Epileptic seizure prediction using machine learning techniques

Detalhes bibliográficos
Autor(a) principal: Salvador, Carolina Duarte
Data de Publicação: 2023
Tipo de documento: Dissertação
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10400.6/13643
Resumo: Epileptic seizures affect about 1% of the world’s population, thus making it the fourth most common neurological disease, this disease is considered a neurological disorder characterized by the abnormal activity of the brain. Part of the population suffering from this disease is unable to avail themselves of any treatment, as this treatment has no beneficial effect on the patient. One of the main concerns associated with this disease is the damage caused by uncontrollable seizures. This damage affects not only the patient himself but also the people around him. With this situation in mind, the goal of this thesis is, through methods of Machine Learning, to create an algorithm that can predict epileptic seizures before they occur. To predict these seizures, the electroencephalogram (EEG) will be employed, since it is the most commonly used method for diagnosing epilepsy. Of the total 23 channels available, only 8 will be used, due to their location. When a seizure occurs, besides the visible changes in the EEG signal, at the moment of the seizure, the alterations before and after the epileptic seizure are also noticeable. These stages have been named in the literature: • Preictal: the moment before the epileptic seizure; • Ictal: the moment of the seizure; • Postictal: the moment after the seizure; • Interictal: space of time between seizures. The goal of the predictive algorithm will be to classify the different classes and study different classification problems by using supervised learning techniques, more precisely a classifier. By performing this classification when indications are detected that a possible epileptic seizure will occur, the patient will then be warned so that he can prepare for the seizure.
id RCAP_ecc547ed7f92a017f0749ff158fac1dc
oai_identifier_str oai:ubibliorum.ubi.pt:10400.6/13643
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Epileptic seizure prediction using machine learning techniquesEegEpilepsiaMachine LearningPrevisão de AtaquesDomínio/Área Científica::Engenharia e Tecnologia::BioengenhariaEpileptic seizures affect about 1% of the world’s population, thus making it the fourth most common neurological disease, this disease is considered a neurological disorder characterized by the abnormal activity of the brain. Part of the population suffering from this disease is unable to avail themselves of any treatment, as this treatment has no beneficial effect on the patient. One of the main concerns associated with this disease is the damage caused by uncontrollable seizures. This damage affects not only the patient himself but also the people around him. With this situation in mind, the goal of this thesis is, through methods of Machine Learning, to create an algorithm that can predict epileptic seizures before they occur. To predict these seizures, the electroencephalogram (EEG) will be employed, since it is the most commonly used method for diagnosing epilepsy. Of the total 23 channels available, only 8 will be used, due to their location. When a seizure occurs, besides the visible changes in the EEG signal, at the moment of the seizure, the alterations before and after the epileptic seizure are also noticeable. These stages have been named in the literature: • Preictal: the moment before the epileptic seizure; • Ictal: the moment of the seizure; • Postictal: the moment after the seizure; • Interictal: space of time between seizures. The goal of the predictive algorithm will be to classify the different classes and study different classification problems by using supervised learning techniques, more precisely a classifier. By performing this classification when indications are detected that a possible epileptic seizure will occur, the patient will then be warned so that he can prepare for the seizure.Crises epiléticas afetam cerca de 1% da população mundial, tornando-a assim a quarta doença neurológica mais comum. Esta é considerada uma doença caracterizada pela atividade anormal do cérebro. Parte da população que sofre desta condição não consegue recorrer a qualquer tratamento, pois este não apresenta qualquer efeito benéfico no paciente. Uma das principais preocupações associadas com este problema são os danos causados pelas convulsões imprevisíveis. Estes danos não afetam somente o próprio paciente, como também as pessoas que o rodeiam. Com esta situação em mente, o objetivo desta dissertação consiste em, através de métodos de Machine Learning, criar um algoritmo capaz de prever as crises epiléticas antes da sua ocorrência. Para proceder à previsão destas