Thesis (DPhil (Informatics))--Cape Peninsula University of Technology, 2018. / As in many parts of the world, the need for healthcare services is increasing rapidly in South Africa. Owing to many official languages in the country, health service delivery is continuously challenged by spoken language and semantics. The challenges result to poor health services in many areas of the country. Thus, this study was undertaken with the aim: to develop a framework which can be used to guide the selection and implementation of mobile systems in the translation of language semantics for improved healthcare service delivery in South Africa. For this purpose, the study was based on one significant research question: How can the challenge(s) of semantics and language translation in South African healthcare delivery be addressed using mobile systems? In achieving the aim of the study, a qualitative study was conducted using the semi-strtructured interviews to collect the data. The analysis of the data was carried out using the hermeneutic approach within the interpretative paradigm, which was guided by two theories, actor network theory (ANT) and diffusion of innovation (DOI). The ANT was used to focus on the interaction and relationship between human and non-human actors within a heterogeneous networks, in the activities of healthcare. The DOI was employed to examine how mobiles systems can be diffused, in addressing the challenges and barriers which the health facilities encounter from language perspective. The case study approach was followed, based on three cases, two healthcare organisations, and a community in the northern part of South Africa were used in the study. Based on the analysis of the data, the influencing factors were found, and interpreted. The interpretation helps gain deeper understanding of the challenges, from which a framework (see Figure 6.5 in Chapter 6) was developed. From an understanding of the factors that influence language semantics, and its translaton by using mobile systems, challenges in the South African healthcare can be reduced, and quality improved. The way in which the theories were used brought a fresh perspective to the study. In practice, the framework can be used by both healthcare practitioners and ICT specialists to guide the selection, use and support of mobile systems for the translation of language semantics in South Africa. The complementary use of ANT and DOI in the study contributes methodologically.

Lau, Siu Him. / "November 2009." / Thesis (M.Phil.)--Chinese University of Hong Kong, 2010. / Includes bibliographical references (leaves 46). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.7 / Chapter 2 --- Support Vector Machine --- p.9 / Chapter 2.1 --- Two-Class Support Vector Machine --- p.9 / Chapter 2.2 --- Kernel Tricks --- p.12 / Chapter 2.3 --- Weighted Support Vector Machine --- p.14 / Chapter 2.4 --- Parameter Selection in Support Vector Machine --- p.16 / Chapter 3 --- Feature Selection Methods --- p.17 / Chapter 3.1 --- Principle Component Analysis --- p.17 / Chapter 3.1.1 --- Maximizing Variance --- p.17 / Chapter 3.1.2 --- Relation with Singular Value Decomposition --- p.19 / Chapter 3.1.3 --- Feature Selection by Singular Value Decomposition --- p.20 / Chapter 3.1.4 --- Disadvantage of Unsupervised Learning --- p.21 / Chapter 3.2 --- Linear Discriminant Analysis --- p.21 / Chapter 3.2.1 --- Between-class Distance and Within-class Variance --- p.22 / Chapter 3.2.2 --- Generalized Eigenvalue Problem --- p.24 / Chapter 3.2.3 --- Feature Selection by Linear Discriminant Analysis --- p.25 / Chapter 4 --- Application on a Real Problem --- p.27 / Chapter 4.1 --- Problem and Goals --- p.27 / Chapter 4.2 --- Diabetes Data Set --- p.27 / Chapter 4.3 --- Data Processing --- p.28 / Chapter 4.3.1 --- Pre-processing for Categorical Data --- p.28 / Chapter 4.3.2 --- Handling Uneven Data Set --- p.31 / Chapter 5 --- Results on Simulated and Real Data --- p.33 / Chapter 5.1 --- Evaluation --- p.33 / Chapter 5.1.1 --- Training and Testing --- p.33 / Chapter 5.1.2 --- Evaluation Method --- p.34 / Chapter 5.2 --- Classification Procedure --- p.35 / Chapter 5.3 --- Performance on Simulated Data --- p.36 / Chapter 5.4 --- Results on a Real Data Set --- p.39 / Chapter 5.4.1 --- Features Selection --- p.39 / Chapter 5.4.2 --- Performance on the Real Data Set --- p.41 / Chapter 5.4.3 --- Analysis on Risk Factors --- p.42 / Chapter 6 --- Conclusion --- p.44 / Bibliography --- p.46

