Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Tipo de documento: | Trabalho de conclusão de curso |
Idioma: | por |
Título da fonte: | Repositório Institucional da UFS |
Texto Completo: | https://ri.ufs.br/handle/riufs/6727 |
Resumo: | One commonly observed phenomenon in health plans is the distribution of costs in such a way that a small portion (less than 5%) of the population accounts for a large portion (more than two thirds) of expenditure. In this way, the objective of this work is to explain the health sector as a whole, as well as to obtain a logistic model of prediction that can classify the beneficiaries of a supplementary healthcare provider, with a focus on those with higher healthcare costs. This paper addresses the problem of how to optimize the management of health care costs with supplementary health through the identification of beneficiaries who are more likely to belong to this small group of high costs. The logistic regression technique was applied to a sample of 42 thousand beneficiaries of a large health plan operator (150 thousand patients) from Brazil in order to group patients according to their respective expenditures in 2013, from their care costs in the previous year and age. The database used in the study comprises a total of 42 variables, 41 of which are independent based on the information of sex, age and care use in 2012 and 1 dependent variable (cost of care in 2013). The beneficiaries were classified as low, medium and high cost users according to their care costs. The logistic method presented a 96.6% accuracy in the sample considered, but considering the target public (high cost clients) the method presented difficulties in identifying these beneficiaries, correctly predicting 13% of these clients. The result obtained by the logistic model obtained a good accuracy due to the number of correct predictions of the low cost beneficiaries and showed a considerable prediction for the individuals of high cost, since those of high cost are of difficult prediction. |
id |
UFS-2_a076766299317287e16fe6b6239f7ffa |
---|---|
oai_identifier_str |
oai:ufs.br:riufs/6727 |
network_acronym_str |
UFS-2 |
network_name_str |
Repositório Institucional da UFS |
repository_id_str |
|
spelling |
Aquino, Luana Ramos deSá, Marcelo Coelho de2017-10-16T13:10:43Z2017-10-16T13:10:43Z2017https://ri.ufs.br/handle/riufs/6727One commonly observed phenomenon in health plans is the distribution of costs in such a way that a small portion (less than 5%) of the population accounts for a large portion (more than two thirds) of expenditure. In this way, the objective of this work is to explain the health sector as a whole, as well as to obtain a logistic model of prediction that can classify the beneficiaries of a supplementary healthcare provider, with a focus on those with higher healthcare costs. This paper addresses the problem of how to optimize the management of health care costs with supplementary health through the identification of beneficiaries who are more likely to belong to this small group of high costs. The logistic regression technique was applied to a sample of 42 thousand beneficiaries of a large health plan operator (150 thousand patients) from Brazil in order to group patients according to their respective expenditures in 2013, from their care costs in the previous year and age. The database used in the study comprises a total of 42 variables, 41 of which are independent based on the information of sex, age and care use in 2012 and 1 dependent variable (cost of care in 2013). The beneficiaries were classified as low, medium and high cost users according to their care costs. The logistic method presented a 96.6% accuracy in the sample considered, but considering the target public (high cost clients) the method presented difficulties in identifying these beneficiaries, correctly predicting 13% of these clients. The result obtained by the logistic model obtained a good accuracy due to the number of correct predictions of the low cost beneficiaries and showed a considerable prediction for the individuals of high cost, since those of high cost are of difficult prediction.Um fenômeno comumente observado em planos de saúde é a