No description available.

Electronic Healthcare Records (EHRs) are valuable resources, shared across all three subdomains of healthcare: research, policy and practice. The content of these EHRs need to be fit for making critical decisions required for effective and high quality clinical care. The management of the fitness for the purposes of EHR is a well known problem referred to as 'the data quality problem'. within the health care domain, Information Quality (IQ) forms an indirect relation with the quality of service or has a direct impact on decision making. One of the approaches to the management of this problem and its adverse effect on clinical care is through continuous assessment, monitoring and review of its fitness for required purposes. A key challenge to the management of the IQ problem in the health care setting, is having to deal with both objective and subjective determinants of quality in a uniform way on large amount of heterogeneous data and information with complex interdependencies. Whilst the objective determinants like accuracy, completeness, etc. has been well formulated, the subjective determinants like accessibility, confidentiality, privacy, etc. have not been logically formulated. The work presented in this thesis form a step towards a unified logical way to the assessment of the fitness for purpose of data and information from the healthcare context for the activities performed as part of the work flow followed by clinicians during patient care. This thesis makes two main contribution to the assessment of the data and information quality problem for EHRS. First, a model named LOgical Quality (LOQ), which models IQ assessment using fuzzy set and fuzzy logic and thus enables a logical formulation and quantification of both objective and subjective quality. The other contribution, a framework called Process-centric framework for IQ (PROF), builds on the logical model to create a process centric framework using clinical pathways as the source for deriving and generating disease specific IQ rules for the assessment. The clinical pathways, which are disease centric, are also used to determine the evaluation order of the derived quality rules. Given an appropriate domain knowledge representation of the care context and workflow, the two contributions form a road map towards the development of automated online IQ assessment techniques.

Electronic Patient Records have opened up the possibility of re-using the data collected for clinical practice, to support both clinical practice itself, and clinical research. In order to achieve this re-use, we have to address the issue that most Electronic Patient Records make heavy use of narrative text. This thesis reports an approach to automatically extract clinically significant information from the textual component of the medical record, in order to support re-use of that record. The cost of developing such information extraction systems is currently seen to be a barrier to their deployment. We explore ways of lowering this barrier, through the separation of the linguistic, medical and engineering knowledge and skills required for development. We describe a rigorous methodology for the construction of a corpus of clinical texts semantically annotated by medical experts, and its use to automatically train a supervised machine learning-based information extraction system. We explore the re-use of existing medical knowledge in the form of terminologies, and present a way in which these terminologies can be coupled with supervised machine learning for information extraction. Finally, we consider the extent to which pre-existing software components can be used to construct a clinical IE system, and build a system that is capable of extracting clinical concepts, their properties, and the relationships between them. The resulting system shows that it is possible to achieve separation of linguistic, medical and engineering knowledge in clinical information extraction. We find that existing software frameworks are capable of some aspects of information extraction with little additional engineering work, but that they are not mature enough for the construction of a full system by the non-expert. We also find that a new cost is introduced in separating domain and linguistic knowledge, that of manual annotation by domain experts.

No description available.

The historical evolution of South Africa’s health sector, dating back to the 17th century, is significantly different from that of other African countries. Throughout the four centuries of development there have been numerous advances in health policy, legislative instruments and health system progress. Against this background this dissertation critically analysed the management of records in public health care institutions in South Africa. The study did this by addressing three objectives: assess the legislative, policy and regulatory contextual framework of South Africa’s health care system; assess the effectiveness of records management within public health care institutions; and identify appropriate interventions to address the challenges facing records management in the health care system. The study used purposive sampling to identify respondents with diverse expertise in three main sectors: the public sector, the private sector as well as in academic and research institutions. Using interview research technique the study solicited data that was analysed in order to provide a composite picture in addressing the research objectives. The analysis of data revealed three overarching themes. First, there is substantial legislative and regulatory dissonance in the management of health records in the country. While there are extensive legislative, regulatory and policy instruments that could be used to manage records, many lack coherence with records management issues such as records retention. Second, understanding the complex interplay of different legal and regulatory instruments is a critical first step, but it remains the beginning of the process towards building a sophisticated implementation process. For this process to be successful, study respondents argued that records compliance would have to be the backbone of all other compliance processes. Third, while there were substantial areas of weakness in the management of records in South Africa’s public health sector, there have been a number of pockets of excellence. These include the efforts towards complying to access to information legislation by the Limpopo Department of Health and Social Development as well as the successful introduction of Enterprise Content Management systems in health care institutions by the Western Cape Department of Health / Information Science / D. Litt. et Phil. (Information Science)

The historical evolution of South Africa’s health sector, dating back to the 17th century, is significantly different from that of other African countries. Throughout the four centuries of development there have been numerous advances in health policy, legislative instruments and health system progress. Against this background this dissertation critically analysed the management of records in public health care institutions in South Africa. The study did this by addressing three objectives: assess the legislative, policy and regulatory contextual framework of South Africa’s health care system; assess the effectiveness of records management within public health care institutions; and identify appropriate interventions to address the challenges facing records management in the health care system. The study used purposive sampling to identify respondents with diverse expertise in three main sectors: the public sector, the private sector as well as in academic and research institutions. Using interview research technique the study solicited data that was analysed in order to provide a composite picture in addressing the research objectives. The analysis of data revealed three overarching themes. First, there is substantial legislative and regulatory dissonance in the management of health records in the country. While there are extensive legislative, regulatory and policy instruments that could be used to manage records, many lack coherence with records management issues such as records retention. Second, understanding the complex interplay of different legal and regulatory instruments is a critical first step, but it remains the beginning of the process towards building a sophisticated implementation process. For this process to be successful, study respondents argued that records compliance would have to be the backbone of all other compliance processes. Third, while there were substantial areas of weakness in the management of records in South Africa’s public health sector, there have been a number of pockets of excellence. These include the efforts towards complying to access to information legislation by the Limpopo Department of Health and Social Development as well as the successful introduction of Enterprise Content Management systems in health care institutions by the Western Cape Department of Health / Information Science / D. Litt. et Phil. (Information Science)