Learning bayesian-network topologies in realistic medical domains

Xiaofeng Wu; Peter Lucas; Susan Kerr; Roelf Dijkhuizen

doi:10.1007/3-540-45497-7_46

Learning bayesian-network topologies in realistic medical domains

Xiaofeng Wu
, Peter Lucas
, Susan Kerr
, Roelf Dijkhuizen

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

12 Citations (Scopus)

Abstract

In recent years, a number of algorithms have been developed for learning the structure of Bayesian networks from data. In this paper we apply some of these algorithms to a realistic medical domain—stroke. Basically, the domain of stroke is taken as a typical example of a medical domain where much data are available concerning a few hundred patients. Learning the structure of a Bayesian network is known to be hard under these conditions. In this paper, two different structure learning algorithms are compared to each other. A causal model which was constructed with the help of an expert clinician is adopted as the gold standard. The advantages and limitations of various structure-learning algorithms are discussed in the context of the experimental results obtained.

Original language	English
Title of host publication	Medical Data Analysis
Subtitle of host publication	Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings
Editors	Jose Crespo, Victor Maojo, Fernando Martin
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	302-307
Number of pages	6
ISBN (Electronic)	978-3-540-45497-7
ISBN (Print)	978-3-540-42734-6
DOIs	https://doi.org/10.1007/3-540-45497-7_46
Publication status	Published - 2001
Externally published	Yes
Event	2nd International Symposium on Medical Data Analysis, ISMDA 2001 - Madrid, Spain Duration: 8 Oct 2001 → 9 Oct 2001 Conference number: 2

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	2199
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	2nd International Symposium on Medical Data Analysis, ISMDA 2001
Abbreviated title	ISMDA 2001
Country/Territory	Spain
City	Madrid
Period	8/10/01 → 9/10/01

UN SDGs

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

SDG 3 Good Health and Well-being

Keywords

Bayesian networks
Knowledge discovery
Machine learning
Medical decision support systems
n/a OA procedure

Access to Document

10.1007/3-540-45497-7_46

Cite this

Wu, X., Lucas, P., Kerr, S., & Dijkhuizen, R. (2001). Learning bayesian-network topologies in realistic medical domains. In J. Crespo, V. Maojo, & F. Martin (Eds.), Medical Data Analysis: Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings (pp. 302-307). (Lecture Notes in Computer Science; Vol. 2199). Springer. https://doi.org/10.1007/3-540-45497-7_46

Wu, Xiaofeng ; Lucas, Peter ; Kerr, Susan et al. / Learning bayesian-network topologies in realistic medical domains. Medical Data Analysis: Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings. editor / Jose Crespo ; Victor Maojo ; Fernando Martin. Berlin, Heidelberg : Springer, 2001. pp. 302-307 (Lecture Notes in Computer Science).

@inproceedings{97a553a5b8994d6986286c6bfdf54c0b,

title = "Learning bayesian-network topologies in realistic medical domains",

abstract = "In recent years, a number of algorithms have been developed for learning the structure of Bayesian networks from data. In this paper we apply some of these algorithms to a realistic medical domain—stroke. Basically, the domain of stroke is taken as a typical example of a medical domain where much data are available concerning a few hundred patients. Learning the structure of a Bayesian network is known to be hard under these conditions. In this paper, two different structure learning algorithms are compared to each other. A causal model which was constructed with the help of an expert clinician is adopted as the gold standard. The advantages and limitations of various structure-learning algorithms are discussed in the context of the experimental results obtained.",

keywords = "Bayesian networks, Knowledge discovery, Machine learning, Medical decision support systems, n/a OA procedure",

author = "Xiaofeng Wu and Peter Lucas and Susan Kerr and Roelf Dijkhuizen",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2001.; 2nd International Symposium on Medical Data Analysis, ISMDA 2001, ISMDA 2001 ; Conference date: 08-10-2001 Through 09-10-2001",