distribuição dos custos de tal forma que uma pequena parcela (menos de 5%) da população é responsável por uma grande parte (mais que dois terços) das despesas. Dessa maneira, o trabalho objetiva explanar a cerca do setor de saúde suplementar, como também obter um modelo logístico de predição que possa classificar os beneficiários de uma operadora de saúde suplementar, com enfoque nos que possuam maiores custos assistenciais. O presente trabalho aborda o problema de como otimizar a gestão dos custos assistenciais com saúde suplementar através da identificação de beneficiários com uma maior probabilidade de pertencerem a esse pequeno grupo de elevados custos. A técnica de regressão logística foi aplicada a uma amostra com 42 mil beneficiários de uma operadora de plano de saúde de grande porte (150 mil pacientes) do Brasil com o intuito de agrupar os pacientes de acordo com os respectivos gastos em 2013, a partir de seus custos assistenciais no ano anterior e idade. A base de dados utilizada no estudo compreende um total de 42 variáveis, sendo 41 independentes com base nas informações de sexo, idade e utilização assistencial ocorrida em 2012 e 1 variável dependente (custo assistencial em 2013). Os beneficiários foram classificados como usuários de baixo, médio e alto custo de acordo com os seus custos assistenciais. O método logístico apresentou 96,6% de acerto na amostra considerada, porém considerando o público alvo (clientes de alto custo) o método apresentou dificuldade na identificação desses beneficiários, prevendo corretamente 13% desses clientes. O resultado obtido pelo modelo logístico obteve uma boa acurácia devido ao número de acertos na predição dos beneficiários de baixo custo e mostrou uma considerável predição para os indivíduos de alto custo, visto que os de alto custo são de difícil predição.São Cristóvão, SEporCiências atuariaisEnsino de estatísticaActuarial scienceTeaching statisticsOUTROS::CIÊNCIAS ATUARIAISAnálise de regressão logística para predição de custos assistenciais no setor de saúde suplementarLogistic regression analysis to predict healthcare costs in the supplementary health sectorinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bachelorThesisUniversidade Federal de SergipeDECAT - Departamento de Estatística e Ciências Atuariais – Ciências Atuariais – São Cristóvão – Presencialreponame:Repositório Institucional da UFSinstname:Universidade Federal de Sergipe (UFS)instacron:UFSinfo:eu-repo/semantics/openAccessLICENSElicense.txtlicense.txttext/plain; charset=utf-81475https://ri.ufs.br/jspui/bitstream/riufs/6727/1/license.txt098cbbf65c2c15e1fb2e49c5d306a44cMD51ORIGINALLuana Ramos de Aquino.pdfLuana Ramos de Aquino.pdfapplication/pdf1052334https://ri.ufs.br/jspui/bitstream/riufs/6727/2/Luana%20Ramos%20de%20Aquino.pdfb77b7f6703022a1121e87df22a2dc887MD52TEXTLuana Ramos de Aquino.pdf.txtLuana Ramos de Aquino.pdf.txtExtracted texttext/plain99072https://ri.ufs.br/jspui/bitstream/riufs/6727/3/Luana%20Ramos%20de%20Aquino.pdf.txtb400545a4c0fe36f8f6696a4a5116dadMD53THUMBNAILLuana Ramos de Aquino.pdf.jpgLuana Ramos de Aquino.pdf.jpgGenerated Thumbnailimage/jpeg1236https://ri.ufs.br/jspui/bitstream/riufs/6727/4/Luana%20Ramos%20de%20Aquino.pdf.jpg80976a894a1c61342056a20b897c395eMD54riufs/67272018-09-13 19:23:02.273oai:ufs.br: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Repositório InstitucionalPUBhttps://ri.ufs.br/oai/requestrepositorio@academico.ufs.bropendoar:2018-09-13T22:23:02Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS)false |
dc.title.pt_BR.fl_str_mv |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
dc.title.alternative.eng.fl_str_mv |
Logistic regression analysis to predict healthcare costs in the supplementary health sector |
title |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
spellingShingle |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar Aquino, Luana Ramos de Ciências atuariais Ensino de estatística Actuarial science Teaching statistics OUTROS::CIÊNCIAS ATUARIAIS |
title_short |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
title_full |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
title_fullStr |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
