Improved Design of Bayesian Networks for Modelling Toxicity Risk in Breast Radiotherapy using Dynamic Discretization

Philip Ciunkiewicz, Svetlana Yanushkevich, Michael Roumeliotis, Kailyn Stenhouse, Philip McGeachy, Sarah Quirk, Petra Grendarova

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study investigates the dynamic discretization approach with the purpose of improving probabilistic causal models for the task of toxicity risk assessment in breast radiother-apy. We considered a probabilistic causal model such as Bayesian Networks, and implemented a modified version of Fenton & Neil's dynamic discretization algorithm to validate and analyze these models in terms of performance. Our implementation performs discretization at the data- or distribution-level. This approach is shown to provide significant improvement over static methods when assessing distribution fit via relative entropy error, as well as being very computationally efficient. Predictive performance was compared across four distinct datasets using Bayesian Networks, and dynamic discretization was not found to consistently outperform static techniques despite generating discretizations with significantly better fit to their underlying distributions.

Original languageEnglish (US)
Title of host publication2022 International Joint Conference on Neural Networks, IJCNN 2022 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728186719
DOIs
StatePublished - 2022
Event2022 International Joint Conference on Neural Networks, IJCNN 2022 - Padua, Italy
Duration: Jul 18 2022Jul 23 2022

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2022-July

Conference

Conference2022 International Joint Conference on Neural Networks, IJCNN 2022
Country/TerritoryItaly
CityPadua
Period7/18/227/23/22

Keywords

  • Bayesian network
  • discretization
  • information theory
  • machine reasoning
  • probability distribution

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Improved Design of Bayesian Networks for Modelling Toxicity Risk in Breast Radiotherapy using Dynamic Discretization'. Together they form a unique fingerprint.

Cite this