Temporal unsupervised learning models to study ALS progression

Detalhes bibliográficos
Autor(a) principal: Seguro, Afonso Manuel Tito Lopes
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/10451/63205
Resumo: Tese de mestrado, Engenharia Informática, 2023, Universidade de Lisboa, Faculdade de Ciências
id RCAP_31136ec061159a886b6a3791dfe076d4
oai_identifier_str oai:repositorio.ul.pt:10451/63205
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Temporal unsupervised learning models to study ALS progressionEsclerose Lateral AmiotroficaAprendizagem AutomáticaEstratificação Temporal não-supervisionadaProcedimentos médicos ELATeses de mestrado - 2023Departamento de InformáticaTese de mestrado, Engenharia Informática, 2023, Universidade de Lisboa, Faculdade de CiênciasAmyotrophic Lateral Sclerosis (ALS) is a rapidly progressing chronic disease that affects motor neurons, leading to progressive disability and eventually paralysis. Due to its complexity and heterogeneity, the search for effective treatments that can slow down the progression of ALS and improve the quality of life of patients has been a constant challenge in the medical field[54]. Thus, it is important to automatically identify the groups of patients with similar progressions, to improve the prediction of medical procedures. This work is divided into three parts: stratification, prognosis of the type of progression, and prediction of the need for medical procedures. In stratification, groups of patients with similar progressions are found to help new patients predict their needs, resulting in five groups: lower limbs, upper limbs, bulbar, diffuse (with a strong respiratory component), and advanced progressions. Supervised machine-learning models were built to predict the type of progression, using data collected directly at the first consultation, with some classifiers showing an accuracy of over 80%. However, it was difficult to predict patients with diffuse progression, and data balancing techniques were applied which, although they performed slightly worse overall, showed an improvement in this specific group of patients. The need for medical procedures varies according to the type of progression. It was calculated which procedures each cluster tends to need and studied whether creating specific classifiers for each of them would perform better in predicting these procedures when compared to a general classifier. Predictions were made in windows of 90, 180, and 365 days. Comparing the specialized classifiers with the general ones, inconclusive results were obtained at 90 days, but at 365 days, the specialized models showed better results in some procedures, such as predicting non-invasive ventilation and the need for a communication aid device. This project is a step towards a better understanding of ALS in order to contribute to the development of more personalized therapeutic strategies in the future.Tomás, Helena Isabel Aidos LopesMadeira, Sara Alexandra CordeiroRepositório da Universidade de LisboaSeguro, Afonso Manuel Tito Lopes2024-03-06T10:31:00Z202320232023-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10451/63205enginfo: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:RCAAP2024-03-11T01:20:11Zoai:repositorio.ul.pt:10451/63205Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:14:31.182751Repositório 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 Temporal unsupervised learning models to study ALS progression
title Temporal unsupervised learning models to study ALS progression
spellingShingle Temporal unsupervised learning models to study ALS progression
Seguro, Afonso Manuel Tito Lopes
Esclerose Lateral Amiotrofica
Aprendizagem Automática
Estratificação Temporal não-supervisionada
Procedimentos médicos ELA
Teses de mestrado - 2023
Departamento de Informática
title_short Temporal unsupervised learning models to study ALS progression
title_full Temporal unsupervised learning models to study ALS progression
title_fullStr Temporal unsupervised learning models to study ALS progression
title_full_unstemmed Temporal unsupervised learning models to study ALS progression
title_sort Temporal unsupervised learning models to study ALS progression
author Seguro, Afonso Manuel Tito Lopes
author_facet Seguro, Afonso Manuel Tito Lopes
author_role author
dc.contributor.none.fl_str_mv Tomás, Helena Isabel Aidos Lopes
Madeira, Sara Alexandra Cordeiro
Repositório da Universidade de Lisboa
dc.contributor.author.fl_str_mv Seguro, Afonso Manuel Tito Lopes
dc.subject.por.fl_str_mv Esclerose Lateral Amiotrofica
Aprendizagem Automática
Estratificação Temporal não-supervisionada
Procedimentos médicos ELA
Teses de mestrado - 2023
Departamento de Informática
topic Esclerose Lateral Amiotrofica
Aprendizagem Automática
Estratificação Temporal não-supervisionada
Procedimentos médicos ELA
Teses de mestrado - 2023
Departamento de Informática
description Tese de mestrado, Engenharia Informática, 2023, Universidade de Lisboa, Faculdade de Ciências
publishDate 2023
dc.date.none.fl_str_mv 2023
2023
2023-01-01T00:00:00Z
2024-03-06T10:31:00Z
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/10451/63205
url http://hdl.handle.net/10451/63205
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_ 1799137797764808704

Registros relacionados