Introduction A plethora of health indicators have been added into the District Health Information System (DHIS) since its adoption and implementation as the routine health information for South Africa in 1999. The growing demand for the production and dissemination of routine health information has not been equally matched by improvements in the quality of data. In the health sector the value of monitoring and evaluation is not simply the product of conducting monitoring and evaluation but, rather from discussing and using performance indicators to improve health service delivery. Aim The aim of this study was to classify health care indicators in the national health data sets used for planning, monitoring and evaluation and to review the data management practices of personnel at provincial and district level. Methods An observational, cross sectional study with a descriptive component was conducted, in 2009, using a finite sample population from district and provincial level across eight provinces. The study participants completed a self-administered questionnaire which was e-mailed to them. Results A total of 32 (52%) participants responded to the questionnaire and of this total 21 (65.5%) responses were from district level and 11 (34.4%) from provincial level. The National Indicator Data Set, the key source for primary health care and hospital data, was implemented in 1999 with approximately 60 indicators. In less than 10 years it has grown in size and presently contains 219 performance indicators that are used for monitoring and evaluating service delivery in the public health sector. Whilst both district and provincial level personnel have a high awareness (83%) of the DHIS data sets there is variability in the implementation of these data sets across provinces. The number of indicators collected in the DHIS data sets for management decisions are “enough”, however a need was expressed for the collection of community health services data and district level mortality data. Similarities were noted with other studies that were conducted nationally with respect to data sharing, utilisation and feedback practices. Data utilisation for decision making was perceived by district level personnel to be adequate, whereas provincial level personnel indicated there is inadequate use of data for decision making. Whilst 87.1% of personnel indicated that they produce data analysis reports, 71.9% indicated that they never get feedback on the reports submitted. The top 4 data management constraints include: lack of human resources, lack of trained and competent staff, lack of understanding of data and information collected and the lack of financial and material resources. There was agreement by district and provincial level personnel for the need for additional capacity for data collection at health facility level. Discussion The increasing need for accurate, reliable and relevant health information for planning, monitoring and evaluation has highlighted critical areas where systems need to be developed in order to meet the information and reporting requirements of stakeholders at all levels in the health system Recommendations An overarching national policy for routine health information systems management needs to be developed which considers the following: emerging national and international reporting requirements, human resources requirements for health information and integration of systems for data collection. In the short-term a review of the National Indicator Data Set needs to be conducted. / Thesis (MMed.)-University of KwaZulu-Natal, Durban, 2010.

This dissertation aims at the general goal of solving the problem of representing and processing information on conceptual principles, in an unsupervised, human-like manner, and using existing computational methods. Given this very general context, the need for intelligent applications that meet the complexity and sensitivity requirements of Medical Informatics is postulated in what is referred to as "the axiom of medical information systems." The reformulation of the axiom that "medical information systems must be, at the same time, usable and useful" leads naturally to the identification of more immediate. achievable objectives in the form of context dependent information processing and case-based reasoning research on memory models capable of unsupervised representation and processing of information. in a similarity-based manner. Further, the unification of these objectives is proposed in the form of the general problem of managing associative concept representation spaces characterized by four fundamental properties: high dimensionality, sparseness, dynamicity and similarity based organization. The thesis of this dissertation is that the solution to this problem can be approached in the most appropriate way by memory models that specifically address each and every one of the four fundamental properties. The support for the thesis is twofold and comprises theoretical accounts which lead naturally to the definition of a memory model. the deterministic dynamic associative memory model (DDAM) which is based on the existing mathematical structure of partial order set. The model is first introduced informally by means of examples and depictions that speak for its usability. Further the formal description of the DDAM model and learning algorithms is achieved using existing fundamental concepts of set theory and combinatorics. Finally, the DDAM model is evaluated and compared with existing approaches in a series of experiments and simulations that demonstrate usefulness comparable or superior to existing approaches.

Healthcare Informatics suffers from the lack of information exchange among domain partners. Allowing cooperation among distributed and heterogeneous applications is a major need of current healthcare information systems. Beyond the communication and integration problems, medical information itself is by nature complex, combined with data and knowledge. The increasing number of standards and representation of the same data in different structures using these standards constitute another problem in the domain. Platform and implementation independency makes Web service technology the natural way to solve the interoperability problems in the healthcare domain. Standardizing the access to data through WSDL and SOAP rather than standardizing the electronic health record will help to overcome the integration problems among different standards in medical information systems. However, introducing Web services to the healthcare systems will not suffice to solve the problems in the domain unless the semantics of the services are exploited. This thesis aims to show that by generating web services and classifying these services through their functionalities, it is possible to achieve the interoperability among healthcare institutes, such as hospitals. The designed system is based on Artemis P2P Framework, and the annotation of the system is realized in the same framework.

Diss. Linköping : Univ., 2003.

Diss. (sammanfattning) Stockholm : Karolinska institutet, 2005. / Härtill 4 uppsatser.

Diss. (sammanfattning) Stockholm : Karolinska institutet, 2006. / Härtill 4 uppsatser.

Thesis (Ph.D)--University of Wollongong, 2005. / Typescript. Includes bibliographical references: leaf 170-205.

Thesis (Ph.D.)--Victoria University (Melbourne, Vic.), 2008.

Thesis (M. Sc.)--Carleton University, 2004. / Includes bibliographical references (p. 69-72). Also available in electronic format on the Internet.

Thesis (M.App.Sc.) - Carleton University, 2006. / Includes bibliographical references (p. 92-105). Also available in electronic format on the Internet.