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

Personalized 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 personali...

Full description

Saved in:
Bibliographic Details
Main Authors: Abu-Samah, A., Razak, N.N.A., Suhaimi, F.M., Jamaludin, U.K., Chase, J.G.
Format: Article
Language:English
Published: 2020
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uniten.dspace-13267
record_format dspace
spelling my.uniten.dspace-132672020-03-16T07:13:28Z Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study Abu-Samah, A. Razak, N.N.A. Suhaimi, F.M. Jamaludin, U.K. Chase, J.G. Personalized 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. 2020-02-03T03:31:26Z 2020-02-03T03:31:26Z 2019 Article 10.5573/IEIESPC.2019.8.3.202 en
institution Universiti Tenaga Nasional
building UNITEN Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tenaga Nasional
content_source UNITEN Institutional Repository
url_provider http://dspace.uniten.edu.my/
language English
description Personalized 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.
format Article
author Abu-Samah, A.
Razak, N.N.A.
Suhaimi, F.M.
Jamaludin, U.K.
Chase, J.G.
spellingShingle Abu-Samah, A.
Razak, N.N.A.
Suhaimi, F.M.
Jamaludin, U.K.
Chase, J.G.
Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
author_facet Abu-Samah, A.
Razak, N.N.A.
Suhaimi, F.M.
Jamaludin, U.K.
Chase, J.G.
author_sort Abu-Samah, A.
title Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
title_short Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
title_full Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
title_fullStr Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
title_full_unstemmed Towards personalized intensive care decision support using a Bayesian network: A multicenter glycemic control study
title_sort towards personalized intensive care decision support using a bayesian network: a multicenter glycemic control study
publishDate 2020
_version_ 1662758838460219392
score 13.214268