Length of stay in pediatric intensive care unit: prediction model
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Einstein (São Paulo) |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-45082020000100270 |
Resumo: | ABSTRACT Objective To propose a predictive model for the length of stay risk among children admitted to a pediatric intensive care unit based on demographic and clinical characteristics upon admission. Methods This was a retrospective cohort study conducted at a private and general hospital located in the municipality of Sao Paulo, Brazil. We used internal validation procedures and obtained an area under ROC curve for the to build of the predictive model. Results The mean hospital stay was 2 days. Predictive model resulted in a score that enabled the segmentation of hospital stay from 1 to 2 days, 3 to 4 days, and more than 4 days. The accuracy model from 3 to 4 days was 0.71 and model greater than 4 days was 0.69. The accuracy found for 3 to 4 days (65%) and greater than 4 days (66%) of hospital stay showed a chance of correctness, which was considering modest. Conclusion: Our results showed that low accuracy found in the predictive model did not enable the model to be exclusively adopted for decision-making or discharge planning. Predictive models of length of stay risk that consider variables of patients obtained only upon admission are limit, because they do not consider other characteristics present during hospitalization such as possible complications and adverse events, features that could impact negatively the accuracy of the proposed model. |
id |
IIEPAE-1_c25cde239207baa838b1f4ed9b360105 |
---|---|
oai_identifier_str |
oai:scielo:S1679-45082020000100270 |
network_acronym_str |
IIEPAE-1 |
network_name_str |
Einstein (São Paulo) |
repository_id_str |
|
spelling |
Length of stay in pediatric intensive care unit: prediction modelLengh of stayCritical careLogistic modelsForecastingHeath managementBeds/supply & distributionIntensive care units, pediatricABSTRACT Objective To propose a predictive model for the length of stay risk among children admitted to a pediatric intensive care unit based on demographic and clinical characteristics upon admission. Methods This was a retrospective cohort study conducted at a private and general hospital located in the municipality of Sao Paulo, Brazil. We used internal validation procedures and obtained an area under ROC curve for the to build of the predictive model. Results The mean hospital stay was 2 days. Predictive model resulted in a score that enabled the segmentation of hospital stay from 1 to 2 days, 3 to 4 days, and more than 4 days. The accuracy model from 3 to 4 days was 0.71 and model greater than 4 days was 0.69. The accuracy found for 3 to 4 days (65%) and greater than 4 days (66%) of hospital stay showed a chance of correctness, which was considering modest. Conclusion: Our results showed that low accuracy found in the predictive model did not enable the model to be exclusively adopted for decision-making or discharge planning. Predictive models of length of stay risk that consider variables of patients obtained only upon admission are limit, because they do not consider other characteristics present during hospitalization such as possible complications and adverse events, features that could impact negatively the accuracy of the proposed model.Instituto Israelita de Ensino e Pesquisa Albert Einstein2020-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-45082020000100270einstein (São Paulo) v.18 2020reponame:Einstein (São Paulo)instname:Instituto Israelita de Ensino e Pesquisa Albert Einstein (IIEPAE)instacron:IIEPAE10.31744/einstein_journal/2020ao5476info:eu-repo/semantics/openAccessBrandi,SimoneTroster,Eduardo JuanCunha,Mariana Lucas da Rochaeng2020-10-05T00:00:00Zoai:scielo:S1679-45082020000100270Revistahttps://journal.einstein.br/pt-br/ONGhttps://old.scielo.br/oai/scielo-oai.php||revista@einstein.br2317-63851679-4508opendoar:2020-10-05T00:00Einstein (São Paulo) - Instituto Israelita de Ensino e Pesquisa Albert Einstein (IIEPAE)false |
dc.title.none.fl_str_mv |
Length of stay in pediatric intensive care unit: prediction model |
title |
Length of stay in pediatric intensive care unit: prediction model |
spellingShingle |
Length of stay in pediatric intensive care unit: prediction model Brandi,Simone Lengh of stay Critical care Logistic models Forecasting Heath management Beds/supply & distribution Intensive care units, pediatric |
title_short |
Length of stay in pediatric intensive care unit: prediction model |
title_full |
Length of stay in pediatric intensive care unit: prediction model |
title_fullStr |
Length of stay in pediatric intensive care unit: prediction model |
title_full_unstemmed |
Length of stay in pediatric intensive care unit: prediction model |
title_sort |
Length of stay in pediatric intensive care unit: prediction model |
author |
Brandi,Simone |
author_facet |
Brandi,Simone Troster,Eduardo Juan Cunha,Mariana Lucas da Rocha |
author_role |
author |
author2 |
Troster,Eduardo Juan Cunha,Mariana Lucas da Rocha |
author2_role |
author author |
dc.contributor.author.fl_str_mv |
Brandi,Simone Troster,Eduardo Juan Cunha,Mariana Lucas da Rocha |
dc.subject.por.fl_str_mv |
Lengh of stay Critical care Logistic models Forecasting Heath management Beds/supply & distribution Intensive care units, pediatric |
topic |
Lengh of stay Critical care Logistic models Forecasting Heath management Beds/supply & distribution Intensive care units, pediatric |
description |
ABSTRACT Objective To propose a predictive model for the length of stay risk among children admitted to a pediatric intensive care unit based on demographic and clinical characteristics upon admission. Methods This was a retrospective cohort study conducted at a private and general hospital located in the municipality of Sao Paulo, Brazil. We used internal validation procedures and obtained an area under ROC curve for the to build of the predictive model. Results The mean hospital stay was 2 days. Predictive model resulted in a score that enabled the segmentation of hospital stay from 1 to 2 days, 3 to 4 days, and more than 4 days. The accuracy model from 3 to 4 days was 0.71 and model greater than 4 days was 0.69. The accuracy found for 3 to 4 days (65%) and greater than 4 days (66%) of hospital stay showed a chance of correctness, which was considering modest. Conclusion: Our results showed that low accuracy found in the predictive model did not enable the model to be exclusively adopted for decision-making or discharge planning. Predictive models of length of stay risk that consider variables of patients obtained only upon admission are limit, because they do not consider other characteristics present during hospitalization such as possible complications and adverse events, features that could impact negatively the accuracy of the proposed model. |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020-01-01 |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-45082020000100270 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1679-45082020000100270 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.31744/einstein_journal/2020ao5476 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
text/html |
dc.publisher.none.fl_str_mv |
Instituto Israelita de Ensino e Pesquisa Albert Einstein |
publisher.none.fl_str_mv |
Instituto Israelita de Ensino e Pesquisa Albert Einstein |
dc.source.none.fl_str_mv |
einstein (São Paulo) v.18 2020 reponame:Einstein (São Paulo) instname:Instituto Israelita de Ensino e Pesquisa Albert Einstein (IIEPAE) instacron:IIEPAE |
instname_str |
Instituto Israelita de Ensino e Pesquisa Albert Einstein (IIEPAE) |
instacron_str |
IIEPAE |
institution |
IIEPAE |
reponame_str |
Einstein (São Paulo) |
collection |
Einstein (São Paulo) |
repository.name.fl_str_mv |
Einstein (São Paulo) - Instituto Israelita de Ensino e Pesquisa Albert Einstein (IIEPAE) |
repository.mail.fl_str_mv |
||revista@einstein.br |
_version_ |
1752129910144499712 |