Developing a Bayesian network as a decision support system for evaluating patient with diabetes mellitus admitted to the intensive care unit – a proof of concepts

Rune Sejer Jakobsen
Department of Health Science and Technology, Aalborg University, Aalborg, Denmark

Ole Hejlesen
Department of Health Science and Technology, Aalborg University, Aalborg, Denmark

Mads Nibe Stausholm
Department of Health Science and Technology, Aalborg University, Aalborg, Denmark

Simon Lebech Cichosz
Department of Health Science and Technology, Aalborg University, Aalborg, Denmark

Ladda ner artikel

Ingår i: Proceedings from The 16th Scandinavian Conference on Health Informatics 2018, Aalborg, Denmark August 28–29, 2018

Linköping Electronic Conference Proceedings 151:12, s. 70-74

Visa mer +

Publicerad: 2018-08-24

ISBN: 978-91-7685-213-2

ISSN: 1650-3686 (tryckt), 1650-3740 (online)


Evidence is increasing about an unsatisfying performance from the existing non-disease-specific scoring systems in the intensive care unit (ICU). Evidence is furthermore increasing about differences in the mortality rate between diabetics and non-diabetics dependent on the level of blood glucose (BG), but few scoring systems include these variables in the assessment of the patients. 142,404 ICU admissions were included from the eICU database in the development of an unsupervised trained Bayesian Network (BN). The BN suggested that abnormalities in the level of BG should be associated with differences in the mortality rate between diabetics and non-diabetics. The BN showed promising predictive ability with an AUC on 0.86 for predicting death (sensitivity: 75.06, specificity: 78.40 %). 48.43 % of the length of stays (LOS) were correctly predicted. The results were slightly below the results from the APACHE IV scoring system but showed great ability of risk stratification. The BN showed a potential for predicting the patient outcome and might enable an improved method for risk stratifying the patients admitted to the ICU.


Intensive Care Unit, APACHE IV, Mortality, Diabetes Mellitus, Blood Glucose.


[1] Last JM. A Dictionary of Public Health. Oxford University Press. 2007.

[2] Dansk Intensiv Database. Årsrapport. 2016.

[3] Rapsang AG, and Shyam DC. Scoring systems in the intensive care unit: A Compendium. 2014.

[4] Vincent JL, and Moreno R. Clinical review: Scoring systems in the critically ill. 2010.

[5] Zimmerman JE, Kramer AA, McNair DS, and Malila FM Acute Physiology and Chronic Health Evaluation (APACHE) IV: Hospital mortality assessment for today’s critically illpatients. 2006.

[6] Naqvi IH, Mahmood K, Ziaullaha S, Kashif SM, and Sharif A. Better prognostic marker in ICU - APACHE II, SOFA or SAPS II!. 2016.

[7] Enfield K, Miller R, Rice T, Thompson BT, and Truwit J. Limited Utility of SOFA and APACHE II Prediction Models for ICU Triage in Pandemic Influenza. 2011.

[8] Saleh A, Ahmed M, and Mansoura AA.Comparison of the Mortality Prediction of Different ICU Scoring Systems (APACHE II and III, SAPS II, and SOFA) in Acute Respiratory Distress Syndrome Patients. 2016.

[9] Shahpori R, Stelfox HT, Doig CJ, and Boiteau PJE. Sequential Organ Failure Assessment in H1N1 pandemic planning. 2011.

[10] Bisbal M, Jouve E, Papazian L, Bourmont SD, Perrin G, Eon B, and Gainnier M. Effectiveness of SAPS III to predict hospital mortality for post-cardiac arrest patients. 2014.

[11] Rojek-Jarmula A, Hombach R, and Krzych LJ. APACHE II score cannot predict successful weaning from prolonged mechanical ventilation. 2017.

[12] Tayek CJ, and Tayek JA. Diabetes patients and nondiabetic patients intensive care unit and hospital mortality risks associated with sepsis. 2012.

[13] Cichosz SL, and Schaarup C. Hyperglycemia as a Predictor for Adverse Outcome in ICU Patients With and Without Diabetes. 2017.

[14] Carpenter DL, Gregg SR, Xu K, Buchman TG and C. M. Coopersmith. Prevalence and Impact of Unknown Diabetes in the ICU. 2015.

[15] Siegelaar SE, Devries JH, and Hoekstra JB. Patients with diabetes in the intensive care unit; not served by treatment, yet protected?. 2010.

[16] Duda RO, Hart PE, and Stork DG. Pattern Classification. 2001.

[17] Cho SJ, and Boeck PD. A Note on N in Bayesian Information Criterion for Item Response Models. 2018.

[18] Hugin Expert. Hugin Expert – Manual. 2017.

[19] Schneider J. Cross Validation. 1997.

[20] Barski L, Kezerle L, Zeller L, Zektser M, and Jotkowitz A. New approaches to the use of insulin in patients with diabetic ketoacidosis. 2013.

[21] Almdal T, Kjeldsen HC, Vestergaard H, and Sachs C. Sundhed.dk - Type 1 diabetes. 2016.

[22] Almdal T, Kjeldsen HC, Sanbæk A, Vestergaard H, and Sachs C. Sundhed.dk - Type 2 diabetes. 2015.

Citeringar i Crossref