Abstract Data mining is a relatively new field of research whose major objective is to acquire knowledge from large amounts of data. In medical and health care areas, due to regulations and due to the availability of computers, a large amount of data is becoming available. On the one hand, practitioners are expected to use all this data in their work but, at the same time, such a large amount of data cannot be processed by humans in a short time to make diagnosis, prognosis and treatment schedules. A major objective of this thesis is to evaluate data mining tools in medical and health care applications to develop a tool that can help make timely and accurate decisions. Two medical databases are considered, one for describing the various tools and the other as the case study. The first database is related to breast cancer and the second is related to the minimum data set for mental health (MDS-MH). The breast cancer database consists of 10 attributes and the MDS-MH dataset consists of 455 attributes. As there are a number of data mining algorithms and tools available we consider only a few tools to evaluate on these applications and develop classification rules that can be used in prediction. Our results indicate that for the major case study, namely the mental health problem, over 70 to 80% accurate results are possible. A further extension of this work is to make available classification rules in mobile devices such as PDAs. Patient information is directly inputted onto the PDA and the classification of these inputted values takes place based on the rules stored on the PDA to provide real time assistance to practitioners.

Abstract Data mining is a relatively new field of research whose major objective is to acquire knowledge from large amounts of data. In medical and health care areas, due to regulations and due to the availability of computers, a large amount of data is becoming available. On the one hand, practitioners are expected to use all this data in their work but, at the same time, such a large amount of data cannot be processed by humans in a short time to make diagnosis, prognosis and treatment schedules. A major objective of this thesis is to evaluate data mining tools in medical and health care applications to develop a tool that can help make timely and accurate decisions. Two medical databases are considered, one for describing the various tools and the other as the case study. The first database is related to breast cancer and the second is related to the minimum data set for mental health (MDS-MH). The breast cancer database consists of 10 attributes and the MDS-MH dataset consists of 455 attributes. As there are a number of data mining algorithms and tools available we consider only a few tools to evaluate on these applications and develop classification rules that can be used in prediction. Our results indicate that for the major case study, namely the mental health problem, over 70 to 80% accurate results are possible. A further extension of this work is to make available classification rules in mobile devices such as PDAs. Patient information is directly inputted onto the PDA and the classification of these inputted values takes place based on the rules stored on the PDA to provide real time assistance to practitioners.

Information technology (IT) is increasingly being used in the classroom to support instruction. This work addresses the integration of electronic medical records (EMRs) into undergraduate health informatics (HI) education. Such systems have been used to some extent in health professional education but effective integration into HI education remains a gap. This thesis explores the context of integration using the concept of Technological Pedagogical Content Knowledge (TPCK). A structured literature review of previous integration efforts involving EMRs or similar systems in all disciplines was conducted as well as a documentation review specific to undergraduate HI programs to gather insight into current HI education. The findings from these were combined with those of an original qualitative research study done to gather views of instructors and students within one school. This work resulted in an application of TPCK which expands the original framework, describing key findings for the three knowledge bases and adding specific contextual considerations that emerged in terms of when to integrate, instructors, students, courses, technical aspects, system aspects, and overall learning pedagogy. This thesis is organized into nine chapters, beginning with an introduction which explains the rationale for undertaking this work. Next, theoretical perspectives for IT integration are discussed along with the specific EMR integration challenge being addressed. The two additional literature reviews are presented along with their findings which then leads to the research questions for the original study which was undertaken. The next two chapters outline study methods and results. The main questions are then revisited and answered with study findings supplemented by the literature reviews. This leads to the discussion of an initial framework as well as theoretical and practical implications and future research directions for work in this area. / Graduate

Outsourcing involves contracting out a function, or functions, performed by an organization to another organization available in the market. It involves transferring the services, performed by internal staff, as well as the staff themselves, to an external service provider under a contractual agreement. Today in healthcare, many organizations are exploring outsourcing as a way to address demands for health information technology (HIT). This thesis researches the success of outsourcing in the health informatics industry in Canada. The study is designed to help understand whether outsourcing HIT functions, such as development, implementation, operations, and maintenance, can prove successful and result in benefits for an organization. The study finds that outsourcing all four functions of HIT development, implementation, operations, and maintenance occurs in Canada; however, the research from the semi-structured interviews finds that operations and maintenance may be more commonly outsourced in Canada, over development and implementation functions. Despite this, the research from the semi-structured interviews finds that outsourcing development and implementation may actually offer more benefits and fewer challenges than outsourcing operations and maintenance. The research also finds that there can be many benefits of outsourcing for organizations, such as gaining access to expertise and improving service levels, as well as many weaknesses of outsourcing, such as losing internal knowledge and having to manage the change required from outsourcing. The findings from this thesis were used to develop a conceptual model that can be used when an organization is looking at outsourcing. The model considers the inputs and the outputs to outsourcing as an organizational strategy, including the factors that influence an organization’s decision to outsource, the risk and challenges associated with outsourcing, and the expected outcomes and benefits that can result from outsourcing. The study proposes that there are many things that need to be considered when outsourcing to ensure it is successful. / Graduate / 0769 / smalovec@gmail.com

