Doctor-patient partnership has been advocated for achieving effective diabetes management. Such a partnership requires empowering patients with proper knowledge and skills so they are capable of participating in decision-making, effective communication with health professionals and successful diabetes self-management. Although it is well known that patient education should be tailored and prioritised, little research on Computer-based Patient Education Systems (CPESs) has aimed at customising information that is flexible enough to adapt to firstly, the dynamic nature of patients' ongoing information needs and secondly, changes in their personal health and social circumstances. Moreover, except for indirect support for doctor-patient communication through tailored information, current CPESs do not aid patients in formulating their questions. / This thesis targets limitations of current CPESs and explores approaches for using information technology (IT) to support the doctor-patient partnership. Two approaches used to achieve the research goal are 1) providing essential information to individual patients - information that is not only relevant, but also prioritised; and 2) providing direct support for patients to generate personalised agendas prior to scheduled health visits. The innovative technologies that have been developed for implementing these two approaches include a comprehensive Diabetes Information Profile (DIP) for each patient, information tailoring and prioritisation algorithms (information algorithms), quiz tailoring and prioritisation algorithms (quiz algorithms), and agenda personalisation algorithms (which serve to populate an agenda question pool). The DIP includes data elements on a patient's lifestyle, diet profile, psychosocial profile, risk factors of diabetic complications, behaviour change profile, self-management profile, and clinical status. The information algorithms take into account these DIP elements, as well as patients' diabetes knowledge level (based on educational exposure) and individual information preferences. Collectively, the implementation of these approaches, using an extensible architecture based on Extensible Mark-up Language (XML) and Java technologies, is called “Violet Technology” (VT). A VT-based web portal has been developed and evaluated. / A two-phase evaluation was conducted through the Diabetes Centre of a metropolitan hospital. The first study evaluates the validity of the information algorithms through patient and healthcare provider assessment of prioritised information topics. The participants of the first study include 11 patients with diabetes, one General Practician (GP), one endocrinologist, two diabetes nurse educators and one dietician. The second trial evaluates the VT-based portal overall - including information, quiz and agenda personalisation algorithms - through a field trial of the portal with random selection of patients to treatment and control groups. In total, 27 patients, one GP, one endocrinologist, two nurse educators, and one dietician were involved in the second trial. The evaluations provide qualitative support for the relevance of information prioritisation by VT, and show acceptable consumer usability, as well as healthcare provider support, for the portal. The evaluations also revealed further incremental refinements to the information algorithms. / This thesis contributes a specific framework for the use of IT to support the doctor-patient partnership through prioritised information and integrated agenda formulation services. While a larger scale of evaluation is needed to establish patient health benefits, the results of the two initial studies are encouraging. This framework could be adapted for other chronic diseases, such as depression or asthma. It could also be used for other purposes, such as an intelligent information searching facility. A future VT framework should provide more explicit representation of patients' emotional supports and have further mechanisms for promoting patient behaviour changes. / Thesis (PhDInformationTechnology)--University of South Australia, 2005.

Thesis (MEng in Electronic Engineering (Research)) -- University of South Australia, 1995

Knowledge Based Systems (KBS) have been actively investigated since the early period of AI. There are four common methods of building expert systems: modeling approaches, programming approaches, case-based approaches and machine-learning approaches. One particular technique is Ripple Down Rules (RDR) which may be classified as an incremental case-based approach. Knowledge needs to be acquired from experts in the context of individual cases viewed by them. In the RDR framework, the expert adds a new rule based on the context of an individual case. This task is simple and only affects the expert???s workflow minimally. The rule added fixes an incorrect interpretation made by the KBS but with minimal impact on the KBS's previous correct performance. This provides incremental improvement. Despite these strengths of RDR, there are some limitations including rule redundancy, lack of intermediate features and lack of models. This thesis addresses these RDR limitations by applying automatic learning algorithms to reorganize the knowledge base, to learn intermediate features and possibly to discover domain models. The redundancy problem occurs because rules created in particular contexts which should have more general application. We address this limitation by reorganizing the knowledge base and removing redundant rules. Removal of redundant rules should also reduce the number of future knowledge acquisition sessions. Intermediate features improve modularity, because the expert can deal with features in groups rather than individually. In addition to the manual creation of intermediate features for RDR, we propose the automated discovery of intermediate features to speed up the knowledge acquisition process by generalizing existing rules. Finally, the Ripple Down Rules approach facilitates rapid knowledge acquisition as it can be initialized with a minimal ontology. Despite minimal modeling, we propose that a more developed knowledge model can be extracted from an existing RDR KBS. This may be useful in using RDR KBS for other applications. The most useful of these three developments was the automated discovery of intermediate features. This made a significant difference to the number of knowledge acquisition sessions required.

Thesis (Ph. D.)--University of Washington, 1988. / Vita. Includes bibliographical references.

Thesis (M.S.)--West Virginia University, 2008. / Title from document title page. Document formatted into pages; contains xiii, 151 p. : ill. (some col.), col. maps. Includes abstract. Includes bibliographical references (p. 104-107).

Thesis (Ph. D.)--University of Washington, 1989. / Vita. Includes bibliographical references (leaves [107]-110).

Thesis (Ph. D.)--University of New South Wales, 2003. / Also available online.

Thesis (Ph. D.)--Virginia Polytechnic Institute and State University, 1991. / Vita. Abstract. Includes bibliographical references (leaves 190-201). Also available via the Internet

Thesis (Ph. D.)--University of Washington, 1991. / Vita. Includes bibliographical references (leaves [116]-120).

Univ., Diss--Kaiserslautern.