O objetivo deste trabalho foi desenvolver um software de computador que gerencie um banco de dados contendo informações sobre avaliação da voz e o exame de fonetografia e que confeccione o fonetograma (gráfico). Através da utilização de software de desenvolvimento de sistemas (Delphi), foi criado um programa com a finalidade de gerenciar um banco de dados (Paradox), com informações referentes ao exame de fonetografia e, baseado nestes dados, gerar o gráfico do fonetograma. Para a avaliação deste software foram introduzidos no sistema os dados de 30 fichas, contendo as informações de exames de fonetografia já realizados, no intuito de verificar da sua capacidade de gerenciar estas informações e traçar seus gráficos. O programa mostrou-se capaz de realizar o armazenamento dos dados, a consulta de informações e a geração do fonetograma. Sua utilização poderá ser muito útil para melhorar a organização dos dados dos exames, agilizar a interpretação dos resultados e facilitar a interação entre clínico e paciente, tornando-se assim um valioso instrumento na aplicação da fonetografia / The aim of this study was to develop a computer software in order to manage a data base with information collected during phonetography, which allows the program to produce a phonetogram graph. The computer software was obtained through Delphi Developer and the data base used was Paradox. The data of 30 forms of phonetography test were introduced in the system in order to evaluate, to store the data, to make the data available for consulting and to produce the phonetogram successfully. The developed software will be very useful to improve the organization of the test data, to speed up the comprehension of the results and to facilitate the interaction between the clinician and patient

Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2018. / Healthcare facilities in South Africa accumulate big data, daily. However, this data is not being utilised to its full potential. The healthcare sector still uses traditional methods to store, process, and analyse data. Currently, there are no big data analytics tools being used in the South African healthcare environment. This study was conducted to establish what factors hinder the effective use of big data in the South African healthcare environment. To fulfil the objectives of this research, qualitative methods were followed. Using the case study method, two healthcare organisations were selected as cases. This enabled the researcher to find similarities between the cases which drove them towards generalisation. The data collected in this study was analysed using the Actor-Network Theory (ANT). Through the application of ANT, the researcher was able to uncover the influencing factors behind big data analytics in the healthcare environment. ANT was essential to the study as it brought out the different interactions that take place between human and non-human actors, resulting in big data. From the analysis, findings were drawn and interpreted. The interpretation of findings led to the developed framework in Figure 5.5. This framework was developed to guide the healthcare sector of South Africa towards the selection of appropriate big data analytics tools. The contribution of this study is in twofold; namely, theoretically and practically. Theoretically, the developed framework will act as a useful guide towards the selection of big data analytics tools. Practically, this guide can be used by South African healthcare practitioners to gain better understanding of big data analytics and how they can be used to improve healthcare service delivery.

The controlled experiment is a highly regarded form of scientific inquiry because its properties permit conclusions with the most scientific rigor. Controlled experimentation is important for the scientific foundation of disciplines that claim to be scientific. It is also important to conduct them properly: they come at a high cost in time, effort and participation; there is an associated esteem that confers credibility; there is often an ethical responsibility to human participants. However, the quality of controlled experiments performed in health informatics and computer science is often poor. One way to address quality issues is to measure quality. This follows the example of the creation of instruments (scales or scores) to measure quality of controlled medical trials, which have also had problems with experimental quality. The rationale for this research was that no satisfactory scales had been developed for informatics. There is also no empirical research into the construct of experimental quality in informatics, which this research addresses. / Doctor of Philosophy (PhD)

Existing patient medical records are a rich data source with a potential to support clinical research. Fragmentation of data across disparate medical database inhibits the use of these existing datasets. Overcoming such disjointedness is possible through the use of a data warehouse. Once the data is cleansed, transformed, and stored within the data warehouse it is possible to turn attention to the exploration of the medical datasets. Exploratory and confirmatory Data Mining Tools are well suited to such activities. This thesis concerned with: demonstrating parallels between scientific method and CRISP-DM; extending CRISP-DM for use with medical datasets; and proposal of the supporting Intelligent Decision Support System framework. This research has been undertaken using a fetal-maternal case study. / Master of Science (Hons)

