Predicting healthcare high-cost users using data mining methods

Detalhes bibliográficos
Autor(a) principal: Pantaleão, Bernardo Neves
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/10362/134138
Resumo: Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
id RCAP_a665bd21def1b289f91b14f544567fd4
oai_identifier_str oai:run.unl.pt:10362/134138
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling Predicting healthcare high-cost users using data mining methodsHealthcare CostsCosts PredictionHealth ManagementPredictive MethodsData MiningDissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business IntelligenceThe increase in healthcare costs is, perhaps, one of the most important issues that governments and organizations face nowadays. An ageing population and technological advancements are the key reasons for this phenomenon. In this scenario, proactive measures are very important. This work aimed to improve the effectiveness of the prevention by helping the identification of the most probable high-cost users of health services in future years. Data from 2015 to 2019 of approximately 30,000 Central Bank of Brazil’s Health Program’s enrollees were used to train, validate and test four types of models, considering the kind of high-cost users (simple or cost-bloomers, i.e., non-high-cost in previous periods) and the time-span between predictors and the dependent variable (none or one year), an innovation suggested by other authors. Different percentual cut-off points to define highcost were used, and up to 67% of high-risk users’ expenses could be correctly captured. Results confirmed the importance of previous costs data for this kind of prediction and showed that costbloomers and one-year time-span approaches reach good performance, creating opportunities to improve users’ health outcomes while contributing to the fiscal sustainability of private and public health systems.Henriques, Roberto André PereiraRUNPantaleão, Bernardo Neves2022-03-09T17:46:36Z2022-01-262022-01-26T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10362/134138TID:202959830enginfo: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:RCAAP2024-03-11T05:12:35Zoai:run.unl.pt:10362/134138Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T03:47:59.907154Repositório 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 Predicting healthcare high-cost users using data mining methods
title Predicting healthcare high-cost users using data mining methods
spellingShingle Predicting healthcare high-cost users using data mining methods
Pantaleão, Bernardo Neves
Healthcare Costs
Costs Prediction
Health Management
Predictive Methods
Data Mining
title_short Predicting healthcare high-cost users using data mining methods
title_full Predicting healthcare high-cost users using data mining methods
title_fullStr Predicting healthcare high-cost users using data mining methods
title_full_unstemmed Predicting healthcare high-cost users using data mining methods
title_sort Predicting healthcare high-cost users using data mining methods
author Pantaleão, Bernardo Neves
author_facet Pantaleão, Bernardo Neves
author_role author
dc.contributor.none.fl_str_mv Henriques, Roberto André Pereira
RUN
dc.contributor.author.fl_str_mv Pantaleão, Bernardo Neves
dc.subject.por.fl_str_mv Healthcare Costs
Costs Prediction
Health Management
Predictive Methods
Data Mining
topic Healthcare Costs
Costs Prediction
Health Management
Predictive Methods
Data Mining
description Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
publishDate 2022
dc.date.none.fl_str_mv 2022-03-09T17:46:36Z
2022-01-26
2022-01-26T00:00:00Z
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/10362/134138
TID:202959830
url http://hdl.handle.net/10362/134138
identifier_str_mv TID:202959830
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_ 1799138081594408960

Registros relacionados