Publicação

Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models

Ver documento

Detalhes bibliográficos
Resumo:Objective: One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. Methods: We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. Results: Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. Significance: This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.
Autores principais:Viana, Pedro
Outros Autores:Pal Attia, Tal; Nasseri, Mona; Duun‐Henriksen, Jonas; Biondi, Andrea; Winston, Joel S.; Martins, Isabel Pavão; Nurse, Ewan S.; Dümpelmann, Matthias; Schulze‐Bonhage, Andreas; Freestone, Dean R.; Kjaer, Troels W.; Richardson, Mark P.; Brinkmann, Benjamin H.
Assunto:deep learning Epilepsy Mobile health Seizure forecasting Seizure prediction Subcutaneous EEG
Ano:2022
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso restrito
Instituição associada:Universidade de Lisboa
Idioma:inglês
Origem:Repositório da Universidade de Lisboa
_version_ 1866810025102540800
author Viana, Pedro
author2 Pal Attia, Tal
Nasseri, Mona
Duun‐Henriksen, Jonas
Biondi, Andrea
Winston, Joel S.
Martins, Isabel Pavão
Nurse, Ewan S.
Dümpelmann, Matthias
Schulze‐Bonhage, Andreas
Freestone, Dean R.
Kjaer, Troels W.
Richardson, Mark P.
Brinkmann, Benjamin H.
author2_role author
author
author
author
author
author
author
author
author
author
author
author
author
author_facet Viana, Pedro
Pal Attia, Tal
Nasseri, Mona
Duun‐Henriksen, Jonas
Biondi, Andrea
Winston, Joel S.
Martins, Isabel Pavão
Nurse, Ewan S.
Dümpelmann, Matthias
Schulze‐Bonhage, Andreas
Freestone, Dean R.
Kjaer, Troels W.
Richardson, Mark P.
Brinkmann, Benjamin H.
author_role author
contributor_name_str_mv Repositório Científico de Acesso Aberto da ULisboa
country_str PT
creators_json_txt [{\"Person.name\":\"Viana, Pedro\",\"Person.identifier.orcid\":\"0000-0003-0861-8705\"},{\"Person.name\":\"Pal Attia, Tal\"},{\"Person.name\":\"Nasseri, Mona\"},{\"Person.name\":\"Duun‐Henriksen, Jonas\"},{\"Person.name\":\"Biondi, Andrea\"},{\"Person.name\":\"Winston, Joel S.\"},{\"Person.name\":\"Martins, Isabel Pavão\",\"Person.identifier.orcid\":\"0000-0002-9611-7400\"},{\"Person.name\":\"Nurse, Ewan S.\"},{\"Person.name\":\"Dümpelmann, Matthias\"},{\"Person.name\":\"Schulze‐Bonhage, Andreas\"},{\"Person.name\":\"Freestone, Dean R.\"},{\"Person.name\":\"Kjaer, Troels W.\"},{\"Person.name\":\"Richardson, Mark P.\"},{\"Person.name\":\"Brinkmann, Benjamin H.\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Repositório Científico de Acesso Aberto da ULisboa
datacite.creators.creator.creatorName.fl_str_mv Viana, Pedro
Pal Attia, Tal
Nasseri, Mona
Duun‐Henriksen, Jonas
Biondi, Andrea
Winston, Joel S.
Martins, Isabel Pavão
Nurse, Ewan S.
Dümpelmann, Matthias
Schulze‐Bonhage, Andreas
Freestone, Dean R.
Kjaer, Troels W.
Richardson, Mark P.
Brinkmann, Benjamin H.
datacite.date.Accepted.fl_str_mv 2022-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2022-04-21T15:58:00Z
datacite.date.embargoed.fl_str_mv 2022-04-21T15:58:00Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_16ec
datacite.subjects.subject.fl_str_mv deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
datacite.titles.title.fl_str_mv Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
dc.contributor.none.fl_str_mv Repositório Científico de Acesso Aberto da ULisboa
dc.creator.none.fl_str_mv Viana, Pedro
Pal Attia, Tal
Nasseri, Mona
Duun‐Henriksen, Jonas
Biondi, Andrea
Winston, Joel S.
Martins, Isabel Pavão
Nurse, Ewan S.
Dümpelmann, Matthias
Schulze‐Bonhage, Andreas
Freestone, Dean R.
Kjaer, Troels W.
Richardson, Mark P.
Brinkmann, Benjamin H.
dc.date.Accepted.fl_str_mv 2022-01-01T00:00:00Z
dc.date.available.fl_str_mv 2022-04-21T15:58:00Z
dc.date.embargoed.fl_str_mv 2022-04-21T15:58:00Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10451/52525
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv Wiley
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_16ec
dc.subject.none.fl_str_mv deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
dc.title.fl_str_mv Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Objective: One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. Methods: We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. Results: Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. Significance: This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.
dirty 0
eu_rights_str_mv restrictedAccess
format article
fulltext.url.fl_str_mv https://repositorio.ulisboa.pt/bitstreams/13ffb2d9-0b6b-458d-aa24-99ce3d8d351a/download
funding.funder.alternateName_str_mv EC
funding.funder.identifier_str_mv http://doi.org/10.13039/501100008530
funding.funder.name_str_mv European Commission
funding.name_str_mv H2020
id ul_62b71fccd7400a0bcdc4295caf7755d2
identifier.url.fl_str_mv http://hdl.handle.net/10451/52525
instacron_str ul
institution Universidade de Lisboa
instname_str Universidade de Lisboa
language eng
network_acronym_str ul
network_name_str Repositório da Universidade de Lisboa
oai_identifier_str oai:repositorio.ulisboa.pt:10451/52525
organization_str_mv urn:organizationAcronym:ul
person_str_mv Viana, Pedro
