Machine learning approaches for detecting depression using eeg signals
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Tipo de documento: | Dissertação |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10400.14/37977 |
Resumo: | The burden of neurological disorders continues to grow, as an estimated 264 million people currently suffer from depression worldwide. Due to the stigma surrounding mental illness and to the standard diagnostic approach being so human-intensive, depressed individuals are less likely to seek help. Additionally, the diagnosis’ results are dependent on the doctor’s experience. When patients are misdiagnosed, the search for physical explanations of symptoms further increases the medical care cost, which a lot of people are not able to support. Hence, the search for a cost-effective, objective, and less human-intensive diagnostic method of depression happens to be crucial. The present study focused on developing a tool capable of detecting indicative patterns of depression and automatically discriminate patients with depression through EEG signal analysis. With resource to 1D Discrete Wavelet Transform, a multiband analysis of the signals was performed per EEG channel. After the feature extraction and the feature selection processes, the obtained features fed 25 Machine Learning models and a convolutional neural network (CNN). The three classifiers with the best performance were Linear Discriminant Analysis, Cubic Support Vector Machine, and the designed CNN, with an overall classification accuracy of 94.8%, 93.9%, and 94.9%, respectively. Through these three classifiers, the comparison between depressed subjects and healthy controls reached an accuracy of 100% on several channels. The results obtained by the classifiers alongside an analysis through topographic maps lead to conclude that there is a difference in the frequency of brain waves between the two groups, with a strong incidence in the frontocentral, central, and parietooccipital regions of the scalp. Although EEG signal analysis cannot yet be applied as a diagnostic tool for depression, the findings in this study remain relevant from a theoretical point of view. |
id |
RCAP_ab7d8d05bee73b91abecdb154a4795d3 |
---|---|
oai_identifier_str |
oai:repositorio.ucp.pt:10400.14/37977 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Machine learning approaches for detecting depression using eeg signalsConvolutional neural networkDepressionDiscrete wavelet transformEEG signalsMachine learningDepressãoRede neural convolucionSinais EEGTransformada de wavelet discretaDomínio/Área Científica::Engenharia e Tecnologia::Engenharia MédicaThe burden of neurological disorders continues to grow, as an estimated 264 million people currently suffer from depression worldwide. Due to the stigma surrounding mental illness and to the standard diagnostic approach being so human-intensive, depressed individuals are less likely to seek help. Additionally, the diagnosis’ results are dependent on the doctor’s experience. When patients are misdiagnosed, the search for physical explanations of symptoms further increases the medical care cost, which a lot of people are not able to support. Hence, the search for a cost-effective, objective, and less human-intensive diagnostic method of depression happens to be crucial. The present study focused on developing a tool capable of detecting indicative patterns of depression and automatically discriminate patients with depression through EEG signal analysis. With resource to 1D Discrete Wavelet Transform, a multiband analysis of the signals was performed per EEG channel. After the feature extraction and the feature selection processes, the obtained features fed 25 Machine Learning models and a convolutional neural network (CNN). The three classifiers with the best performance were Linear Discriminant Analysis, Cubic Support Vector Machine, and the designed CNN, with an overall classification accuracy of 94.8%, 93.9%, and 94.9%, respectively. Through these three classifiers, the comparison between depressed subjects and healthy controls reached an accuracy of 100% on several channels. The results obtained by the classifiers alongside an analysis through topographic maps lead to conclude that there is a difference in the frequency of brain waves between the two groups, with a strong incidence in the frontocentral, central, and parietooccipital regions of the scalp. Although EEG signal analysis cannot yet be applied as a diagnostic tool for depression, the findings in this study remain relevant from a theoretical point of view.O cargo dos distúrbios neurológicos continua a crescer, estimando-se que, a nível mundial, 264 milhões de pessoas sofram de depressão atualmente. Devido ao estigma associado à doença mental e ao facto de a abordagem de diagnóstico mais comum ser tão humano-intensiva, é menos provável que os indivíduos deprimidos procurem ajuda. Além disso, os resultados do diagnóstico estão dependentes da experiência do profissional de saúde. Quando os pacientes são incorretamente diagnosticados, a procura de explicações físicas dos sintomas aumenta ainda mais o custo dos cuidados médicos, que muitas pessoas não têm capacidade financeira para suportar. Como tal, a procura de um método de diagnóstico da depressão económico, objetivo, e menos humano-intensivo torna-se crucial. O presente estudo centrou-se no desenvolvimento de uma ferramenta capaz de detetar padrões indicativos de depressão e de discriminar automaticamente os pacientes deprimidos através da análise de sinais EEG. Com recurso à Transformada de Wavelet Discreta 1D, foi realizada uma análise multibanda dos sinais por canal