Introduction - Eighty five per cent of Australians visit a GP each year, but do not receive all of the preventive care which is indicated for them. There have been no controlled trials of the effects of on-screen preventive care reminders in Australian general practice, and there is little published research examining characteristics of patients, doctors and consultations associated with the performance of preventive services in general practice. This study aimed to measure the effects of opportunistic reminders and to explore previously unexamined patient, GP and consultation factors associated with performance of preventive activities. The hypotheses were : a ) that general practitioners who were using a computer medical record system would take at least fifteen per cent more of opportunities to perform preventive care activities if they were reminded ; b ) that this would occur without any significant increase in the number of consultations or in patient billings ; and c ) that every characteristic of patients, GPs, consultations and preventive opportunities would be significantly associated with the performance of the preventive activities. Method - All patients who attended a ten GP fully computerised practice during one year were enrolled and randomised either to an intervention group, for whom the GPs received opportunistic on-screen reminders about eleven preventive activities, or to a 'usual care' control group. Performance by the GPs of the preventive activities was recorded automatically and correlated with routinely-collected demographic and clinical information about the patients and billing data. Results - For the intervention group compared to the control group, the GPs took thirty two per cent more of the preventive opportunities without any increase in numbers of services or in patient billings. Every characteristic of patients, GPs, consultations and preventive opportunities was independently associated with the performance of at least two of the preventive activities. Discussion - This trial has shown that a low cost minimally-intrusive intervention in the form of automated opportunistic reminder messages can significantly improve GPs' performance of preventive care activities. The findings of this trial may help to improve the design and effectiveness of opportunistic reminders in clinical software, and provide direction about possible changes to the health system which may foster increased provision of preventive care. / Thesis (Ph.D.)--University of Adelaide, School of Population Health and Clinical Practice, Discipline of General Practice, 2006.

<p>KTH, Division of Neuronic Engineering, have a finite element model of the head. However, this model does not contain detailed modeling of the brain. This thesis project consists of finding a method to extract brain tissues from T1-weighted MR images of the head. The method should be automatic to be suitable for patient individual modeling.</p><p>A summary of the most common segmentation methods is presented and one of the methods is implemented. The implemented method is based on the assumption that the probability density function (pdf) of an MR image can be described by parametric models. The intensity distribution of each tissue class is modeled as a Gaussian distribution. Thus, the total pdf is a sum of Gaussians. However, the voxel values are also influenced by intensity inhomogeneities, which affect the pdf. The implemented method is based on the expectation-maximization algorithm and it corrects for intensity inhomogeneities. The result from the algorithm is a classification of the voxels. The brain is extracted from the classified voxels using morphological operations.</p>

No description available.

<p>I dagens samhälle är det vanligt att patienter söker vård hos olika vårdgivare, vilket resulterar i att vårdinformationen blir splittrad och allt högre krav ställs på de datoriserade journalsystemen. Till exempel ska de stödja ett processorienterat arbetssätt för att samla information från samma vårdprocess. Vårdinformationen måste därför vara tillgänglig över organisationsgränser och olika journalsystem måste kunna kommunicera med varandra, där en ökad tillgänglighet ställer högre krav på informationssäkerhet och behörighetskontroll. Journalsystemen bör, för att uppfylla dessa krav, utvecklas enligt standarder och riktlinjer.</p><p>Det finns ett flertal nationella och internationella organisationer som arbetar med att ta fram standarder och riktlinjer för hur journalsystem bör utvecklas. Problemet är att dessa arbeten sker på olika nivåer och gäller olika delar av journalsystemen. Det är därmed en stor utmaning för journalleverantörer att förhålla sig till dessa arbeten. Syftet med det här examensarbetet har varit att utreda hur utvalda, svenska och europeiska, standardiseringsarbeten förhåller sig till varandra samt att avgöra på vilket sätt de är av relevans för journalleverantörer. Dessutom har syftet varit att framställa en prototyp av ett IT-stöd för processorienterad vårddokumentation.</p><p>En kvalitativ litteraturstudie har i det här examensarbetet resulterat i en sammanställning av de utvalda standardiseringsarbetena. Arbetena hanterar främst områden som kan användas för att ena vårdprocessen, exempel på dessa är behörighetskontroll och standardiserad kommunikation med informationsspecifikationer eller arketyper. SAMBA har tagit fram en processmodell som beskriver vårdprocessen. Baserat på denna modell och krav från standardiseringsarbetena har vi framställt ett förslag på ett IT-stöd för processorienterad vårddokumentation.</p>