Viana, Pedro
http://orcid.org/0000-0003-0861-8705
0000-0003-0861-8705
Pal Attia, Tal
Nasseri, Mona
Duun‐Henriksen, Jonas
Biondi, Andrea
Winston, Joel S.
Martins, Isabel Pavão
Martins, Isabel Pavão
https://www.ciencia-id.pt/4D1D-4040-BE76
4D1D-4040-BE76
http://orcid.org/0000-0002-9611-7400
0000-0002-9611-7400
Nurse, Ewan S.
Dümpelmann, Matthias
Schulze‐Bonhage, Andreas
Freestone, Dean R.
Kjaer, Troels W.
Richardson, Mark P.
Brinkmann, Benjamin H.
publishDate 2022
publisher.none.fl_str_mv Wiley
reponame_str Repositório da Universidade de Lisboa
repository_id_str urn:repositoryAcronym:ul
service_str_mv urn:repositoryAcronym:ul
spelling engWileypt_PTObjective: One of the most disabling aspects of living with chronic epilepsy is the unpredictability of seizures. Cumulative research in the past decades has advanced our understanding of the dynamics of seizure risk. Technological advances have recently made it possible to record pertinent biological signals, including electroencephalogram (EEG), continuously. We aimed to assess whether patient-specific seizure forecasting is possible using remote, minimally invasive ultra-long-term subcutaneous EEG. Methods: We analyzed a two-center cohort of ultra-long-term subcutaneous EEG recordings, including six patients with drug-resistant focal epilepsy monitored for 46-230 days with median 18 h/day of recorded data, totaling >11 000 h of EEG. Total electrographic seizures identified by visual review ranged from 12 to 36 per patient. Three candidate subject-specific long short-term memory network deep learning classifiers were trained offline and pseudoprospectively on preictal (1 h before) and interictal (>1 day from seizures) EEG segments. Performance was assessed relative to a random predictor. Periodicity of the final forecasts was also investigated with autocorrelation. Results: Depending on each architecture, significant forecasting performance was achieved in three to five of six patients, with overall mean area under the receiver operating characteristic curve of .65-.74. Significant forecasts showed sensitivity ranging from 64% to 80% and time in warning from 10.9% to 44.4%. Overall, the output of the forecasts closely followed patient-specific circadian patterns of seizure occurrence. Significance: This study demonstrates proof-of-principle for the possibility of subject-specific seizure forecasting using a minimally invasive subcutaneous EEG device capable of ultra-long-term at-home recordings. These results are encouraging for the development of a prospective seizure forecasting trial with minimally invasive EEG.application/pdfpt_PTSeizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient modelsPersonalViana, PedroDSpacehttp://dspace.org/items/e22897a7-0bb2-4e48-8b22-d70ddea4c03fDSpacehttp://dspace.org/items/e22897a7-0bb2-4e48-8b22-d70ddea4c03fVianaPedroORCIDhttp://orcid.org0000-0003-0861-8705Pal Attia, TalNasseri, MonaDuun‐Henriksen, JonasBiondi, AndreaWinston, Joel S.PersonalMartins, Isabel PavãoDSpacehttp://dspace.org/items/d134f8f9-be2a-4990-b8ec-3159ff3c51f2DSpacehttp://dspace.org/items/d134f8f9-be2a-4990-b8ec-3159ff3c51f2Pavão MartinsIsabelCiência IDhttps://www.ciencia-id.pt4D1D-4040-BE76ORCIDhttp://orcid.org0000-0002-9611-7400Scopus Author IDhttps://www.scopus.com7103152782Nurse, Ewan S.Dümpelmann, MatthiasSchulze‐Bonhage, AndreasFreestone, Dean R.Kjaer, Troels W.Richardson, Mark P.Brinkmann, Benjamin H.HostingInstitutionOrganizationalRepositório Científico de Acesso Aberto da ULisboae-mailmailto:repositorio@reitoria.ulisboa.ptrepositorio@reitoria.ulisboa.ptISSNIsPartOf0013-9580DOIIsPartOf10.1111/epi.172522022-04-21T15:58:00Z20222022-01-01T00:00:00ZHandlehttp://hdl.handle.net/10451/52525http://purl.org/coar/access_right/c_16ecrestricted accessdeep learningEpilepsyMobile healthSeizure forecastingSeizure predictionSubcutaneous EEG985242 bytesEuropean CommissionRemote Assessment of Disease and Relapse in Central Nervous System DisordersH2020Crossref Funder IDhttp://doi.org/10.13039/501100008530literaturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_16ecapplication/pdffulltexthttps://repositorio.ulisboa.pt/bitstreams/13ffb2d9-0b6b-458d-aa24-99ce3d8d351a/downloadEpilepsia
spellingShingle Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
Viana, Pedro
deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
status SINGLETON
subject.fl_str_mv deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
title Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
title_full Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
title_fullStr Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
title_full_unstemmed Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
title_short Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
title_sort Seizure forecasting using minimally invasive, ultra‐long‐term subcutaneous electroencephalography: individualized intrapatient models
topic deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
topic_facet deep learning
Epilepsy
Mobile health
Seizure forecasting
Seizure prediction
Subcutaneous EEG
url http://hdl.handle.net/10451/52525
visible 1