A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks

Simon Rabinowicz, Arjen Hommersom*, Raphaela Butz, Matt Williams

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

Abstract

Bayesian networks are attractive for developing prognostic models in medicine, due to the possibility for modelling the multivariate relationships between variables that come into play in the care process. In practice, the development of these models is hindered due to the fact that medical data is often censored, in particular the survival time. In this paper, we propose to directly integrate Cox proportional hazards models as part of a Bayesian network. Furthermore, we show how such Bayesian network models can be learned from data, after which these models can be used for probabilistic reasoning about survival. Finally, this method is applied to develop a prognostic model for Glioblastoma Multiforme, a common malignant brain tumour.
Original languageEnglish
Title of host publicationArtificial Intelligence in Medicine
Subtitle of host publication16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings
EditorsAnnette ten Teije, Christian Popow, John H. Holmes, Lucia Sacchi
Place of PublicationCham
PublisherSpringer International Publishing AG
Pages81-85
Number of pages5
ISBN (Electronic)9783319597584
ISBN (Print)9783319597577
DOIs
Publication statusPublished - 2017

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10259
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Fingerprint

Bayesian networks
Medicine
Tumors
Brain
Hazards

Cite this

Rabinowicz, S., Hommersom, A., Butz, R., & Williams, M. (2017). A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks. In A. ten Teije, C. Popow, J. H. Holmes, & L. Sacchi (Eds.), Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings (pp. 81-85). (Lecture Notes in Computer Science; Vol. 10259). Cham: Springer International Publishing AG. https://doi.org/10.1007/978-3-319-59758-4_9
Rabinowicz, Simon ; Hommersom, Arjen ; Butz, Raphaela ; Williams, Matt. / A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks. Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings. editor / Annette ten Teije ; Christian Popow ; John H. Holmes ; Lucia Sacchi. Cham : Springer International Publishing AG, 2017. pp. 81-85 (Lecture Notes in Computer Science).
@inproceedings{6427cdbc5e27490c9a4735f057901bb5,
title = "A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks",
abstract = "Bayesian networks are attractive for developing prognostic models in medicine, due to the possibility for modelling the multivariate relationships between variables that come into play in the care process. In practice, the development of these models is hindered due to the fact that medical data is often censored, in particular the survival time. In this paper, we propose to directly integrate Cox proportional hazards models as part of a Bayesian network. Furthermore, we show how such Bayesian network models can be learned from data, after which these models can be used for probabilistic reasoning about survival. Finally, this method is applied to develop a prognostic model for Glioblastoma Multiforme, a common malignant brain tumour.",
author = "Simon Rabinowicz and Arjen Hommersom and Raphaela Butz and Matt Williams",
year = "2017",
doi = "10.1007/978-3-319-59758-4_9",
language = "English",
isbn = "9783319597577",
series = "Lecture Notes in Computer Science",
publisher = "Springer International Publishing AG",
pages = "81--85",
editor = "{ten Teije}, Annette and Christian Popow and Holmes, {John H.} and Lucia Sacchi",
booktitle = "Artificial Intelligence in Medicine",
address = "Switzerland",

}

Rabinowicz, S, Hommersom, A, Butz, R & Williams, M 2017, A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks. in A ten Teije, C Popow, JH Holmes & L Sacchi (eds), Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings. Lecture Notes in Computer Science, vol. 10259, Springer International Publishing AG, Cham, pp. 81-85. https://doi.org/10.1007/978-3-319-59758-4_9

A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks. / Rabinowicz, Simon; Hommersom, Arjen; Butz, Raphaela; Williams, Matt.

Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings. ed. / Annette ten Teije; Christian Popow; John H. Holmes; Lucia Sacchi. Cham : Springer International Publishing AG, 2017. p. 81-85 (Lecture Notes in Computer Science; Vol. 10259).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review

TY - GEN

T1 - A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks

AU - Rabinowicz, Simon

AU - Hommersom, Arjen

AU - Butz, Raphaela

AU - Williams, Matt

PY - 2017

Y1 - 2017

N2 - Bayesian networks are attractive for developing prognostic models in medicine, due to the possibility for modelling the multivariate relationships between variables that come into play in the care process. In practice, the development of these models is hindered due to the fact that medical data is often censored, in particular the survival time. In this paper, we propose to directly integrate Cox proportional hazards models as part of a Bayesian network. Furthermore, we show how such Bayesian network models can be learned from data, after which these models can be used for probabilistic reasoning about survival. Finally, this method is applied to develop a prognostic model for Glioblastoma Multiforme, a common malignant brain tumour.

AB - Bayesian networks are attractive for developing prognostic models in medicine, due to the possibility for modelling the multivariate relationships between variables that come into play in the care process. In practice, the development of these models is hindered due to the fact that medical data is often censored, in particular the survival time. In this paper, we propose to directly integrate Cox proportional hazards models as part of a Bayesian network. Furthermore, we show how such Bayesian network models can be learned from data, after which these models can be used for probabilistic reasoning about survival. Finally, this method is applied to develop a prognostic model for Glioblastoma Multiforme, a common malignant brain tumour.

U2 - 10.1007/978-3-319-59758-4_9

DO - 10.1007/978-3-319-59758-4_9

M3 - Conference article in proceeding

SN - 9783319597577

T3 - Lecture Notes in Computer Science

SP - 81

EP - 85

BT - Artificial Intelligence in Medicine

A2 - ten Teije, Annette

A2 - Popow, Christian

A2 - Holmes, John H.

A2 - Sacchi, Lucia

PB - Springer International Publishing AG

CY - Cham

ER -

Rabinowicz S, Hommersom A, Butz R, Williams M. A Prognostic Model of Glioblastoma Multiforme Using Survival Bayesian Networks. In ten Teije A, Popow C, Holmes JH, Sacchi L, editors, Artificial Intelligence in Medicine: 16th Conference on Artificial Intelligence in Medicine, AIME 2017, Vienna, Austria, June 21-24, 2017, Proceedings. Cham: Springer International Publishing AG. 2017. p. 81-85. (Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-319-59758-4_9