year = "2001",

doi = "10.1007/3-540-45497-7\_46",

language = "English",

isbn = "978-3-540-42734-6",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "302--307",

editor = "Jose Crespo and Victor Maojo and Fernando Martin",

booktitle = "Medical Data Analysis",

address = "Germany",

}

Wu, X, Lucas, P, Kerr, S & Dijkhuizen, R 2001, Learning bayesian-network topologies in realistic medical domains. in J Crespo, V Maojo & F Martin (eds), Medical Data Analysis: Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings. Lecture Notes in Computer Science, vol. 2199, Springer, Berlin, Heidelberg, pp. 302-307, 2nd International Symposium on Medical Data Analysis, ISMDA 2001, Madrid, Spain, 8/10/01. https://doi.org/10.1007/3-540-45497-7_46

Learning bayesian-network topologies in realistic medical domains. / Wu, Xiaofeng; Lucas, Peter; Kerr, Susan et al.
Medical Data Analysis: Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings. ed. / Jose Crespo; Victor Maojo; Fernando Martin. Berlin, Heidelberg: Springer, 2001. p. 302-307 (Lecture Notes in Computer Science; Vol. 2199).

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

TY - GEN

T1 - Learning bayesian-network topologies in realistic medical domains

AU - Wu, Xiaofeng

AU - Lucas, Peter

AU - Kerr, Susan

AU - Dijkhuizen, Roelf

N1 - Conference code: 2

PY - 2001

Y1 - 2001

N2 - In recent years, a number of algorithms have been developed for learning the structure of Bayesian networks from data. In this paper we apply some of these algorithms to a realistic medical domain—stroke. Basically, the domain of stroke is taken as a typical example of a medical domain where much data are available concerning a few hundred patients. Learning the structure of a Bayesian network is known to be hard under these conditions. In this paper, two different structure learning algorithms are compared to each other. A causal model which was constructed with the help of an expert clinician is adopted as the gold standard. The advantages and limitations of various structure-learning algorithms are discussed in the context of the experimental results obtained.

AB - In recent years, a number of algorithms have been developed for learning the structure of Bayesian networks from data. In this paper we apply some of these algorithms to a realistic medical domain—stroke. Basically, the domain of stroke is taken as a typical example of a medical domain where much data are available concerning a few hundred patients. Learning the structure of a Bayesian network is known to be hard under these conditions. In this paper, two different structure learning algorithms are compared to each other. A causal model which was constructed with the help of an expert clinician is adopted as the gold standard. The advantages and limitations of various structure-learning algorithms are discussed in the context of the experimental results obtained.

KW - Bayesian networks

KW - Knowledge discovery

KW - Machine learning

KW - Medical decision support systems

KW - n/a OA procedure

UR - https://www.scopus.com/pages/publications/84937406249

U2 - 10.1007/3-540-45497-7_46

DO - 10.1007/3-540-45497-7_46

M3 - Conference contribution

AN - SCOPUS:84937406249

SN - 978-3-540-42734-6

T3 - Lecture Notes in Computer Science

SP - 302

EP - 307

BT - Medical Data Analysis

A2 - Crespo, Jose

A2 - Maojo, Victor

A2 - Martin, Fernando

PB - Springer

CY - Berlin, Heidelberg

T2 - 2nd International Symposium on Medical Data Analysis, ISMDA 2001

Y2 - 8 October 2001 through 9 October 2001

ER -

Wu X, Lucas P, Kerr S, Dijkhuizen R. Learning bayesian-network topologies in realistic medical domains. In Crespo J, Maojo V, Martin F, editors, Medical Data Analysis: Second International Symposium, ISMDA 2001, Madrid, Spain, October 8-9, 2001 Proceedings. Berlin, Heidelberg: Springer. 2001. p. 302-307. (Lecture Notes in Computer Science). doi: 10.1007/3-540-45497-7_46

Learning bayesian-network topologies in realistic medical domains

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this