Advanced

A Bayesian Network for Probabilistic Reasoning and Imputation of Missing Risk Factors in Type 2 Diabetes

Sambo, Francesco; Facchinetti, Andrea; Hakaste, Liisa; Kravic, Jasmina LU ; Di Camillo, Barbara; Fico, Giuseppe; Tuomilehto, Jaakko; Groop, Leif LU ; Gabriel, Rafael and Tiinamaija, Tuomi, et al. (2015) 15th Conference on Artificial Intelligence in Medicine (AIME) In Lecture Notes in Computer Science 9105. p.172-176
Abstract
We propose a novel Bayesian network tool to model the probabilistic relations between a set of type 2 diabetes risk factors. The tool can be used for probabilistic reasoning and for imputation of missing values among risk factors. The Bayesian network is learnt from a joint training set of three European population studies. Tested on an independent patient set, the network is shown to be competitive with both a standard imputation tool and a widely used risk score for type 2 diabetes, providing in addition a richer description of the interdependencies between diabetes risk factors.
Please use this url to cite or link to this publication:
author
, et al. (More)
(Less)
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
values imputation, Missing, Probabilistic reasoning, Type 2 diabetes, Bayesian networks
in
Lecture Notes in Computer Science
volume
9105
pages
172 - 176
publisher
Springer
conference name
15th Conference on Artificial Intelligence in Medicine (AIME)
external identifiers
  • wos:000364534300022
  • scopus:84947968258
ISSN
1611-3349
0302-9743
DOI
10.1007/978-3-319-19551-3_22
language
English
LU publication?
yes
id
80f4bc69-57ba-4fbb-86e6-e9e1f12742ae (old id 8386415)
date added to LUP
2015-12-22 09:15:20
date last changed
2017-01-01 04:10:28
@inproceedings{80f4bc69-57ba-4fbb-86e6-e9e1f12742ae,
  abstract     = {We propose a novel Bayesian network tool to model the probabilistic relations between a set of type 2 diabetes risk factors. The tool can be used for probabilistic reasoning and for imputation of missing values among risk factors. The Bayesian network is learnt from a joint training set of three European population studies. Tested on an independent patient set, the network is shown to be competitive with both a standard imputation tool and a widely used risk score for type 2 diabetes, providing in addition a richer description of the interdependencies between diabetes risk factors.},
  author       = {Sambo, Francesco and Facchinetti, Andrea and Hakaste, Liisa and Kravic, Jasmina and Di Camillo, Barbara and Fico, Giuseppe and Tuomilehto, Jaakko and Groop, Leif and Gabriel, Rafael and Tiinamaija, Tuomi and Cobelli, Claudio},
  booktitle    = {Lecture Notes in Computer Science},
  issn         = {1611-3349},
  keyword      = {values imputation,Missing,Probabilistic reasoning,Type 2 diabetes,Bayesian networks},
  language     = {eng},
  pages        = {172--176},
  publisher    = {Springer},
  title        = {A Bayesian Network for Probabilistic Reasoning and Imputation of Missing Risk Factors in Type 2 Diabetes},
  url          = {http://dx.doi.org/10.1007/978-3-319-19551-3_22},
  volume       = {9105},
  year         = {2015},
}