A Bayesian network for early diagnosis of sepsis patients: A basis for a clinical decision support system

Eren Gultepe; Hien H Nguyen; Timothy E Albertson; Ilias Tagkopoulos

doi:10.1109/ICCABS.2012.6182636

A Bayesian network for early diagnosis of sepsis patients: A basis for a clinical decision support system

Eren Gultepe, Hien H Nguyen, Timothy E Albertson, Ilias Tagkopoulos

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

8 Scopus citations

Abstract

Sepsis is a severe medical condition caused by an inordinate immune response to an infection. Early detection of sepsis symptoms is important to prevent the progression into the more severe stages of the disease, which kills one in four it effects. Electronic medical records of 1492 patients containing 233 cases of sepsis were used in a clustering analysis to identify features that are indicative of sepsis and can be further used for training a Bayesian inference network. The Bayesian network was constructed using the systemic inflammatory response syndrome criteria, mean arterial pressure, and lactate levels for sepsis patients. The resulting network reveals a clear correlation between lactate levels and sepsis. Furthermore, it was shown that lactate levels may be predicative of the SIRS criteria. In this light, Bayesian networks of sepsis patients hold the promise of providing a clinical decision support system in the future.

Original language	English (US)
Title of host publication	2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012
DOIs	https://doi.org/10.1109/ICCABS.2012.6182636
State	Published - 2012
Event	2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012 - Las Vegas, NV, United States Duration: Feb 23 2012 → Feb 25 2012

Other

Other	2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012
Country	United States
City	Las Vegas, NV
Period	2/23/12 → 2/25/12

Keywords

Bayesian Network
CDSS
Clustering
Decisison support system
EMR
Sepsis
Septic shock
Severe Sepsis

ASJC Scopus subject areas

Biomedical Engineering
Applied Mathematics

Access to Document

10.1109/ICCABS.2012.6182636

Fingerprint Dive into the research topics of 'A Bayesian network for early diagnosis of sepsis patients: A basis for a clinical decision support system'. Together they form a unique fingerprint.

Cite this

A Bayesian network for early diagnosis of sepsis patients : A basis for a clinical decision support system. / Gultepe, Eren; Nguyen, Hien H ; Albertson, Timothy E; Tagkopoulos, Ilias.

2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012. 2012. 6182636.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Gultepe, E, Nguyen, HH , Albertson, TE & Tagkopoulos, I 2012, A Bayesian network for early diagnosis of sepsis patients: A basis for a clinical decision support system. in 2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012., 6182636, 2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012, Las Vegas, NV, United States, 2/23/12. https://doi.org/10.1109/ICCABS.2012.6182636

@inproceedings{7d2e057e27674197acf75f81903db33c,

title = "A Bayesian network for early diagnosis of sepsis patients: A basis for a clinical decision support system",

abstract = "Sepsis is a severe medical condition caused by an inordinate immune response to an infection. Early detection of sepsis symptoms is important to prevent the progression into the more severe stages of the disease, which kills one in four it effects. Electronic medical records of 1492 patients containing 233 cases of sepsis were used in a clustering analysis to identify features that are indicative of sepsis and can be further used for training a Bayesian inference network. The Bayesian network was constructed using the systemic inflammatory response syndrome criteria, mean arterial pressure, and lactate levels for sepsis patients. The resulting network reveals a clear correlation between lactate levels and sepsis. Furthermore, it was shown that lactate levels may be predicative of the SIRS criteria. In this light, Bayesian networks of sepsis patients hold the promise of providing a clinical decision support system in the future.",

keywords = "Bayesian Network, CDSS, Clustering, Decisison support system, EMR, Sepsis, Septic shock, Severe Sepsis",

author = "Eren Gultepe and Nguyen, {Hien H} and Albertson, {Timothy E} and Ilias Tagkopoulos",

year = "2012",

doi = "10.1109/ICCABS.2012.6182636",

language = "English (US)",

isbn = "9781467313216",

booktitle = "2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012",

note = "2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012 ; Conference date: 23-02-2012 Through 25-02-2012",

}

TY - GEN

T1 - A Bayesian network for early diagnosis of sepsis patients

T2 - 2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012

AU - Gultepe, Eren

AU - Nguyen, Hien H

AU - Albertson, Timothy E

AU - Tagkopoulos, Ilias

PY - 2012

Y1 - 2012

N2 - Sepsis is a severe medical condition caused by an inordinate immune response to an infection. Early detection of sepsis symptoms is important to prevent the progression into the more severe stages of the disease, which kills one in four it effects. Electronic medical records of 1492 patients containing 233 cases of sepsis were used in a clustering analysis to identify features that are indicative of sepsis and can be further used for training a Bayesian inference network. The Bayesian network was constructed using the systemic inflammatory response syndrome criteria, mean arterial pressure, and lactate levels for sepsis patients. The resulting network reveals a clear correlation between lactate levels and sepsis. Furthermore, it was shown that lactate levels may be predicative of the SIRS criteria. In this light, Bayesian networks of sepsis patients hold the promise of providing a clinical decision support system in the future.

AB - Sepsis is a severe medical condition caused by an inordinate immune response to an infection. Early detection of sepsis symptoms is important to prevent the progression into the more severe stages of the disease, which kills one in four it effects. Electronic medical records of 1492 patients containing 233 cases of sepsis were used in a clustering analysis to identify features that are indicative of sepsis and can be further used for training a Bayesian inference network. The Bayesian network was constructed using the systemic inflammatory response syndrome criteria, mean arterial pressure, and lactate levels for sepsis patients. The resulting network reveals a clear correlation between lactate levels and sepsis. Furthermore, it was shown that lactate levels may be predicative of the SIRS criteria. In this light, Bayesian networks of sepsis patients hold the promise of providing a clinical decision support system in the future.

KW - Bayesian Network

KW - CDSS

KW - Clustering

KW - Decisison support system

KW - EMR

KW - Sepsis

KW - Septic shock

KW - Severe Sepsis

UR - http://www.scopus.com/inward/record.url?scp=84860523054&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860523054&partnerID=8YFLogxK

U2 - 10.1109/ICCABS.2012.6182636

DO - 10.1109/ICCABS.2012.6182636

M3 - Conference contribution

AN - SCOPUS:84860523054

SN - 9781467313216

BT - 2012 IEEE 2nd International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2012

Y2 - 23 February 2012 through 25 February 2012

ER -