A Game-Theoretical Approach to Clinical Decision Making with Immersive Visualisation

Lau, CW; Catchpoole, D; Simoff, S; Zhang, D; Nguyen, QV

A Game-Theoretical Approach to Clinical Decision Making with Immersive Visualisation

Lau, CW Catchpoole, D

Simoff, S Zhang, D Nguyen, QV

Permalink

Publisher:: MDPI
Publication Type:: Journal Article
Citation:: Applied Sciences (Switzerland), 2023, 13, (18)
Issue Date:: 2023-09-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (5.3 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Lau, CW
dc.contributor.author	Catchpoole, D https://orcid.org/0000-0001-5836-1413
dc.contributor.author	Simoff, S
dc.contributor.author	Zhang, D
dc.contributor.author	Nguyen, QV
dc.date.accessioned	2024-03-14T04:23:30Z
dc.date.available	2024-03-14T04:23:30Z
dc.date.issued	2023-09-01
dc.identifier.citation	Applied Sciences (Switzerland), 2023, 13, (18)
dc.identifier.issn	2076-3417
dc.identifier.issn	2076-3417
dc.identifier.uri	http://hdl.handle.net/10453/176699
dc.description.abstract	Cancer is a disease characterised by changes in combinations of genes within affected tumour cells. The deep understanding of genetic activity afforded to cancer specialists through complex genomics data analytics has advanced the clinical management of cancer by using deep machine learning algorithms and visualisation. However, most of the existing works do not integrate intelligent decision-making aids that can guide users in the analysis and exploration processes. This paper contributes a novel strategy that applies game theory within a VR-enabled immersive visualisation system designed as the decision support engine to mimic real-world interactions between stakeholders within complex relationships, in this case cancer clinicians. Our focus is to apply game theory to assist doctors in the decision-making process regarding the treatment options for rare-cancer patients. Nash Equilibrium and Social Optimality strategy profiles were used to facilitate complex analysis within the visualisation by inspecting which combination of genes and dimensionality reduction methods yields the best survival rate and by investigating the treatment protocol to form new hypotheses. Using a case simulation, we demonstrate the effectiveness of game theory in guiding the analyst with a patient cohort data interrogation system as compared to an analyst without a decision support system. Particularly, the strategy profile (t-SNE method and DNMT3B_ZBTB46_LAPTM4B gene) gains the highest payoff for the two doctors.
dc.language	English
dc.publisher	MDPI
dc.relation.ispartof	Applied Sciences (Switzerland)
dc.relation.isbasedon	10.3390/app131810178
dc.rights	info:eu-repo/semantics/openAccess
dc.title	A Game-Theoretical Approach to Clinical Decision Making with Immersive Visualisation
dc.type	Journal Article
utslib.citation.volume	13
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	open_access	*
dc.date.updated	2024-03-14T04:23:27Z
pubs.issue	18
pubs.publication-status	Published
pubs.volume	13
utslib.citation.issue	18

Abstract:

Cancer is a disease characterised by changes in combinations of genes within affected tumour cells. The deep understanding of genetic activity afforded to cancer specialists through complex genomics data analytics has advanced the clinical management of cancer by using deep machine learning algorithms and visualisation. However, most of the existing works do not integrate intelligent decision-making aids that can guide users in the analysis and exploration processes. This paper contributes a novel strategy that applies game theory within a VR-enabled immersive visualisation system designed as the decision support engine to mimic real-world interactions between stakeholders within complex relationships, in this case cancer clinicians. Our focus is to apply game theory to assist doctors in the decision-making process regarding the treatment options for rare-cancer patients. Nash Equilibrium and Social Optimality strategy profiles were used to facilitate complex analysis within the visualisation by inspecting which combination of genes and dimensionality reduction methods yields the best survival rate and by investigating the treatment protocol to form new hypotheses. Using a case simulation, we demonstrate the effectiveness of game theory in guiding the analyst with a patient cohort data interrogation system as compared to an analyst without a decision support system. Particularly, the strategy profile (t-SNE method and DNMT3B_ZBTB46_LAPTM4B gene) gains the highest payoff for the two doctors.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/176699