Probabilistic glycemic control decision support in ICU

Proof of concept using bayesian network

Asma Abu-Samah, Normy Norfiza Abdul Razak, Fatanah Mohamad Suhaimi, Ummu Kulthum Jamaludin, Azrina Md Ralib

Research output: Contribution to journalArticle

Abstract

Glycemic control in intensive care patients is complex in terms of patients’ response to care and treatment. The variability and the search for improved insulin therapy outcomes have led to the use of human physiology model based on per-patient metabolic condition to provide personalized automated recommendations. One of the most promising solutions for this is the STAR protocol, which is based on a clinically validated insulin-nutrition-glucose physiological model. However, this approach does not consider demographical background such as age, weight, height, and ethnicity. This article presents the extension to intensive care personalized solution by integrating per-patient demographical, and upon admission information to intensive care conditions to automate decision support for clinical staff. In this context, a virtual study was conducted on 210 retrospectives intensive care patients’ data. To provide a ground, the integration concept is presented roughly, but the details are given in terms of a proof of concept using Bayesian Network, linking the admission background and performance of the STAR control. The proof of concept shows 71.43% and 73.90% overall inference precision, and reliability, respectively, on the test dataset. With more data, improved Bayesian Network is believed to be reproduced. These results, nevertheless, points at the feasibility of the network to act as an effective classifier using intensive care units data, and glycemic control performance to be the basis of a probabilistic, personalized, and automated decision support in the intensive care units.

Original languageEnglish
Pages (from-to)61-69
Number of pages9
JournalJurnal Teknologi
Volume81
Issue number2
DOIs
Publication statusPublished - 01 Mar 2019

Fingerprint

Intensive care units
Bayesian networks
Insulin
Physiological models
Physiology
Nutrition
Glucose
Classifiers

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Abu-Samah, Asma ; Abdul Razak, Normy Norfiza ; Suhaimi, Fatanah Mohamad ; Jamaludin, Ummu Kulthum ; Ralib, Azrina Md. / Probabilistic glycemic control decision support in ICU : Proof of concept using bayesian network. In: Jurnal Teknologi. 2019 ; Vol. 81, No. 2. pp. 61-69.
@article{fa5b042ebd8f41f48936fd4f119b0ff2,
title = "Probabilistic glycemic control decision support in ICU: Proof of concept using bayesian network",
abstract = "Glycemic control in intensive care patients is complex in terms of patients’ response to care and treatment. The variability and the search for improved insulin therapy outcomes have led to the use of human physiology model based on per-patient metabolic condition to provide personalized automated recommendations. One of the most promising solutions for this is the STAR protocol, which is based on a clinically validated insulin-nutrition-glucose physiological model. However, this approach does not consider demographical background such as age, weight, height, and ethnicity. This article presents the extension to intensive care personalized solution by integrating per-patient demographical, and upon admission information to intensive care conditions to automate decision support for clinical staff. In this context, a virtual study was conducted on 210 retrospectives intensive care patients’ data. To provide a ground, the integration concept is presented roughly, but the details are given in terms of a proof of concept using Bayesian Network, linking the admission background and performance of the STAR control. The proof of concept shows 71.43{\%} and 73.90{\%} overall inference precision, and reliability, respectively, on the test dataset. With more data, improved Bayesian Network is believed to be reproduced. These results, nevertheless, points at the feasibility of the network to act as an effective classifier using intensive care units data, and glycemic control performance to be the basis of a probabilistic, personalized, and automated decision support in the intensive care units.",
author = "Asma Abu-Samah and {Abdul Razak}, {Normy Norfiza} and Suhaimi, {Fatanah Mohamad} and Jamaludin, {Ummu Kulthum} and Ralib, {Azrina Md}",
year = "2019",
month = "3",
day = "1",
doi = "10.11113/jt.v81.12721",
language = "English",
volume = "81",
pages = "61--69",
journal = "Jurnal Teknologi (Sciences and Engineering)",
issn = "0127-9696",
publisher = "Penerbit Universiti Teknologi Malaysia",
number = "2",

}

Probabilistic glycemic control decision support in ICU : Proof of concept using bayesian network. / Abu-Samah, Asma; Abdul Razak, Normy Norfiza; Suhaimi, Fatanah Mohamad; Jamaludin, Ummu Kulthum; Ralib, Azrina Md.

In: Jurnal Teknologi, Vol. 81, No. 2, 01.03.2019, p. 61-69.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Probabilistic glycemic control decision support in ICU

T2 - Proof of concept using bayesian network

AU - Abu-Samah, Asma

AU - Abdul Razak, Normy Norfiza

AU - Suhaimi, Fatanah Mohamad

AU - Jamaludin, Ummu Kulthum

AU - Ralib, Azrina Md

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Glycemic control in intensive care patients is complex in terms of patients’ response to care and treatment. The variability and the search for improved insulin therapy outcomes have led to the use of human physiology model based on per-patient metabolic condition to provide personalized automated recommendations. One of the most promising solutions for this is the STAR protocol, which is based on a clinically validated insulin-nutrition-glucose physiological model. However, this approach does not consider demographical background such as age, weight, height, and ethnicity. This article presents the extension to intensive care personalized solution by integrating per-patient demographical, and upon admission information to intensive care conditions to automate decision support for clinical staff. In this context, a virtual study was conducted on 210 retrospectives intensive care patients’ data. To provide a ground, the integration concept is presented roughly, but the details are given in terms of a proof of concept using Bayesian Network, linking the admission background and performance of the STAR control. The proof of concept shows 71.43% and 73.90% overall inference precision, and reliability, respectively, on the test dataset. With more data, improved Bayesian Network is believed to be reproduced. These results, nevertheless, points at the feasibility of the network to act as an effective classifier using intensive care units data, and glycemic control performance to be the basis of a probabilistic, personalized, and automated decision support in the intensive care units.

AB - Glycemic control in intensive care patients is complex in terms of patients’ response to care and treatment. The variability and the search for improved insulin therapy outcomes have led to the use of human physiology model based on per-patient metabolic condition to provide personalized automated recommendations. One of the most promising solutions for this is the STAR protocol, which is based on a clinically validated insulin-nutrition-glucose physiological model. However, this approach does not consider demographical background such as age, weight, height, and ethnicity. This article presents the extension to intensive care personalized solution by integrating per-patient demographical, and upon admission information to intensive care conditions to automate decision support for clinical staff. In this context, a virtual study was conducted on 210 retrospectives intensive care patients’ data. To provide a ground, the integration concept is presented roughly, but the details are given in terms of a proof of concept using Bayesian Network, linking the admission background and performance of the STAR control. The proof of concept shows 71.43% and 73.90% overall inference precision, and reliability, respectively, on the test dataset. With more data, improved Bayesian Network is believed to be reproduced. These results, nevertheless, points at the feasibility of the network to act as an effective classifier using intensive care units data, and glycemic control performance to be the basis of a probabilistic, personalized, and automated decision support in the intensive care units.

UR - http://www.scopus.com/inward/record.url?scp=85062991963&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062991963&partnerID=8YFLogxK

U2 - 10.11113/jt.v81.12721

DO - 10.11113/jt.v81.12721

M3 - Article

VL - 81

SP - 61

EP - 69

JO - Jurnal Teknologi (Sciences and Engineering)

JF - Jurnal Teknologi (Sciences and Engineering)

SN - 0127-9696

IS - 2

ER -