An ignorant belief network to forecast glucose concentration from clinical databases

Marco Ramoni, Alberto Riva, Mario Stefanelli, Vimla Patel

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Ignorant Belief Networks (IBNs) are a class of Bayesian Belief Networks (BBNs) able to reason on the basis of incomplete probabilistic information and to incrementally refine the precision of the inferred probabilities as more information becomes available. In this paper, we will describe how can be used to develop a system able to forecast blood glucose concentration in patients affected by insulin dependent diabetes mellitus (IDDM). The major difference between our approach and the traditional ones is that probability distributions over the IBN are not provided by some human expert or by the current literature but they are directly extracted from a clinical database of IDDM patients. This choice capitalizes on the large amount of information generated by the daily control of blood glucose and allows the system to improve the accuracy of predictions as more information becomes available. We will show how, even with a very small subset of the information needed to specify a BBN, the IBN is able to carry out predictions about the future blood glucose concentration in a patient by explicitly taking into consideration the level of ignorance embedded in the network.

Original languageEnglish (US)
Pages (from-to)541-559
Number of pages19
JournalArtificial Intelligence in Medicine
Volume7
Issue number6
DOIs
StatePublished - Jan 1 1995
Externally publishedYes

Fingerprint

Bayesian networks
Glucose
Databases
Blood Glucose
Blood
Insulin
Medical problems
Type 1 Diabetes Mellitus
Probability distributions

Keywords

  • Bayesian belief networks
  • Insulin dependent diabetes mellitus
  • Machine learning

ASJC Scopus subject areas

  • Medicine (miscellaneous)
  • Artificial Intelligence

Cite this

An ignorant belief network to forecast glucose concentration from clinical databases. / Ramoni, Marco; Riva, Alberto; Stefanelli, Mario; Patel, Vimla.

In: Artificial Intelligence in Medicine, Vol. 7, No. 6, 01.01.1995, p. 541-559.

Research output: Contribution to journalArticle

Ramoni, Marco ; Riva, Alberto ; Stefanelli, Mario ; Patel, Vimla. / An ignorant belief network to forecast glucose concentration from clinical databases. In: Artificial Intelligence in Medicine. 1995 ; Vol. 7, No. 6. pp. 541-559.
@article{9ef532edf3e9459c8384bc368474c5c3,
title = "An ignorant belief network to forecast glucose concentration from clinical databases",
abstract = "Ignorant Belief Networks (IBNs) are a class of Bayesian Belief Networks (BBNs) able to reason on the basis of incomplete probabilistic information and to incrementally refine the precision of the inferred probabilities as more information becomes available. In this paper, we will describe how can be used to develop a system able to forecast blood glucose concentration in patients affected by insulin dependent diabetes mellitus (IDDM). The major difference between our approach and the traditional ones is that probability distributions over the IBN are not provided by some human expert or by the current literature but they are directly extracted from a clinical database of IDDM patients. This choice capitalizes on the large amount of information generated by the daily control of blood glucose and allows the system to improve the accuracy of predictions as more information becomes available. We will show how, even with a very small subset of the information needed to specify a BBN, the IBN is able to carry out predictions about the future blood glucose concentration in a patient by explicitly taking into consideration the level of ignorance embedded in the network.",
keywords = "Bayesian belief networks, Insulin dependent diabetes mellitus, Machine learning",
author = "Marco Ramoni and Alberto Riva and Mario Stefanelli and Vimla Patel",
year = "1995",
month = "1",
day = "1",
doi = "10.1016/0933-3657(95)00026-1",
language = "English (US)",
volume = "7",
pages = "541--559",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",
number = "6",

}

TY - JOUR

T1 - An ignorant belief network to forecast glucose concentration from clinical databases

AU - Ramoni, Marco

AU - Riva, Alberto

AU - Stefanelli, Mario

AU - Patel, Vimla

PY - 1995/1/1

Y1 - 1995/1/1

N2 - Ignorant Belief Networks (IBNs) are a class of Bayesian Belief Networks (BBNs) able to reason on the basis of incomplete probabilistic information and to incrementally refine the precision of the inferred probabilities as more information becomes available. In this paper, we will describe how can be used to develop a system able to forecast blood glucose concentration in patients affected by insulin dependent diabetes mellitus (IDDM). The major difference between our approach and the traditional ones is that probability distributions over the IBN are not provided by some human expert or by the current literature but they are directly extracted from a clinical database of IDDM patients. This choice capitalizes on the large amount of information generated by the daily control of blood glucose and allows the system to improve the accuracy of predictions as more information becomes available. We will show how, even with a very small subset of the information needed to specify a BBN, the IBN is able to carry out predictions about the future blood glucose concentration in a patient by explicitly taking into consideration the level of ignorance embedded in the network.

AB - Ignorant Belief Networks (IBNs) are a class of Bayesian Belief Networks (BBNs) able to reason on the basis of incomplete probabilistic information and to incrementally refine the precision of the inferred probabilities as more information becomes available. In this paper, we will describe how can be used to develop a system able to forecast blood glucose concentration in patients affected by insulin dependent diabetes mellitus (IDDM). The major difference between our approach and the traditional ones is that probability distributions over the IBN are not provided by some human expert or by the current literature but they are directly extracted from a clinical database of IDDM patients. This choice capitalizes on the large amount of information generated by the daily control of blood glucose and allows the system to improve the accuracy of predictions as more information becomes available. We will show how, even with a very small subset of the information needed to specify a BBN, the IBN is able to carry out predictions about the future blood glucose concentration in a patient by explicitly taking into consideration the level of ignorance embedded in the network.

KW - Bayesian belief networks

KW - Insulin dependent diabetes mellitus

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=0029411934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029411934&partnerID=8YFLogxK

U2 - 10.1016/0933-3657(95)00026-1

DO - 10.1016/0933-3657(95)00026-1

M3 - Article

C2 - 8963375

AN - SCOPUS:0029411934

VL - 7

SP - 541

EP - 559

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

IS - 6

ER -