&rft.issue=6&rft.spage=1680&rft_id=info:doi/10.1093%2Fbrain%2Fawx098&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1460-2156&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1460-2156&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1460-2156&client=summon