A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/105444 https://doi.org/10.1038/s41598-021-82828-7 |
Resumo: | Seizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms. |
id |
RCAP_562876e73d525a6b6d4f7446b26b7a97 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/105444 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure predictionDrug Resistant EpilepsyEpilepsy, Temporal LobeHumansSeizuresAlgorithmsElectroencephalographyPrecision MedicineSignal Processing, Computer-AssistedSeizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms.Springer Nature2021-02-09info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/105444http://hdl.handle.net/10316/105444https://doi.org/10.1038/s41598-021-82828-7eng2045-2322Pinto, Mauro F.Leal, AdrianaLopes, FábioDourado, AntónioMartins, PedroTeixeira, César A.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2023-02-28T11:11:18Zoai:estudogeral.uc.pt:10316/105444Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:22:01.043905Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
title |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
spellingShingle |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction Pinto, Mauro F. Drug Resistant Epilepsy Epilepsy, Temporal Lobe Humans Seizures Algorithms Electroencephalography Precision Medicine Signal Processing, Computer-Assisted |
title_short |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
title_full |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
title_fullStr |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
title_full_unstemmed |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
title_sort |
A personalized and evolutionary algorithm for interpretable EEG epilepsy seizure prediction |
author |
Pinto, Mauro F. |
author_facet |
Pinto, Mauro F. Leal, Adriana Lopes, Fábio Dourado, António Martins, Pedro Teixeira, César A. |
author_role |
author |
author2 |
Leal, Adriana Lopes, Fábio Dourado, António Martins, Pedro Teixeira, César A. |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Pinto, Mauro F. Leal, Adriana Lopes, Fábio Dourado, António Martins, Pedro Teixeira, César A. |
dc.subject.por.fl_str_mv |
Drug Resistant Epilepsy Epilepsy, Temporal Lobe Humans Seizures Algorithms Electroencephalography Precision Medicine Signal Processing, Computer-Assisted |
topic |
Drug Resistant Epilepsy Epilepsy, Temporal Lobe Humans Seizures Algorithms Electroencephalography Precision Medicine Signal Processing, Computer-Assisted |
description |
Seizure prediction may improve the quality of life of patients suffering from drug-resistant epilepsy, which accounts for about 30% of the total epileptic patients. The pre-ictal period determination, characterized by a transitional stage between normal brain activity and seizure, is a critical step. Past approaches failed to attain real-world applicability due to lack of generalization capacity. More recently, deep learning techniques may outperform traditional classifiers and handle time dependencies. However, despite the existing efforts for providing interpretable insights, clinicians may not be willing to make high-stake decisions based on them. Furthermore, a disadvantageous aspect of the more usual seizure prediction pipeline is its modularity and significant independence between stages. An alternative could be the construction of a search algorithm that, while considering pipeline stages' synergy, fine-tunes the selection of a reduced set of features that are widely used in the literature and computationally efficient. With extracranial recordings from 19 patients suffering from temporal-lobe seizures, we developed a patient-specific evolutionary optimization strategy, aiming to generate the optimal set of features for seizure prediction with a logistic regression classifier, which was tested prospectively in a total of 49 seizures and 710 h of continuous recording and performed above chance for 32% of patients, using a surrogate predictor. These results demonstrate the hypothesis of pre-ictal period identification without the loss of interpretability, which may help understanding brain dynamics leading to seizures and improve prediction algorithms. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-02-09 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://hdl.handle.net/10316/105444 http://hdl.handle.net/10316/105444 https://doi.org/10.1038/s41598-021-82828-7 |
url |
http://hdl.handle.net/10316/105444 https://doi.org/10.1038/s41598-021-82828-7 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2045-2322 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Springer Nature |
publisher.none.fl_str_mv |
Springer Nature |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134110223958016 |