An Ontology-Based Bayesian Network Approach for Representing Uncertainty in Clinical Practice Guidelines

Authors:
Hai-Tao Zheng;Bo-Yeong Kang;Hong-Gee Kim
Affiliations:
Biomedical Knowledge Engineering Laboratory, Seoul National University, Seoul, Korea;Biomedical Knowledge Engineering Laboratory, Seoul National University, Seoul, Korea;Biomedical Knowledge Engineering Laboratory, Seoul National University, Seoul, Korea
Venue:
Uncertainty Reasoning for the Semantic Web I
Year:
2008

Citing 3
Cited 3

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Bucket elimination: a unifying framework for probabilistic inference

Learning in graphical models
Exploiting causal independence in Bayesian network inference

Journal of Artificial Intelligence Research

PCOPM: a probabilistic CBR framework for obesity prescription management

ICIC'10 Proceedings of the Advanced intelligent computing theories and applications, and 6th international conference on Intelligent computing
Application of probabilistic and fuzzy cognitive approaches in semantic web framework for medical decision support

Computer Methods and Programs in Biomedicine
Diagnosis Support System based on clinical guidelines: comparison between Case-Based Fuzzy Cognitive Maps and Bayesian Networks

Computer Methods and Programs in Biomedicine

Quantified Score

Hi-index	0.00

Visualization

Abstract

Clinical Practice Guidelines (CPGs) play an important role in improving quality of care and patient outcomes. Although several machine-readable representations of practice guidelines have been implemented with semantic web technologies, there is no implementation to represent uncertainty in activity graphs in clinical practice guidelines. In this paper, we explore a Bayesian Network(BN) approach for representing the uncertainty in CPGs based on ontologies. Using this representation, we can evaluate the effect of an activity on the whole clinical process, which can help doctors judge the risk of uncertainty for other activities when making a decision. A variable elimination algorithm is applied to implement the BN inference and a validation of an aspirin therapy scenario for diabetic patients is proposed.