A Markov model to describe daily changes in organ failure for patients at the ICU

Linda Peelen; Niels Peek; Nicolette F. De Keizer; Evert De Jonge; Robert J. Bosman

A Markov model to describe daily changes in organ failure for patients at the ICU

Linda Peelen^*, Niels Peek, Nicolette F. De Keizer, Evert De Jonge, Robert J. Bosman

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

1 Citation (Scopus)

Abstract

As the support and stabilization of organ function is a major goal of treatment in the Intensive Care Unit (ICU), changes in the function of organ systems are an important indicator of the progression of the disease and recovery. This paper presents how to construct a model that describes changes in organ failure of ICU patients on a day-to-day basis. The model is based on the daily Sequential Organ Failure Assessment (SOFA) scores for six organ systems and predicts, for each of these organ systems, whether failure or recovery is due on the next day, using six logistic regression equations. The joint set of equations, extended with equations for predicting ICU discharge and death, constitutes a firstorder multivariate Markov model. We applied the procedure on a dataset and found that most types of organ failure are highly persistent.

Original language	English
Title of host publication	Ubiquity: Technologies for Better Health in Aging Societies - Proceedings of MIE 2006
Pages	555-560
Number of pages	6
Volume	124
Publication status	Published - 2006
Event	20th International Congress of the European Federation for Medical Informatics, MIE 2006 - Maastricht, Netherlands Duration: 27 Aug 2006 → 30 Aug 2006

Conference

Conference	20th International Congress of the European Federation for Medical Informatics, MIE 2006
Country/Territory	Netherlands
City	Maastricht
Period	27/08/06 → 30/08/06

Keywords

Decision-support
Intensive Care
Multivariate Markov Model
Prognosis
SOFA score

Cite this

@inproceedings{c2b05ea532614229b58ee9ced4407e7b,

title = "A Markov model to describe daily changes in organ failure for patients at the ICU",

abstract = "As the support and stabilization of organ function is a major goal of treatment in the Intensive Care Unit (ICU), changes in the function of organ systems are an important indicator of the progression of the disease and recovery. This paper presents how to construct a model that describes changes in organ failure of ICU patients on a day-to-day basis. The model is based on the daily Sequential Organ Failure Assessment (SOFA) scores for six organ systems and predicts, for each of these organ systems, whether failure or recovery is due on the next day, using six logistic regression equations. The joint set of equations, extended with equations for predicting ICU discharge and death, constitutes a firstorder multivariate Markov model. We applied the procedure on a dataset and found that most types of organ failure are highly persistent.",

keywords = "Decision-support, Intensive Care, Multivariate Markov Model, Prognosis, SOFA score",

author = "Linda Peelen and Niels Peek and {De Keizer}, {Nicolette F.} and {De Jonge}, Evert and Bosman, {Robert J.}",

year = "2006",

language = "English",

isbn = "1586036475",

volume = "124",

pages = "555--560",

booktitle = "Ubiquity: Technologies for Better Health in Aging Societies - Proceedings of MIE 2006",

note = "20th International Congress of the European Federation for Medical Informatics, MIE 2006 ; Conference date: 27-08-2006 Through 30-08-2006",

}

Peelen, L, Peek, N, De Keizer, NF, De Jonge, E & Bosman, RJ 2006, A Markov model to describe daily changes in organ failure for patients at the ICU. in Ubiquity: Technologies for Better Health in Aging Societies - Proceedings of MIE 2006. vol. 124, pp. 555-560, 20th International Congress of the European Federation for Medical Informatics, MIE 2006, Maastricht, Netherlands, 27/08/06.

A Markov model to describe daily changes in organ failure for patients at the ICU. / Peelen, Linda; Peek, Niels; De Keizer, Nicolette F. et al.
Ubiquity: Technologies for Better Health in Aging Societies - Proceedings of MIE 2006. Vol. 124 2006. p. 555-560.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - A Markov model to describe daily changes in organ failure for patients at the ICU

AU - Peelen, Linda

AU - Peek, Niels

AU - De Keizer, Nicolette F.

AU - De Jonge, Evert

AU - Bosman, Robert J.

PY - 2006

Y1 - 2006

N2 - As the support and stabilization of organ function is a major goal of treatment in the Intensive Care Unit (ICU), changes in the function of organ systems are an important indicator of the progression of the disease and recovery. This paper presents how to construct a model that describes changes in organ failure of ICU patients on a day-to-day basis. The model is based on the daily Sequential Organ Failure Assessment (SOFA) scores for six organ systems and predicts, for each of these organ systems, whether failure or recovery is due on the next day, using six logistic regression equations. The joint set of equations, extended with equations for predicting ICU discharge and death, constitutes a firstorder multivariate Markov model. We applied the procedure on a dataset and found that most types of organ failure are highly persistent.

AB - As the support and stabilization of organ function is a major goal of treatment in the Intensive Care Unit (ICU), changes in the function of organ systems are an important indicator of the progression of the disease and recovery. This paper presents how to construct a model that describes changes in organ failure of ICU patients on a day-to-day basis. The model is based on the daily Sequential Organ Failure Assessment (SOFA) scores for six organ systems and predicts, for each of these organ systems, whether failure or recovery is due on the next day, using six logistic regression equations. The joint set of equations, extended with equations for predicting ICU discharge and death, constitutes a firstorder multivariate Markov model. We applied the procedure on a dataset and found that most types of organ failure are highly persistent.

KW - Decision-support

KW - Intensive Care

KW - Multivariate Markov Model

KW - Prognosis

KW - SOFA score

UR - http://www.scopus.com/inward/record.url?scp=39049187672&partnerID=8YFLogxK

M3 - Conference contribution

C2 - 17108576

AN - SCOPUS:39049187672

SN - 1586036475

SN - 9781586036478

VL - 124

SP - 555

EP - 560

BT - Ubiquity: Technologies for Better Health in Aging Societies - Proceedings of MIE 2006

T2 - 20th International Congress of the European Federation for Medical Informatics, MIE 2006

Y2 - 27 August 2006 through 30 August 2006

ER -

A Markov model to describe daily changes in organ failure for patients at the ICU

Abstract

Conference

Keywords

Other files and links

Fingerprint

Cite this