Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables

Bibliographic Details
Main Author: Oliveira, Sérgio Manuel Costa
Publication Date: 2015
Other Authors: Portela, Filipe, Santos, Manuel Filipe, Machado, José, Abelha, António, Silva, Álvaro, Rua, Fernando
Language: eng
Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
Download full: http://hdl.handle.net/1822/39279
Summary: Predicting barotrauma occurrence in intensive care patients is a difficult task. Data Mining modelling can contribute significantly to the identification of patients who will suffer barotrauma. This can be achieved by grouping patient data, considering a set of variables collected from ventilators directly related with barotrauma, and identifying similarities among them. For clustering have been considered k-means and k-medoids algortihms (Partitioning Around Medoids). The best model induced presented a Davies-Bouldin Index of 0.64. This model identifies the variables that have more similarity among the variables monitored by the ventilators and the occurrence of barotrauma.
id RCAP_511d2b5d4e11d76f856376cc05c47db4
oai_identifier_str oai:repositorium.sdum.uminho.pt:1822/39279
network_acronym_str RCAP
network_name_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository_id_str https://opendoar.ac.uk/repository/7160
spelling Clustering barotrauma patients in ICU–A data mining based approach using ventilator variablesBarotraumaPlateau pressureIntensive medicineData miningClusteringSimilarityCorrelationScience & TechnologyPredicting barotrauma occurrence in intensive care patients is a difficult task. Data Mining modelling can contribute significantly to the identification of patients who will suffer barotrauma. This can be achieved by grouping patient data, considering a set of variables collected from ventilators directly related with barotrauma, and identifying similarities among them. For clustering have been considered k-means and k-medoids algortihms (Partitioning Around Medoids). The best model induced presented a Davies-Bouldin Index of 0.64. This model identifies the variables that have more similarity among the variables monitored by the ventilators and the occurrence of barotrauma.SpringerUniversidade do MinhoOliveira, Sérgio Manuel CostaPortela, FilipeSantos, Manuel FilipeMachado, JoséAbelha, AntónioSilva, ÁlvaroRua, Fernando20152015-01-01T00:00:00Zconference paperinfo:eu-repo/semantics/publishedVersionapplication/pdfhttp://hdl.handle.net/1822/39279eng978-3-319-23484-70302-974310.1007/978-3-319-23485-4_13http://link.springer.com/chapter/10.1007%2F978-3-319-23485-4_13info:eu-repo/semantics/openAccessreponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiainstacron:RCAAP2024-05-11T07:35:46Zoai:repositorium.sdum.uminho.pt:1822/39279Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireinfo@rcaap.ptopendoar:https://opendoar.ac.uk/repository/71602025-05-28T16:32:47.539444Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologiafalse
dc.title.none.fl_str_mv Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
title Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
spellingShingle Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
Oliveira, Sérgio Manuel Costa
Barotrauma
Plateau pressure
Intensive medicine
Data mining
Clustering
Similarity
Correlation
Science & Technology
title_short Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
title_full Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
title_fullStr Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
title_full_unstemmed Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
title_sort Clustering barotrauma patients in ICU–A data mining based approach using ventilator variables
author Oliveira, Sérgio Manuel Costa
author_facet Oliveira, Sérgio Manuel Costa
Portela, Filipe
Santos, Manuel Filipe
Machado, José
Abelha, António
Silva, Álvaro
Rua, Fernando
author_role author
author2 Portela, Filipe
Santos, Manuel Filipe
Machado, José
Abelha, António
Silva, Álvaro
Rua, Fernando
author2_role author
author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade do Minho
dc.contributor.author.fl_str_mv Oliveira, Sérgio Manuel Costa
Portela, Filipe
Santos, Manuel Filipe
Machado, José
Abelha, António
Silva, Álvaro
Rua, Fernando
dc.subject.por.fl_str_mv Barotrauma
Plateau pressure
Intensive medicine
Data mining
Clustering
Similarity
Correlation
Science & Technology
topic Barotrauma
Plateau pressure
Intensive medicine
Data mining
Clustering
Similarity
Correlation
Science & Technology
description Predicting barotrauma occurrence in intensive care patients is a difficult task. Data Mining modelling can contribute significantly to the identification of patients who will suffer barotrauma. This can be achieved by grouping patient data, considering a set of variables collected from ventilators directly related with barotrauma, and identifying similarities among them. For clustering have been considered k-means and k-medoids algortihms (Partitioning Around Medoids). The best model induced presented a Davies-Bouldin Index of 0.64. This model identifies the variables that have more similarity among the variables monitored by the ventilators and the occurrence of barotrauma.
publishDate 2015
dc.date.none.fl_str_mv 2015
2015-01-01T00:00:00Z
dc.type.driver.fl_str_mv conference paper
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://hdl.handle.net/1822/39279
url http://hdl.handle.net/1822/39279
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 978-3-319-23484-7
0302-9743
10.1007/978-3-319-23485-4_13
http://link.springer.com/chapter/10.1007%2F978-3-319-23485-4_13
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.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
instname:FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron:RCAAP
instname_str FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
instacron_str RCAAP
institution RCAAP
reponame_str Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
collection Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
repository.name.fl_str_mv Repositórios Científicos de Acesso Aberto de Portugal (RCAAP) - FCCN, serviços digitais da FCT – Fundação para a Ciência e a Tecnologia
repository.mail.fl_str_mv info@rcaap.pt
_version_ 1833596013866123264

Similar Items