convulsões, será utilizado o eletroencefalograma (EEG), uma vez que é o método mais usado para o diagnóstico de epilepsia. Serão utilizados apenas 8 dos 23 canais disponíveis, devido à sua localização. Quando ocorre uma crise, além das alterações visíveis no sinal EEG, não só no momento da crise, são também notáveis alterações antes e após a convulsão. A estas fases a literatura nomeou: • Pre-ictal: momento anterior à crise epilética; • Ictal: momento da convulsão; • Pós-ictal: momento posterior à crise; • Interictal: espaço de tempo entre convulsões. O objetivo do algoritmo preditivo será fazer a classificação das diferentes classes e o estudo de diferentes problemas de classificação, através do uso de técnicas de machine learning, mais precisamente um classificador. Ao realizar esta classificação, quando forem detetados indícios de que uma possível crise epilética irá ocorrer, o paciente será então avisado, podendo assim preparar-se para esta.Santos, Nuno Manuel Garcia dosFelizardo, Virginie dos SantosPourvahab, MehranuBibliorumSalvador, Carolina Duarte2023-11-10T14:39:41Z2023-07-202023-06-122023-07-20T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.6/13643TID:203382935enginfo: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:RCAAP2024-01-31T02:31:59Zoai:ubibliorum.ubi.pt:10400.6/13643Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:53:02.320364Repositório 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 Epileptic seizure prediction using machine learning techniques
title Epileptic seizure prediction using machine learning techniques
spellingShingle Epileptic seizure prediction using machine learning techniques
Salvador, Carolina Duarte
Eeg
Epilepsia
Machine Learning
Previsão de Ataques
Domínio/Área Científica::Engenharia e Tecnologia::Bioengenharia
title_short Epileptic seizure prediction using machine learning techniques
title_full Epileptic seizure prediction using machine learning techniques
title_fullStr Epileptic seizure prediction using machine learning techniques
title_full_unstemmed Epileptic seizure prediction using machine learning techniques
title_sort Epileptic seizure prediction using machine learning techniques
author Salvador, Carolina Duarte
author_facet Salvador, Carolina Duarte
author_role author
dc.contributor.none.fl_str_mv Santos, Nuno Manuel Garcia dos
Felizardo, Virginie dos Santos
Pourvahab, Mehran
uBibliorum
dc.contributor.author.fl_str_mv Salvador, Carolina Duarte
dc.subject.por.fl_str_mv Eeg
Epilepsia
Machine Learning
Previsão de Ataques
Domínio/Área Científica::Engenharia e Tecnologia::Bioengenharia
topic Eeg
Epilepsia
Machine Learning
Previsão de Ataques
Domínio/Área Científica::Engenharia e Tecnologia::Bioengenharia
description Epileptic seizures affect about 1% of the world’s population, thus making it the fourth most common neurological disease, this disease is considered a neurological disorder characterized by the abnormal activity of the brain. Part of the population suffering from this disease is unable to avail themselves of any treatment, as this treatment has no beneficial effect on the patient. One of the main concerns associated with this disease is the damage caused by uncontrollable seizures. This damage affects not only the patient himself but also the people around him. With this situation in mind, the goal of this thesis is, through methods of Machine Learning, to create an algorithm that can predict epileptic seizures before they occur. To predict these seizures, the electroencephalogram (EEG) will be employed, since it is the most commonly used method for diagnosing epilepsy. Of the total 23 channels available, only 8 will be used, due to their location. When a seizure occurs, besides the visible changes in the EEG signal, at the moment of the seizure, the alterations before and after the epileptic seizure are also noticeable. These stages have been named in the literature: • Preictal: the moment before the epileptic seizure; • Ictal: the moment of the seizure; • Postictal: the moment after the seizure; • Interictal: space of time between seizures. The goal of the predictive algorithm will be to classify the different classes and study different classification problems by using supervised learning techniques, more precisely a classifier. By performing this classification when indications are detected that a possible epileptic seizure will occur, the patient will then be warned so that he can prepare for the seizure.
publishDate 2023
dc.date.none.fl_str_mv 2023-11-10T14:39:41Z
2023-07-20
2023-06-12
2023-07-20T00:00:00Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/10400.6/13643
TID:203382935
url http://hdl.handle.net/10400.6/13643
identifier_str_mv TID:203382935
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
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_ 1799136418434383872