EEG. Após os processos de extração e seleção de parâmetros, os parâmetros obtidos alimentaram 25 modelos de Machine Learning e uma Rede Neural Convolucional (CNN). Os três classificadores com melhor desempenho foram os seguintes: Análise Discriminante Linear, Máquina de Vetor de Suporte (janela cúbica), e a CNN concebida, com uma precisão de classificação global de 94,8%, 93,9%, e 94,9%, respetivamente. Através destes três classificadores, a comparação entre sujeitos deprimidos e controlos saudáveis atingiu uma precisão de 100% em vários canais. Os resultados obtidos pelos classificadores, juntamente com uma análise através de mapas topográficos, levam a concluir que existe uma diferença na frequência das ondas cerebrais entre os dois grupos, com uma forte incidência nas regiões frontocentral, central, e parietoccipital do couro cabeludo. Embora a análise do sinal EEG ainda não possa ser aplicada como ferramenta de diagnóstico da depressão, os resultados deste estudo continuam a ser relevantes do ponto de vista teórico.Rodrigues, Pedro Miguel de LuísBispo, Bruno CatarinoVeritati - Repositório Institucional da Universidade Católica PortuguesaOliveira, Eunice Monteiro de2022-06-24T16:49:57Z2022-05-262022-022022-05-26T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10400.14/37977TID:203025237enginfo: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:RCAAP2023-07-12T17:43:29Zoai:repositorio.ucp.pt:10400.14/37977Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T18:30:56.916003Repositório 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 |
Machine learning approaches for detecting depression using eeg signals |
title |
Machine learning approaches for detecting depression using eeg signals |
spellingShingle |
Machine learning approaches for detecting depression using eeg signals Oliveira, Eunice Monteiro de Convolutional neural network Depression Discrete wavelet transform EEG signals Machine learning Depressão Rede neural convolucion Sinais EEG Transformada de wavelet discreta Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Médica |
title_short |
Machine learning approaches for detecting depression using eeg signals |
title_full |
Machine learning approaches for detecting depression using eeg signals |
title_fullStr |
Machine learning approaches for detecting depression using eeg signals |
title_full_unstemmed |
Machine learning approaches for detecting depression using eeg signals |
title_sort |
Machine learning approaches for detecting depression using eeg signals |
author |
Oliveira, Eunice Monteiro de |
author_facet |
Oliveira, Eunice Monteiro de |
author_role |
author |
dc.contributor.none.fl_str_mv |
Rodrigues, Pedro Miguel de Luís Bispo, Bruno Catarino Veritati - Repositório Institucional da Universidade Católica Portuguesa |
dc.contributor.author.fl_str_mv |
Oliveira, Eunice Monteiro de |
dc.subject.por.fl_str_mv |
Convolutional neural network Depression Discrete wavelet transform EEG signals Machine learning Depressão Rede neural convolucion Sinais EEG Transformada de wavelet discreta Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Médica |
topic |
Convolutional neural network Depression Discrete wavelet transform EEG signals Machine learning Depressão Rede neural convolucion Sinais EEG Transformada de wavelet discreta Domínio/Área Científica::Engenharia e Tecnologia::Engenharia Médica |
description |
The burden of neurological disorders continues to grow, as an estimated 264 million people currently suffer from depression worldwide. Due to the stigma surrounding mental illness and to the standard diagnostic approach being so human-intensive, depressed individuals are less likely to seek help. Additionally, the diagnosis’ results are dependent on the doctor’s experience. When patients are misdiagnosed, the search for physical explanations of symptoms further increases the medical care cost, which a lot of people are not able to support. Hence, the search for a cost-effective, objective, and less human-intensive diagnostic method of depression happens to be crucial. The present study focused on developing a tool capable of detecting indicative patterns of depression and automatically discriminate patients with depression through EEG signal analysis. With resource to 1D Discrete Wavelet Transform, a multiband analysis of the signals was performed per EEG channel. After the feature extraction and the feature selection processes, the obtained features fed 25 Machine Learning models and a convolutional neural network (CNN). The three classifiers with the best performance were Linear Discriminant Analysis, Cubic Support Vector Machine, and the designed CNN, with an overall classification accuracy of 94.8%, 93.9%, and 94.9%, respectively. Through these three classifiers, the comparison between depressed subjects and healthy controls reached an accuracy of 100% on several channels. The results obtained by the classifiers alongside an analysis through topographic maps lead to conclude that there is a difference in the frequency of brain waves between the two groups, with a strong incidence in the frontocentral, central, and parietooccipital regions of the scalp. Although EEG signal analysis cannot yet be applied as a diagnostic tool for depression, the findings in this study remain relevant from a theoretical point of view. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-06-24T16:49:57Z 2022-05-26 2022-02 2022-05-26T00:00:00Z |
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/10400.14/37977 TID:203025237 |
url |
http://hdl.handle.net/10400.14/37977 |
identifier_str_mv |
TID:203025237 |
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_ |
1799132032330104832 |