Early Identification of Patients at Risk of Sepsis in a Hospital Environment
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Brazilian Archives of Biology and Technology |
Texto Completo: | http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132021000200223 |
Resumo: | Abstract Sepsis is a systematic response to an infectious disease, being a concerning factor because of the increase in the mortality ratio for every delayed hour in the identification and start of patient’s treatment. Studies that aim to identify sepsis early are valuable for the healthcare domain. Further, studies that propose machine learning-based models to identify sepsis risk are scarce for the Brazilian scenario. Hence, we propose the early identification of sepsis considering data from a Brazilian hospital. We developed a temporal series based on LSTM to predict sepsis in patients considering a three-day timestep. The patients were selected using both criteria, ICD-10, and qSOFA, where we supplemented qSOFA with the additional identification of words referring to infections in the clinical texts. Additionally, we tested a Random Forest classifier to classify patients with sepsis with a single timestep before the sepsis event, evaluating the most relevant features. We achieved an accuracy of 0.907, a sensitivity of 0.912, and a specificity of 0.971 when considering a three-day timestep with LSTM. The Random Forest classifier achieved an accuracy of 0.971, a sensitivity of 0.611, and a specificity of 0.998. The features age, blood glucose, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and admission days had the most influence over the algorithm classification, with age being the most relevant feature. We achieved satisfactory results compared with the literature considering a scenario of spaced measures and a high amount of missing data. |
id |
TECPAR-1_38986f55b8a63dd864fb4991dae7cc9f |
---|---|
oai_identifier_str |
oai:scielo:S1516-89132021000200223 |
network_acronym_str |
TECPAR-1 |
network_name_str |
Brazilian Archives of Biology and Technology |
repository_id_str |
|
spelling |
Early Identification of Patients at Risk of Sepsis in a Hospital Environmentsepsismachine learninghealthcareAbstract Sepsis is a systematic response to an infectious disease, being a concerning factor because of the increase in the mortality ratio for every delayed hour in the identification and start of patient’s treatment. Studies that aim to identify sepsis early are valuable for the healthcare domain. Further, studies that propose machine learning-based models to identify sepsis risk are scarce for the Brazilian scenario. Hence, we propose the early identification of sepsis considering data from a Brazilian hospital. We developed a temporal series based on LSTM to predict sepsis in patients considering a three-day timestep. The patients were selected using both criteria, ICD-10, and qSOFA, where we supplemented qSOFA with the additional identification of words referring to infections in the clinical texts. Additionally, we tested a Random Forest classifier to classify patients with sepsis with a single timestep before the sepsis event, evaluating the most relevant features. We achieved an accuracy of 0.907, a sensitivity of 0.912, and a specificity of 0.971 when considering a three-day timestep with LSTM. The Random Forest classifier achieved an accuracy of 0.971, a sensitivity of 0.611, and a specificity of 0.998. The features age, blood glucose, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and admission days had the most influence over the algorithm classification, with age being the most relevant feature. We achieved satisfactory results compared with the literature considering a scenario of spaced measures and a high amount of missing data.Instituto de Tecnologia do Paraná - Tecpar2021-01-01info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersiontext/htmlhttp://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132021000200223Brazilian Archives of Biology and Technology v.64 n.spe 2021reponame:Brazilian Archives of Biology and Technologyinstname:Instituto de Tecnologia do Paraná (Tecpar)instacron:TECPAR10.1590/1678-4324-75years-2021210142info:eu-repo/semantics/openAccessCesario,Everton OsneiGumiel,Yohan BonesckiMartins,Marcia Cristina MarinsDias,Viviane Maria de Carvalho HesselMoro,ClaudiaCarvalho,Deborah Ribeiroeng2021-11-17T00:00:00Zoai:scielo:S1516-89132021000200223Revistahttps://www.scielo.br/j/babt/https://old.scielo.br/oai/scielo-oai.phpbabt@tecpar.br||babt@tecpar.br1678-43241516-8913opendoar:2021-11-17T00:00Brazilian Archives of Biology and Technology - Instituto de Tecnologia do Paraná (Tecpar)false |
dc.title.none.fl_str_mv |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
title |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
spellingShingle |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment Cesario,Everton Osnei sepsis machine learning healthcare |
title_short |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
title_full |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
title_fullStr |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
title_full_unstemmed |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
title_sort |
Early Identification of Patients at Risk of Sepsis in a Hospital Environment |
author |
Cesario,Everton Osnei |
author_facet |
Cesario,Everton Osnei Gumiel,Yohan Bonescki Martins,Marcia Cristina Marins Dias,Viviane Maria de Carvalho Hessel Moro,Claudia Carvalho,Deborah Ribeiro |
author_role |
author |
author2 |
Gumiel,Yohan Bonescki Martins,Marcia Cristina Marins Dias,Viviane Maria de Carvalho Hessel Moro,Claudia Carvalho,Deborah Ribeiro |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Cesario,Everton Osnei Gumiel,Yohan Bonescki Martins,Marcia Cristina Marins Dias,Viviane Maria de Carvalho Hessel Moro,Claudia Carvalho,Deborah Ribeiro |
dc.subject.por.fl_str_mv |
sepsis machine learning healthcare |
topic |
sepsis machine learning healthcare |
description |
Abstract Sepsis is a systematic response to an infectious disease, being a concerning factor because of the increase in the mortality ratio for every delayed hour in the identification and start of patient’s treatment. Studies that aim to identify sepsis early are valuable for the healthcare domain. Further, studies that propose machine learning-based models to identify sepsis risk are scarce for the Brazilian scenario. Hence, we propose the early identification of sepsis considering data from a Brazilian hospital. We developed a temporal series based on LSTM to predict sepsis in patients considering a three-day timestep. The patients were selected using both criteria, ICD-10, and qSOFA, where we supplemented qSOFA with the additional identification of words referring to infections in the clinical texts. Additionally, we tested a Random Forest classifier to classify patients with sepsis with a single timestep before the sepsis event, evaluating the most relevant features. We achieved an accuracy of 0.907, a sensitivity of 0.912, and a specificity of 0.971 when considering a three-day timestep with LSTM. The Random Forest classifier achieved an accuracy of 0.971, a sensitivity of 0.611, and a specificity of 0.998. The features age, blood glucose, systolic blood pressure, diastolic blood pressure, heart rate, respiratory rate, and admission days had the most influence over the algorithm classification, with age being the most relevant feature. We achieved satisfactory results compared with the literature considering a scenario of spaced measures and a high amount of missing data. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 |
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=S1516-89132021000200223 |
url |
http://old.scielo.br/scielo.php?script=sci_arttext&pid=S1516-89132021000200223 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1590/1678-4324-75years-2021210142 |
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 de Tecnologia do Paraná - Tecpar |
publisher.none.fl_str_mv |
Instituto de Tecnologia do Paraná - Tecpar |
dc.source.none.fl_str_mv |
Brazilian Archives of Biology and Technology v.64 n.spe 2021 reponame:Brazilian Archives of Biology and Technology instname:Instituto de Tecnologia do Paraná (Tecpar) instacron:TECPAR |
instname_str |
Instituto de Tecnologia do Paraná (Tecpar) |
instacron_str |
TECPAR |
institution |
TECPAR |
reponame_str |
Brazilian Archives of Biology and Technology |
collection |
Brazilian Archives of Biology and Technology |
repository.name.fl_str_mv |
Brazilian Archives of Biology and Technology - Instituto de Tecnologia do Paraná (Tecpar) |
repository.mail.fl_str_mv |
babt@tecpar.br||babt@tecpar.br |
_version_ |
1750318280998912000 |