Examining differences in brain metabolism associated with childhood maltreatment and suicidal attempt in euthymic patients with bipolar disorder: A PET and Machine Learning Study

Página do item simplificado
dc.creatorDante Duarte
dc.creatorManuel Schütze
dc.creatorMazen Elkhayat
dc.creatorMaila de Castro Lourenço Das Neves
dc.creatorMarco Aurélio Romano Silva
dc.creatorHumberto Correa
dc.date.accessioned2023-11-06T20:40:26Z
dc.date.accessioned2025-09-08T23:18:06Z
dc.date.available2023-11-06T20:40:26Z
dc.date.issued2023-04-19
dc.description.sponsorshipCNPq - Conselho Nacional de Desenvolvimento Científico e Tecnológico
dc.format.mimetypepdf
dc.identifier.doihttp://doi.org/10.47626/1516-4446-2022-2811
dc.identifier.issn1809-452X
dc.identifier.urihttps://hdl.handle.net/1843/60519
dc.languageeng
dc.publisherUniversidade Federal de Minas Gerais
dc.relation.ispartofBrazilian Journal of Psychiatry
dc.rightsAcesso Aberto
dc.subjectInfância
dc.subjectAprendizado do computador
dc.subjectTomografia por emissão de pósitrons
dc.subjectTentativa de Suicídio
dc.subjectTranstorno Bipolar
dc.subject.otherBipolar disorder
dc.subject.otherChildhood maltreatment
dc.subject.otherSuicide attempt
dc.subject.other18F-FDG
dc.subject.otherPositron emission tomography
dc.subject.otherMachine learning
dc.titleExamining differences in brain metabolism associated with childhood maltreatment and suicidal attempt in euthymic patients with bipolar disorder: A PET and Machine Learning Study
dc.typeArtigo de periódico
local.citation.epage131
local.citation.issue2
local.citation.spage127
local.citation.volume45
local.description.resumoOBJECTIVE: Childhood maltreatment (CM) is a significant risk factor for the development and severity of bipolar disorder (BD) with increased risk of suicide attempts (SA). This study evaluated whether a machine learning algorithm could be trained to predict if a patient with BD has a history of CM or previous SA based on brain metabolism measured by positron emission tomography. METHODS: Thirty-six euthymic patients diagnosed with BD type I, with and without a history of CM were assessed using the Childhood Trauma Questionnaire. Suicide attempts were assessed through the Mini International Neuropsychiatric Interview (MINI-Plus) and a semi-structured interview. Resting-state positron emission tomography with 18F-fluorodeoxyglucose was conducted, electing only grey matter voxels through the Statistical Parametric Mapping toolbox. Imaging analysis was performed using a supervised machine learning approach following Gaussian Process Classification. RESULTS: Patients were divided into 18 participants with a history of CM and 18 participants without it, along with 18 individuals with previous SA and 18 individuals without such history. The predictions for CM and SA were not significant (accuracy = 41.67%; p = 0.879). CONCLUSION: Further investigation is needed to improve the accuracy of machine learning, as its predictive qualities could potentially be highly useful in determining histories and possible outcomes of high-risk psychiatric patients.
local.identifier.orcidhttps://orcid.org/0000-0001-7516-5473
local.identifier.orcidhttps://orcid.org/0000-0003-1947-9675
local.identifier.orcidhttps://orcid.org/0000-0003-1876-2022
local.identifier.orcidhttps://orcid.org/0000-0003-4125-3736
local.publisher.countryBrasil
local.publisher.departmentMED - DEPARTAMENTO DE SAÚDE MENTAL
local.publisher.departmentMEDICINA - FACULDADE DE MEDICINA
local.publisher.initialsUFMG
local.url.externahttps://www.bjp.org.br/details/2335/en-US/examining-differences-in-brain-metabolism-associated-with-childhood-maltreatment-and-suicidal-attempt-in-euthymic-patients-with-bipolar-disorder--a-pe

Arquivos

Pacote original

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
Examining differences in brain metabolism associated with childhood maltreatment and suicidal attempt in euthymic patients with bipolar disorder_ A PET and Machine Learning Study.pdf
Tamanho:
151.44 KB
Formato:
Adobe Portable Document Format
Baixar

Licença do pacote

Agora exibindo 1 - 1 de 1
Imagem de Miniatura
Nome:
License.txt
Tamanho:
978 B
Formato:
Plain Text
Descrição:
Baixar

Coleções

Artigo de Periódico

Logo UFMG