This project sought to develop a system that facilitated the visual inspection of venous leg ulcers by establishing a selection of reliable parameters. The project had three principal aims: to develop a reliable method for capturing the colours exhibited by a venous leg ulcer; to establish a colour range that experienced clinicians believed represented wet necrotic tissue and erythema; and to develop software that highlighted the two manifestations in digital photographs. The project method was divided into three phases. The first phase examined images taken from twenty-two patients over forty-seven episodes of care. During each episode three sequential images were captured using a frame to control for orientation, magnification and lighting resulting in a bank of 141 images. The reliability of the system to accurately capture colour was then determined by examining the amount of colour variation recorded across the set of three images taken at each episode. The second phase asked eight experienced clinicians to examine a set of twenty photographs taken from the bank established in phase one. On each photograph the clinicians were asked to identify areas of wet necrotic tissue or erythema and outline the areas with a colour pen supplied for each manifestation. A colour range was then constructed to represent each manifestation by measuring the range, mean and standard deviation of pixels that were located within the outlined areas. The third phase developed a computerised system that used the colour range established in phase two to highlight areas of a digital image that represented either erythema or wet necrotic tissue. The validity of the highlighted areas was then tested by asking experienced clinicians to identify their level of agreement with the areas selected by the computer system. Analysis of the results from phase one indicated that the system used to record images at each episode of care provided a reliable method for maintaining consistent orientation, magnification and replication of colour. Results from phase two yielded a two distinct colour representation of erythema and wet necrotic tissue. Erythema ranged from 3600 to 3780 of hue with a mean of 369.210, and wet necrotic tissue ranged from 3670 to 3900 of hue with a mean of 387.730. Results from phase three indicated that whilst clearly delineated areas of erythema and wet necrotic tissue were visible, the validity of the representations was varied. 50 per cent of experienced clinicians agreed with the areas selected as erythema and 60 per cent agreed with the areas selected by the computer system as wet necrotic tissue. The system developed during this study for recording images of venous leg ulcers provides a reliable method for further research into the visual progression of this disease. However, the colour range identified as being representative of erythema or wet necrotic tissue and the computer system developed to highlight such areas in a digital image, requires further investigation before it is applicable to the clinical setting. The findings do however provide further insights into the varied nature of expert opinion when judging the colour of venous leg ulceration.

Information Technology (IT) systems have now become an important component of the delivery of healthcare services in Canada. Appropriately supporting healthcare technologies is critical to ensuring successful management and use of these systems. The purpose of this thesis is to determine the challenges and requirements associated with providing support services for healthcare technologies, specifically through the use of standardized IT Service Management (ITSM) frameworks. To accomplish this a systematic review is completed on the implementation, adoption and use of ITSM in healthcare. In addition, a survey of healthcare providers and health informatics professionals is conducted to explore the current gaps and challenges with supporting healthcare technologies. The results of the systematic review and survey are used to define the challenges and requirements of ITSM in the healthcare domain. Using the research findings, a conceptual Health ITSM (HITSM) framework is proposed. / Graduate / 0984 / ppayne@uvic.ca

This thesis examines the potential interface that exists between health information, specifically electronic health record (EHR) systems, and notifiable disease surveillance in Canada. It aims to highlight the benefits and barriers experienced by the current national notifiable disease surveillance strategy, as well as to highlight the successes and roadblocks to the successful implementation and adoption of EHR technologies in Canada. Qualitative methodologies, which include the 16 semi-structured interviews conducted with four key stakeholder groups, including public health experts, physicians, health administrators and academics that are concerned with EHR adoption and public health were used to obtain data. Data from interviews was analysed using grounded theory methodology and then verified using member checking and other data validation methods. Emergent themes from obtained data indicated that there is a large potential for the improvement of the current notifiable disease through the use of EHR technologies: however, the barriers currently faced by both the notifiable disease surveillance system and the state of implementation and adoption of EHR technologies prevent this from occurring. These barriers include political, financial, human, security/privacy, and technology barriers. Differences between stakeholder groups were explored, and potential solutions and insights into existing barriers were provided. The information gained from this study provides insight into the efficiency of the current infectious disease surveillance system and the progress of and need for the implementation of EHRs nationwide. In addition, the results of this study provide stakeholders with a deeper understanding of the barriers facing the use of EHR technologies for infectious disease surveillance and provide a starting place to address these issues. The results of this study can help to inform policy regarding public health surveillance and EHR implementation and adoption.

