Bayesian networks for patient monitoring

C. Berzuini, R. Bellazzi, S. Quaglini, D. J. Spiegelhalter

Research output: Contribution to journalArticle

Abstract

We consider a Bayesian statistical approach to model-based prediction of a future patient's response to a therapy, suitable in a wide range of clinical monitoring applications, especially when the observations made on the pathophysiological process of interest are imprecise and sporadic. Potential areas of application range from the predictive control of drug delivery to the management of chronic diseases. A distinctive characteristic of the proposed method is the capability of learning from a database of past patients, by explicitly modeling inter-subject variability of the unknown model parameters, and at an individual's level, by periodic updating of patient-specific parameter estimates on the basis of the accumulating data. By combining information about the population and information contained in the data of the specific patient we improve patient-specific forecasts. In order to make the proposed methodology operational within knowledge-based systems for patient monitoring, we present a Bayesian network representation of the underlying probabilistic model. Inferences involved in the prediction process can thus be performed via general algorithms for probability propagation on a Bayesian network. As an illustration of the proposed methodology we describe numerical results from an application in the field of cancer therapy.

Original languageEnglish
Pages (from-to)243-260
Number of pages18
JournalArtificial Intelligence in Medicine
Volume4
Issue number3
DOIs
Publication statusPublished - 1992

Fingerprint

Patient monitoring
Physiologic Monitoring
Bayesian networks
Knowledge based systems
Drug delivery
Bayes Theorem
Drug and Narcotic Control
Statistical Models
Monitoring
Chronic Disease
Learning
Databases
Therapeutics
Population
Neoplasms

Keywords

  • Bayesian forecasting
  • Bayesian networks
  • Gibbs sampler
  • knowledge-based systems
  • Monte Carlo methods
  • Therapy monitoring

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine(all)

Cite this

Bayesian networks for patient monitoring. / Berzuini, C.; Bellazzi, R.; Quaglini, S.; Spiegelhalter, D. J.

In: Artificial Intelligence in Medicine, Vol. 4, No. 3, 1992, p. 243-260.

Research output: Contribution to journalArticle

Berzuini, C. ; Bellazzi, R. ; Quaglini, S. ; Spiegelhalter, D. J. / Bayesian networks for patient monitoring. In: Artificial Intelligence in Medicine. 1992 ; Vol. 4, No. 3. pp. 243-260.
@article{5a084c04d87c4dd5b9cf6af586784073,
title = "Bayesian networks for patient monitoring",
abstract = "We consider a Bayesian statistical approach to model-based prediction of a future patient's response to a therapy, suitable in a wide range of clinical monitoring applications, especially when the observations made on the pathophysiological process of interest are imprecise and sporadic. Potential areas of application range from the predictive control of drug delivery to the management of chronic diseases. A distinctive characteristic of the proposed method is the capability of learning from a database of past patients, by explicitly modeling inter-subject variability of the unknown model parameters, and at an individual's level, by periodic updating of patient-specific parameter estimates on the basis of the accumulating data. By combining information about the population and information contained in the data of the specific patient we improve patient-specific forecasts. In order to make the proposed methodology operational within knowledge-based systems for patient monitoring, we present a Bayesian network representation of the underlying probabilistic model. Inferences involved in the prediction process can thus be performed via general algorithms for probability propagation on a Bayesian network. As an illustration of the proposed methodology we describe numerical results from an application in the field of cancer therapy.",
keywords = "Bayesian forecasting, Bayesian networks, Gibbs sampler, knowledge-based systems, Monte Carlo methods, Therapy monitoring",
author = "C. Berzuini and R. Bellazzi and S. Quaglini and Spiegelhalter, {D. J.}",
year = "1992",
doi = "10.1016/0933-3657(92)90030-S",
language = "English",
volume = "4",
pages = "243--260",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "3",

}

TY - JOUR

T1 - Bayesian networks for patient monitoring

AU - Berzuini, C.

AU - Bellazzi, R.

AU - Quaglini, S.

AU - Spiegelhalter, D. J.

PY - 1992

Y1 - 1992

N2 - We consider a Bayesian statistical approach to model-based prediction of a future patient's response to a therapy, suitable in a wide range of clinical monitoring applications, especially when the observations made on the pathophysiological process of interest are imprecise and sporadic. Potential areas of application range from the predictive control of drug delivery to the management of chronic diseases. A distinctive characteristic of the proposed method is the capability of learning from a database of past patients, by explicitly modeling inter-subject variability of the unknown model parameters, and at an individual's level, by periodic updating of patient-specific parameter estimates on the basis of the accumulating data. By combining information about the population and information contained in the data of the specific patient we improve patient-specific forecasts. In order to make the proposed methodology operational within knowledge-based systems for patient monitoring, we present a Bayesian network representation of the underlying probabilistic model. Inferences involved in the prediction process can thus be performed via general algorithms for probability propagation on a Bayesian network. As an illustration of the proposed methodology we describe numerical results from an application in the field of cancer therapy.

AB - We consider a Bayesian statistical approach to model-based prediction of a future patient's response to a therapy, suitable in a wide range of clinical monitoring applications, especially when the observations made on the pathophysiological process of interest are imprecise and sporadic. Potential areas of application range from the predictive control of drug delivery to the management of chronic diseases. A distinctive characteristic of the proposed method is the capability of learning from a database of past patients, by explicitly modeling inter-subject variability of the unknown model parameters, and at an individual's level, by periodic updating of patient-specific parameter estimates on the basis of the accumulating data. By combining information about the population and information contained in the data of the specific patient we improve patient-specific forecasts. In order to make the proposed methodology operational within knowledge-based systems for patient monitoring, we present a Bayesian network representation of the underlying probabilistic model. Inferences involved in the prediction process can thus be performed via general algorithms for probability propagation on a Bayesian network. As an illustration of the proposed methodology we describe numerical results from an application in the field of cancer therapy.

KW - Bayesian forecasting

KW - Bayesian networks

KW - Gibbs sampler

KW - knowledge-based systems

KW - Monte Carlo methods

KW - Therapy monitoring

UR - http://www.scopus.com/inward/record.url?scp=0026870035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026870035&partnerID=8YFLogxK

U2 - 10.1016/0933-3657(92)90030-S

DO - 10.1016/0933-3657(92)90030-S

M3 - Article

AN - SCOPUS:0026870035

VL - 4

SP - 243

EP - 260

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 3

ER -