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

Francesco Sambo; Andrea Facchinetti; Liisa Hakaste; Jasmina Kravic; Barbara Di Camillo; Giuseppe Fico; Jaakko Tuomilehto; Leif Groop; Rafael Gabriel; Tuomi Tiinamaija; Claudio Cobelli

doi:10.1007/978-3-319-19551-3_22

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

Francesco Sambo, Andrea Facchinetti, Liisa Hakaste, Jasmina Kravic, Barbara Di Camillo, Giuseppe Fico, Jaakko Tuomilehto, Leif Groop, Rafael Gabriel, Tuomi Tiinamaija, Claudio Cobelli

Research output: Chapter in Book/Report/Conference proceeding › Paper in conference proceeding › peer-review

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.

Original language	English
Title of host publication	Lecture Notes in Computer Science
Publisher	Springer
Pages	172-176
Volume	9105
DOIs	https://doi.org/10.1007/978-3-319-19551-3_22
Publication status	Published - 2015
Event	15th Conference on Artificial Intelligence in Medicine (AIME) - Univ Pavia, Pavia, Italy Duration: 2015 Jun 17 → 2015 Jun 20

Publication series

Name
Volume	9105
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	15th Conference on Artificial Intelligence in Medicine (AIME)
Country/Territory	Italy
City	Univ Pavia, Pavia
Period	2015/06/17 → 2015/06/20

Subject classification (UKÄ)

Computer Vision and Robotics (Autonomous Systems)
Endocrinology and Diabetes

Free keywords

values imputation
Missing
Probabilistic reasoning
Type 2 diabetes
Bayesian networks

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-319-19551-3_22

Cite this

Sambo, F., Facchinetti, A., Hakaste, L., Kravic, J., Di Camillo, B., Fico, G., Tuomilehto, J., Groop, L., Gabriel, R., Tiinamaija, T., & Cobelli, C. (2015). A Bayesian Network for Probabilistic Reasoning and Imputation of Missing Risk Factors in Type 2 Diabetes. In Lecture Notes in Computer Science (Vol. 9105, pp. 172-176). Springer. https://doi.org/10.1007/978-3-319-19551-3_22

@inproceedings{80f4bc6957ba4fbb86e6e9e1f12742ae,

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

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.",

keywords = "values imputation, Missing, Probabilistic reasoning, Type 2 diabetes, Bayesian networks",

author = "Francesco Sambo and Andrea Facchinetti and Liisa Hakaste and Jasmina Kravic and {Di Camillo}, Barbara and Giuseppe Fico and Jaakko Tuomilehto and Leif Groop and Rafael Gabriel and Tuomi Tiinamaija and Claudio Cobelli",

year = "2015",

doi = "10.1007/978-3-319-19551-3_22",

language = "English",

volume = "9105",

publisher = "Springer",

pages = "172--176",

booktitle = "Lecture Notes in Computer Science",

address = "Germany",

note = "15th Conference on Artificial Intelligence in Medicine (AIME) ; Conference date: 17-06-2015 Through 20-06-2015",

}

Sambo, F, Facchinetti, A, Hakaste, L, Kravic, J, Di Camillo, B, Fico, G, Tuomilehto, J, Groop, L, Gabriel, R, Tiinamaija, T & Cobelli, C 2015, A Bayesian Network for Probabilistic Reasoning and Imputation of Missing Risk Factors in Type 2 Diabetes. in Lecture Notes in Computer Science. vol. 9105, Springer, pp. 172-176, 15th Conference on Artificial Intelligence in Medicine (AIME), Univ Pavia, Pavia, Italy, 2015/06/17. https://doi.org/10.1007/978-3-319-19551-3_22

TY - GEN

T1 - A Bayesian Network for Probabilistic Reasoning and Imputation of Missing Risk Factors in Type 2 Diabetes

AU - Sambo, Francesco

AU - Facchinetti, Andrea

AU - Hakaste, Liisa

AU - Kravic, Jasmina

AU - Di Camillo, Barbara

AU - Fico, Giuseppe

AU - Tuomilehto, Jaakko

AU - Groop, Leif

AU - Gabriel, Rafael

AU - Tiinamaija, Tuomi

AU - Cobelli, Claudio

PY - 2015

Y1 - 2015

N2 - 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.

AB - 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.

KW - values imputation

KW - Missing

KW - Probabilistic reasoning

KW - Type 2 diabetes

KW - Bayesian networks

U2 - 10.1007/978-3-319-19551-3_22

DO - 10.1007/978-3-319-19551-3_22

M3 - Paper in conference proceeding

VL - 9105

SP - 172

EP - 176

BT - Lecture Notes in Computer Science

PB - Springer

T2 - 15th Conference on Artificial Intelligence in Medicine (AIME)

Y2 - 17 June 2015 through 20 June 2015

ER -

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

Abstract

Publication series

Conference

Subject classification (UKÄ)

Free keywords

UN SDGs

Access to Document

Fingerprint

Cite this