A causal model for fluctuating sugar levels in diabetes patients

Kinzang Chhogyal, Abhaya Nayak, Rolf Schwitter, Abdul Sattar

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background Causal models of physiological systems can be immensely useful in medicine as they may be used for both diagnostic and therapeutic reasoning. Aims In this paper we investigate how an agent may use the theory of belief change to rectify simple causal models of changing blood sugar levels in diabetes patients. Method We employ the semantic approach to belief change together with a popular measure of distance called Dalal distance between different state descriptions in order to implement a simple application that simulates the effectiveness of the proposed method in helping an agent rectify a simple causal model. Results Our simulation results show that distance-based belief change can help in improving the agent's causal knowledge. However, under the current implementation there is no guarantee that the agent will learn the complete model and the agent may at times get stuck in local optima. Conclusion Distance-based belief change can help in refining simple causal models such as the example in this paper. Future work will include larger state-action spaces, better distance measures and strategies for choosing actions.

LanguageEnglish
Pages497-502
Number of pages6
JournalAustralasian Medical Journal
Volume5
Issue number9
DOIs
Publication statusPublished - 2012

Fingerprint

Semantics
Blood Glucose
Medicine
Therapeutics

Cite this

@article{bfa58645bac84d10828b9d4d68219ba5,
title = "A causal model for fluctuating sugar levels in diabetes patients",
abstract = "Background Causal models of physiological systems can be immensely useful in medicine as they may be used for both diagnostic and therapeutic reasoning. Aims In this paper we investigate how an agent may use the theory of belief change to rectify simple causal models of changing blood sugar levels in diabetes patients. Method We employ the semantic approach to belief change together with a popular measure of distance called Dalal distance between different state descriptions in order to implement a simple application that simulates the effectiveness of the proposed method in helping an agent rectify a simple causal model. Results Our simulation results show that distance-based belief change can help in improving the agent's causal knowledge. However, under the current implementation there is no guarantee that the agent will learn the complete model and the agent may at times get stuck in local optima. Conclusion Distance-based belief change can help in refining simple causal models such as the example in this paper. Future work will include larger state-action spaces, better distance measures and strategies for choosing actions.",
author = "Kinzang Chhogyal and Abhaya Nayak and Rolf Schwitter and Abdul Sattar",
year = "2012",
doi = "10.4066/AMJ.2012.1392",
language = "English",
volume = "5",
pages = "497--502",
journal = "Australasian Medical Journal",
issn = "1836-1935",
publisher = "The Australasian Medical Journal Pty. Ltd.",
number = "9",

}

A causal model for fluctuating sugar levels in diabetes patients. / Chhogyal, Kinzang; Nayak, Abhaya; Schwitter, Rolf; Sattar, Abdul.

In: Australasian Medical Journal, Vol. 5, No. 9, 2012, p. 497-502.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - A causal model for fluctuating sugar levels in diabetes patients

AU - Chhogyal, Kinzang

AU - Nayak, Abhaya

AU - Schwitter, Rolf

AU - Sattar, Abdul

PY - 2012

Y1 - 2012

N2 - Background Causal models of physiological systems can be immensely useful in medicine as they may be used for both diagnostic and therapeutic reasoning. Aims In this paper we investigate how an agent may use the theory of belief change to rectify simple causal models of changing blood sugar levels in diabetes patients. Method We employ the semantic approach to belief change together with a popular measure of distance called Dalal distance between different state descriptions in order to implement a simple application that simulates the effectiveness of the proposed method in helping an agent rectify a simple causal model. Results Our simulation results show that distance-based belief change can help in improving the agent's causal knowledge. However, under the current implementation there is no guarantee that the agent will learn the complete model and the agent may at times get stuck in local optima. Conclusion Distance-based belief change can help in refining simple causal models such as the example in this paper. Future work will include larger state-action spaces, better distance measures and strategies for choosing actions.

AB - Background Causal models of physiological systems can be immensely useful in medicine as they may be used for both diagnostic and therapeutic reasoning. Aims In this paper we investigate how an agent may use the theory of belief change to rectify simple causal models of changing blood sugar levels in diabetes patients. Method We employ the semantic approach to belief change together with a popular measure of distance called Dalal distance between different state descriptions in order to implement a simple application that simulates the effectiveness of the proposed method in helping an agent rectify a simple causal model. Results Our simulation results show that distance-based belief change can help in improving the agent's causal knowledge. However, under the current implementation there is no guarantee that the agent will learn the complete model and the agent may at times get stuck in local optima. Conclusion Distance-based belief change can help in refining simple causal models such as the example in this paper. Future work will include larger state-action spaces, better distance measures and strategies for choosing actions.

UR - http://www.scopus.com/inward/record.url?scp=84867258304&partnerID=8YFLogxK

U2 - 10.4066/AMJ.2012.1392

DO - 10.4066/AMJ.2012.1392

M3 - Article

VL - 5

SP - 497

EP - 502

JO - Australasian Medical Journal

T2 - Australasian Medical Journal

JF - Australasian Medical Journal

SN - 1836-1935

IS - 9

ER -