Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms

Autores
Wang, Shurun; Tang, Hao; Himeno, Ryutaro; Solé Casals, Jordi; Caiafa, César Federico; Han, Shuning; Aoki, Shigeki; Sun, Zhe
Año de publicación
2024
Idioma
inglés
Tipo de recurso
artículo
Estado
versión publicada
Descripción
Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.Methods:This paper propose an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible.Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.
Fil: Wang, Shurun. Hefei University Of Technology; China
Fil: Tang, Hao. Hefei University Of Technology; China
Fil: Himeno, Ryutaro. Juntendo University; Japón
Fil: Solé Casals, Jordi. University of Vic; España
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Han, Shuning. ;
Fil: Aoki, Shigeki. Juntendo University; Japón
Fil: Sun, Zhe. Juntendo University; Japón
Materia
Graph Neural Network
Graph Neural Architecture Search
Evolutionary Algorithm
Squizophrenia
Nivel de accesibilidad
acceso abierto
Condiciones de uso
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
Repositorio
CONICET Digital (CONICET)
Institución
Consejo Nacional de Investigaciones Científicas y Técnicas
OAI Identificador
oai:ri.conicet.gov.ar:11336/245841
Acceder
id CONICETDig_4147752fb77e81d4187bda5a0029ded1
oai_identifier_str oai:ri.conicet.gov.ar:11336/245841
network_acronym_str CONICETDig
repository_id_str 3498
network_name_str CONICET Digital (CONICET)
spelling Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithmsWang, ShurunTang, HaoHimeno, RyutaroSolé Casals, JordiCaiafa, César FedericoHan, ShuningAoki, ShigekiSun, ZheGraph Neural NetworkGraph Neural Architecture SearchEvolutionary AlgorithmSquizophreniahttps://purl.org/becyt/ford/1.2https://purl.org/becyt/ford/1Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.Methods:This paper propose an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible.Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.Fil: Wang, Shurun. Hefei University Of Technology; ChinaFil: Tang, Hao. Hefei University Of Technology; ChinaFil: Himeno, Ryutaro. Juntendo University; JapónFil: Solé Casals, Jordi. University of Vic; EspañaFil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; ArgentinaFil: Han, Shuning. ;Fil: Aoki, Shigeki. Juntendo University; JapónFil: Sun, Zhe. Juntendo University; JapónElsevier Ireland2024-09info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionhttp://purl.org/coar/resource_type/c_6501info:ar-repo/semantics/articuloapplication/pdfapplication/pdfhttp://hdl.handle.net/11336/245841Wang, Shurun; Tang, Hao; Himeno, Ryutaro; Solé Casals, Jordi; Caiafa, César Federico; et al.; Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms; Elsevier Ireland; Computer Methods And Programs In Biomedicine; 257; 9-2024; 108419, 1-280169-2607CONICET DigitalCONICETenginfo:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0169260724004127info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cmpb.2024.108419info:eu-repo/semantics/openAccesshttps://creativecommons.org/licenses/by-nc-sa/2.5/ar/reponame:CONICET Digital (CONICET)instname:Consejo Nacional de Investigaciones Científicas y Técnicas2025-09-03T10:08:05Zoai:ri.conicet.gov.ar:11336/245841instacron:CONICETInstitucionalhttp://ri.conicet.gov.ar/Organismo científico-tecnológicoNo correspondehttp://ri.conicet.gov.ar/oai/requestdasensio@conicet.gov.ar; lcarlino@conicet.gov.arArgentinaNo correspondeNo correspondeNo correspondeopendoar:34982025-09-03 10:08:05.26CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicasfalse
dc.title.none.fl_str_mv Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
title Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
spellingShingle Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
Wang, Shurun
Graph Neural Network
Graph Neural Architecture Search
Evolutionary Algorithm
Squizophrenia
title_short Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
title_full Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
title_fullStr Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
title_full_unstemmed Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
title_sort Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms
dc.creator.none.fl_str_mv Wang, Shurun
Tang, Hao
Himeno, Ryutaro
Solé Casals, Jordi
Caiafa, César Federico
Han, Shuning
Aoki, Shigeki
Sun, Zhe
author Wang, Shurun
author_facet Wang, Shurun
Tang, Hao
Himeno, Ryutaro
Solé Casals, Jordi
Caiafa, César Federico
Han, Shuning
Aoki, Shigeki
Sun, Zhe
author_role author
author2 Tang, Hao
Himeno, Ryutaro
Solé Casals, Jordi
Caiafa, César Federico
Han, Shuning
Aoki, Shigeki
Sun, Zhe
author2_role author
author
author
author
author
author
author
dc.subject.none.fl_str_mv Graph Neural Network
Graph Neural Architecture Search
Evolutionary Algorithm
Squizophrenia
topic Graph Neural Network
Graph Neural Architecture Search
Evolutionary Algorithm
Squizophrenia
purl_subject.fl_str_mv https://purl.org/becyt/ford/1.2
https://purl.org/becyt/ford/1
dc.description.none.fl_txt_mv Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.Methods:This paper propose an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible.Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.