Indiana University-Purdue University Indianapolis (IUPUI) / Autoimmune Hepatitis (AIH), an incurable chronic condition of unknown cause where the body attacks its own liver, is a rare disease, with a current diagnosed worldwide prevalence of < 150,000. Inadequately treated, AIH can cause progressive liver damage and ultimately liver failure. A wide variety of symptoms are associated with AIH including severe fatigue, joint pain, depression, anxiety, and insomnia. While precision medicine’s genomics has attempted to shed light on the disease, other non-molecular “-omics” approaches can be taken in studying AIH patients, who often utilize social media to gather information from other patients or care providers to apply to their own AIH disease course. It is proposed that these patient-generated social mediomes can create self-report health records for patients – and facets of their lives - otherwise unreachable by conventional research. In this feasibility study, I examined in an exploratory fashion the social mediome of a large (N > 1000) gathering of AIH patients and caregivers as present on a Facebook Group to determine the potential of mining various types health-related user information. The following types of information were mined, with feasible indicating a reliability of F >= 0.670: 1) Types of health information shared and structures of information sharing (Feasible) 2) Types and directionality of support provided by and to users (Portions feasible) 3) Clinical factors (AIH-related and otherwise) disclosed by users a. Medication intake (Feasible) b. Signs and symptoms (including pain and injury) and diagnosed comorbidities (Portions feasible) c. Results of disease monitoring blood tests (Portions feasible) 4) Contextual (non-clinical; environmental; social) factors disclosed by users (Detection of which type of factor discussed occasionally feasible). The resulting knowledge is required to adequately describe the disease not only clinically, but also environmentally and socially, and will form part of the basis for future disease studies.

This thesis focuses on the different aspects of role-play as an approach for user-centred design of mobile information technology (IT). This is done through development of a sequence of workshops and reflecting on the outcome. The motivation for the thesis has been to develop an understanding of the important conditions for involving end-users in the process of understanding user needs and exploring requirements for mobile IT. The need for new methods to understand mobile IT and the focus on user involvement in the traditions of participatory design and user-centred design established the background for the work. Most of the workshops were carried out in a hospital context. The overall research approach has been to work iteratively by carrying out a set of smaller studies, so-called workshops. The research design was flexible, characterized by a design that evolves, develops and unfolds, as the research proceeds. The current state of the knowledge on role-play called for a qualitative approach with a focus on understanding important issues concerning user role-plays. The overall research subject of this thesis is: Develop understanding of key premises for using role-play with low-fidelity prototyping to involve end-users in exploring user needs and requirements for mobile IT. This research subject was further divided into three specific research questions: What are the important issues related to planning and running of role-play design workshops with end-users? What do system developers perceive as the strengths and limitations of such role-play workshops as a system development method? What is the role of the workshop facilitators in such role-play work­shops? Five categories of issues of importance for planning and running of role-play workshops with end-users were identified: practicalities, user role-playing, idea generation, workshop resources and roles in the workshop. The system developers regarded the approach as useful for several reasons including enhancing user involvement, helping developers understand the context of use, and creating a focus in a project. The developers also called attentions to limitations of using role-play; such as a narrow user view on the system that does not take system development premises into account. One of the issues that emerged as a particularly important factor in the workshops was the role-play facilitator’s skills in leading the role-play part and the idea generation process. A framework developed by Yardley-Matwiejcsuk proved useful for understanding how to develop and rehearse these kinds of role-play. The thesis contributes with an understanding of different aspects regarding role-play workshops with end users in the field of Human-Computer Interaction.

Due to the complicated nature of medical information needs, the time constraints of clinicians, and the linguistic complexities and sheer volume of medical information, most medical questions go unanswered. It has been shown that nearly all of these questions can be answered with the presently available medical sources and that when these questions get answered, patient health benefits. In this work, we design and describe a framework for Evidence-Based medical information research and delivery, MedicInfoSys. This system leverages the strengths of knowledge-based workers and of mature knowledge-based technologies within the medical domain. The most critical element of this framework, is a search interface, PifMed. PifMed uses gold-standard MeSH categorization (presently integrated into medline) as the basis of a navigational structure, which allows users to browse search results with an interactive tree of categories. Evaluation by user study shows it to be superior to PubMed, in terms of speed and usability.