Publication:
Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study

Simple item page
dc.citedby2
dc.contributor.authorAbu-Samah A.en_US
dc.contributor.authorRazak N.N.A.en_US
dc.contributor.authorSuhaimi F.M.en_US
dc.contributor.authorJamaludin U.K.en_US
dc.contributor.authorChase J.G.en_US
dc.contributor.authorid56719596600en_US
dc.contributor.authorid37059587300en_US
dc.contributor.authorid36247893200en_US
dc.contributor.authorid55330889600en_US
dc.contributor.authorid35570524900en_US
dc.date.accessioned2023-05-29T07:30:01Z
dc.date.available2023-05-29T07:30:01Z
dc.date.issued2019
dc.descriptionBenchmarking; Decision support systems; Hospital data processing; Intensive care units; Patient treatment; Trees (mathematics); Blood glucose measurements; Classification precision; Discretization algorithms; Discretizations; Glycemic control; Performance prediction; Structure-learning; Variable selection; Bayesian networksen_US
dc.description.abstractPersonalized treatment in glycemic control (GC) is a visibly promising research area that requires improved mechanisms providing patient-specific procedures to enable complicated decision support. Available per-patient data must be more than written records, and be fully integrated in this personalization process. This article presents a process for relating the intensive care unit patients' demographic and admission data to their GC performance. With this objective, a probabilistic Bayesian network was chosen to provide more personalized decisions. As a case study, average daily blood glucose measurements were chosen as the interest target node in order to weigh GC that provides a reduced nursing workload. To test the idea, data from 482 patients, with nine variables from four Malaysian intensive care units with different controls were exploited. The identified steps crucial in building a dependable model are variable selection, continuous state discretization, and unsupervised structure learning. Using a multi-target node evaluation, a network with 80% mean overall classification precision was obtained with a normalized equal distance discretization algorithm and a maximum weight spanning tree technique. Meanwhile, the interest target node scored 90.39% precision. The results from this study, which are complemented with an evaluation of missing data, are proposed as a benchmark for using Bayesian networks in this type of application. � 2019 Institute of Electronics and Information Engineers. All rights reserved.en_US
dc.description.natureFinalen_US
dc.identifier.doi10.5573/IEIESPC.2019.8.3.202
dc.identifier.epage209
dc.identifier.issue3
dc.identifier.scopus2-s2.0-85068541334
dc.identifier.spage202
dc.identifier.urihttps://www.scopus.com/inward/record.uri?eid=2-s2.0-85068541334&doi=10.5573%2fIEIESPC.2019.8.3.202&partnerID=40&md5=9626ff963dbb29ecf9f895252e07d14d
dc.identifier.urihttps://irepository.uniten.edu.my/handle/123456789/24994
dc.identifier.volume8
dc.publisherInstitute of Electronics Engineers of Koreaen_US
dc.relation.ispartofAll Open Access, Green
dc.sourceScopus
dc.sourcetitleIEIE Transactions on Smart Processing and Computing
dc.titleTowards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control studyen_US
dc.typeArticleen_US
dspace.entity.typePublication
Files
Collections
SCOPUS