Fil: Wang, Shurun. Hefei University Of Technology; China
Fil: Tang, Hao. Hefei University Of Technology; China
Fil: Himeno, Ryutaro. Juntendo University; Japón
Fil: Solé Casals, Jordi. University of Vic; España
Fil: Caiafa, César Federico. Provincia de Buenos Aires. Gobernación. Comisión de Investigaciones Científicas. Instituto Argentino de Radioastronomía. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - La Plata. Instituto Argentino de Radioastronomía; Argentina
Fil: Han, Shuning. ;
Fil: Aoki, Shigeki. Juntendo University; Japón
Fil: Sun, Zhe. Juntendo University; Japón
description Background and Objective:The accurate diagnosis of schizophrenia spectrum disorder plays an important role in improving patient outcomes, enabling timely interventions, and optimizing treatment plans. Functional connectivity analysis, utilizing functional magnetic resonance imaging data, has been demonstrated to offer invaluable biomarkers conducive to clinical diagnosis. However, previous studies mainly focus on traditional machine learning methods or hand-crafted neural networks, which may not fully capture the spatial topological relationship between brain regions.Methods:This paper propose an evolutionary algorithm (EA) based graph neural architecture search (GNAS) method. EA-GNAS has the ability to search for high-performance graph neural networks for schizophrenia spectrum disorder prediction. Moreover, we adopt GNNExplainer to investigate the explainability of the acquired architectures, ensuring that the model’s predictions are both accurate and comprehensible.Results:The results suggest that the graph neural network model, derived using genetic algorithm search, outperforms under five-fold cross-validation, achieving a fitness of 0.1850. Relative to conventional machine learning and other deep learning approaches, the proposed method yields superior accuracy, F1 score, and AUC values of 0.8246, 0.8438, and 0.8258, respectively.Conclusion:Based on a multi-site dataset from schizophrenia spectrum disorder patients, the findings reveal an enhancement over prior methods, advancing our comprehension of brain function and potentially offering a biomarker for diagnosing schizophrenia spectrum disorder.
publishDate 2024
dc.date.none.fl_str_mv 2024-09
dc.type.none.fl_str_mv info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
http://purl.org/coar/resource_type/c_6501
info:ar-repo/semantics/articulo
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv http://hdl.handle.net/11336/245841
Wang, Shurun; Tang, Hao; Himeno, Ryutaro; Solé Casals, Jordi; Caiafa, César Federico; et al.; Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms; Elsevier Ireland; Computer Methods And Programs In Biomedicine; 257; 9-2024; 108419, 1-28
0169-2607
CONICET Digital
CONICET
url http://hdl.handle.net/11336/245841
identifier_str_mv Wang, Shurun; Tang, Hao; Himeno, Ryutaro; Solé Casals, Jordi; Caiafa, César Federico; et al.; Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms; Elsevier Ireland; Computer Methods And Programs In Biomedicine; 257; 9-2024; 108419, 1-28
0169-2607
CONICET Digital
CONICET
dc.language.none.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv info:eu-repo/semantics/altIdentifier/url/https://linkinghub.elsevier.com/retrieve/pii/S0169260724004127
info:eu-repo/semantics/altIdentifier/doi/10.1016/j.cmpb.2024.108419
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
eu_rights_str_mv openAccess
rights_invalid_str_mv https://creativecommons.org/licenses/by-nc-sa/2.5/ar/
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Elsevier Ireland
publisher.none.fl_str_mv Elsevier Ireland
dc.source.none.fl_str_mv reponame:CONICET Digital (CONICET)
instname:Consejo Nacional de Investigaciones Científicas y Técnicas
reponame_str CONICET Digital (CONICET)
collection CONICET Digital (CONICET)
instname_str Consejo Nacional de Investigaciones Científicas y Técnicas
repository.name.fl_str_mv CONICET Digital (CONICET) - Consejo Nacional de Investigaciones Científicas y Técnicas
repository.mail.fl_str_mv dasensio@conicet.gov.ar; lcarlino@conicet.gov.ar
_version_ 1842270030401634304
score 13.13397

Publicaciones similares