Repository logo
 

Discovery of High Quality Knowledge for Clinical Decision Support Systems by Applying Semantic Web Technology

Files

Whole thesis(7.65 MB)

Date

2017

Authors

Supervisor

Parry, Dave
Bai, Quan
Narayanan, Ajit

Item type

Thesis

Degree name

Doctor of Philosophy

Journal Title

Journal ISSN

Volume Title

Publisher

Auckland University of Technology

Abstract

While the discovery of new clinical knowledge is always a good thing, it can lead to difficulties. Health experts are required to actively ensure they are informed about the latest accurate knowledge in their field. Many health experts already have access to Clinical Decision Support Systems (CDSSs). These systems aid health experts in making decisions by providing clinical knowledge. CDSS is helpful, but often has issues with the quality of knowledge extracted from knowledge sources (KSs) for decision making. Discovery of high quality clinical knowledge to support decision making is difficult. This issue is partly due to the enormous amount of research, guideline data and other knowledge published every year. Available KSs (e.g. PubMed, Google scholar) are very diverse in terms of formats, structure, and vocabulary. Clinical knowledge may need to be extracted from these diverse locations and sources. To facilitate this task, many health experts focus on developing methods to manage and analyse clinical knowledge in this changeable environment. Most of KSs suffer from a lack of proper mechanism for identifying high quality knowledge. For example the PubMed search engine does not fully check some important knowledge quality metrics (QMs) such as citation, structure, accuracy and relevancy. This research has potential to make decisions easier, save time, and in turn allows the CDSSs operate more effectively. The objective of this research is to propose a knowledge quality assessment (KQA) approach to discover the high quality clinical knowledge needed for the purpose of decision making. Semantic Web (SW) technology has been used in the approach to assess how qualified knowledge is about given query. The candidate knowledge QMs were identified from related work to improve assessment of knowledge quality in CDSSs. By running a survey, the candidate knowledge QMs were reviewed and rated by health experts. Based on the survey results the knowledge QM measurements were proposed. While at an elementary stage and considered to be a “proof of concept”, this research offers fresh insights into what the world of healthcare will look like when knowledge quality assessment mechanism for knowledge acquisition of CDSSs is fully implemented.

Description

Keywords

Knowledge Quality Assessment, Semantic Web technology, Clinical Decision Support System, Knowledge Discovery, Knowledge Acquisition

Source

DOI

Publisher's version

Rights statement

Permanent link

https://hdl.handle.net/10292/10966

Collections

Doctoral Theses