Using compression for profiling rheumatoid arthritis disease progression through data mining techniques

Detalhes bibliográficos
Autor(a) principal: Azevedo, Diogo Henrique Rodrigues
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/10451/56825
Resumo: Tese de mestrado, Ciência de Dados, 2022, Universidade de Lisboa, Faculdade de Ciências
id RCAP_d69676bccd166b1b1312400e540bd9ab
oai_identifier_str oai:repositorio.ul.pt:10451/56825
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Using compression for profiling rheumatoid arthritis disease progression through data mining techniquesKolmogorovComplearnZgliClusteringAITeses de mestrado - 2022Departamento de InformáticaTese de mestrado, Ciência de Dados, 2022, Universidade de Lisboa, Faculdade de CiênciasAnkylosing spondylitis (AS) is a chronic autoimmune inflammatory condition belonging to the spondyloarthropathy category of rheumatic diseases characterized by being highly debilitating diseases and having a high impact on patients physical and mental health as well as social and quality of life. Biological treatment for this pathology is difficult to pick and lacks clear selection criteria. Usually, treatment is chosen based on patient convenience. Our goal is to use an approach based on algorithmic information theory, without any domain-specific parameters to set, or any background knowledge required (clustering by compression), iterate over the current state of the art, so it can be better integrated into python pipelines as well as better suit our specific problem, and apply it to our data comprised of patients with AS so patterns between biological treatments and patient profiles can be established thereby helping clinicians make a better treatment choice for each patient. Unsupervised clustering models are generated using normalized compression distance matrices, which are then evaluated using v-measure, adjusted random score, and visually analyzed taking into account model contingency matrix and feature distribution per cluster. Possible patterns between biological treatment success and patient profiles were identified. Furthermore, we observed that the compression by column developed and implemented in this new tool for clustering by compression seemed to yield better results than the previous approach.Souto, André Nuno CarvalhoRepositório da Universidade de LisboaAzevedo, Diogo Henrique Rodrigues2023-03-27T10:40:07Z202220222022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10451/56825enginfo: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:RCAAP2023-11-08T17:04:49Zoai:repositorio.ul.pt:10451/56825Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T22:07:22.813913Repositório 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 Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
title Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
spellingShingle Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
Azevedo, Diogo Henrique Rodrigues
Kolmogorov
Complearn
Zgli
Clustering
AI
Teses de mestrado - 2022
Departamento de Informática
title_short Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
title_full Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
title_fullStr Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
title_full_unstemmed Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
title_sort Using compression for profiling rheumatoid arthritis disease progression through data mining techniques
author Azevedo, Diogo Henrique Rodrigues
author_facet Azevedo, Diogo Henrique Rodrigues
author_role author
dc.contributor.none.fl_str_mv Souto, André Nuno Carvalho
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Azevedo, Diogo Henrique Rodrigues
dc.subject.por.fl_str_mv Kolmogorov
Complearn
Zgli
Clustering
AI
Teses de mestrado - 2022
Departamento de Informática
topic Kolmogorov
Complearn
Zgli
Clustering
AI
Teses de mestrado - 2022
Departamento de Informática
description Tese de mestrado, Ciência de Dados, 2022, Universidade de Lisboa, Faculdade de Ciências
publishDate 2022
dc.date.none.fl_str_mv 2022
2022
2022-01-01T00:00:00Z
2023-03-27T10:40:07Z
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/10451/56825
url http://hdl.handle.net/10451/56825
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_ 1799134627388981248

Registros relacionados