title_full_unstemmed |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
title_sort |
Análise de regressão logística para predição de custos assistenciais no setor de saúde suplementar |
author |
Aquino, Luana Ramos de |
author_facet |
Aquino, Luana Ramos de |
author_role |
author |
dc.contributor.author.fl_str_mv |
Aquino, Luana Ramos de |
dc.contributor.advisor1.fl_str_mv |
Sá, Marcelo Coelho de |
contributor_str_mv |
Sá, Marcelo Coelho de |
dc.subject.por.fl_str_mv |
Ciências atuariais Ensino de estatística |
topic |
Ciências atuariais Ensino de estatística Actuarial science Teaching statistics OUTROS::CIÊNCIAS ATUARIAIS |
dc.subject.eng.fl_str_mv |
Actuarial science Teaching statistics |
dc.subject.cnpq.fl_str_mv |
OUTROS::CIÊNCIAS ATUARIAIS |
description |
One commonly observed phenomenon in health plans is the distribution of costs in such a way that a small portion (less than 5%) of the population accounts for a large portion (more than two thirds) of expenditure. In this way, the objective of this work is to explain the health sector as a whole, as well as to obtain a logistic model of prediction that can classify the beneficiaries of a supplementary healthcare provider, with a focus on those with higher healthcare costs. This paper addresses the problem of how to optimize the management of health care costs with supplementary health through the identification of beneficiaries who are more likely to belong to this small group of high costs. The logistic regression technique was applied to a sample of 42 thousand beneficiaries of a large health plan operator (150 thousand patients) from Brazil in order to group patients according to their respective expenditures in 2013, from their care costs in the previous year and age. The database used in the study comprises a total of 42 variables, 41 of which are independent based on the information of sex, age and care use in 2012 and 1 dependent variable (cost of care in 2013). The beneficiaries were classified as low, medium and high cost users according to their care costs. The logistic method presented a 96.6% accuracy in the sample considered, but considering the target public (high cost clients) the method presented difficulties in identifying these beneficiaries, correctly predicting 13% of these clients. The result obtained by the logistic model obtained a good accuracy due to the number of correct predictions of the low cost beneficiaries and showed a considerable prediction for the individuals of high cost, since those of high cost are of difficult prediction. |
publishDate |
2017 |
dc.date.accessioned.fl_str_mv |
2017-10-16T13:10:43Z |
dc.date.available.fl_str_mv |
2017-10-16T13:10:43Z |
dc.date.issued.fl_str_mv |
2017 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
format |
bachelorThesis |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://ri.ufs.br/handle/riufs/6727 |
url |
https://ri.ufs.br/handle/riufs/6727 |
dc.language.iso.fl_str_mv |
por |
language |
por |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.initials.fl_str_mv |
Universidade Federal de Sergipe |
dc.publisher.department.fl_str_mv |
DECAT - Departamento de Estatística e Ciências Atuariais – Ciências Atuariais – São Cristóvão – Presencial |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFS instname:Universidade Federal de Sergipe (UFS) instacron:UFS |
instname_str |
Universidade Federal de Sergipe (UFS) |
instacron_str |
UFS |
institution |
UFS |
reponame_str |
Repositório Institucional da UFS |
collection |
Repositório Institucional da UFS |
bitstream.url.fl_str_mv |
https://ri.ufs.br/jspui/bitstream/riufs/6727/1/license.txt https://ri.ufs.br/jspui/bitstream/riufs/6727/2/Luana%20Ramos%20de%20Aquino.pdf https://ri.ufs.br/jspui/bitstream/riufs/6727/3/Luana%20Ramos%20de%20Aquino.pdf.txt https://ri.ufs.br/jspui/bitstream/riufs/6727/4/Luana%20Ramos%20de%20Aquino.pdf.jpg |
bitstream.checksum.fl_str_mv |
098cbbf65c2c15e1fb2e49c5d306a44c b77b7f6703022a1121e87df22a2dc887 b400545a4c0fe36f8f6696a4a5116dad 80976a894a1c61342056a20b897c395e |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFS - Universidade Federal de Sergipe (UFS) |
repository.mail.fl_str_mv |
repositorio@academico.ufs.br |
_version_ |
1802110731908284416 |