Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2017-04-19T16:13:06Z No. of bitstreams: 1 William Hart Oliveira_.pdf: 1603577 bytes, checksum: 0fec245f4abb48747a3fd395b8984212 (MD5) / Made available in DSpace on 2017-04-19T16:13:06Z (GMT). No. of bitstreams: 1 William Hart Oliveira_.pdf: 1603577 bytes, checksum: 0fec245f4abb48747a3fd395b8984212 (MD5) Previous issue date: 2016-07-19 / CAPES - Coordenação de Aperfeiçoamento de Pessoal de Nível Superior / PROSUP - Programa de Suporte à Pós-Gradução de Instituições de Ensino Particulares / A computação móvel pode ser definida como informação na ponta dos dedos a qualquer hora, em qualquer lugar e avança como uma realidade nas tarefas e atividades das pessoas, em decorrência da popularização e diversificação de dispositivos móveis e redes sem fio. Faz-se importante então, desenvolver modelos que permitam não somente compartilhar dados clínicos, mas sim aumentar a longevidade dos dados, melhorar a sua qualidade, tornar os dados independentes da tecnologia usada e cientes de contexto. Neste cenário, o presente trabalho, denominado PEPContextual, consiste em um modelo que faz uso da ciência da situação (situation awareness), explorando informações relacionad as com o ambiente ou com os próprios usuários e onde diversos tipos de contextos são aglomerados de forma a gerar uma visualização mais rica, complexa e inteligente, criando inúmeras possibilidades, dentre elas, a inferência de riscos associados ao paciente. A contribuição principal deste trabalho está relacionada na identificação da dados de PHR do paciente e do uso da ciência da situação a fim de que seja possível realizar inferências de sintomas e possíveis diagnósticos. O modelo foi avaliado de duas formas: A primeira avaliação por estudo de caso confirmou a expectativa de que a aplicação de ciência de situação, baseada no modelo de Endsley, possibilitaria que o modelo de forma ubíqua detectasse riscos associados ao paciente; A segunda avaliação contemplou a usabilidade do modelo, como facilidade de uso e utilidade onde a maioria dos utilizadores considerou que as informações inferidas podem auxiliar diariamente em tratamentos. / Ubuiquitous computing can be defined as information at anytime, anywhere and its grows as a reality on people‘s activities and daily tasks through the diversification and popularization of mobile devices and networks. So, it‘s important create models that allow not only share clinical data, but increase its quality, making it indifferent to technology and context aware. In this case, the present paper, called PEPContextual, is about a model that makes use of situation awareness, exploring environment related information and/or its own users, where several types of contexts are combined looking a richer, complex and smart visualization, creating several possibilities and, among that, the inferrence of associated risks to patients. The main contribution of this paper is related to make use of PHR data and situation awareness in order to inferrence symptoms and some diagnoses. The model was evaluated by two distinct ways: The first evaluation by case study has confirmed the proposal that situation awareness, based on Endsley model, makes possible that the model is capable to find associated risks through ubiquity; The second evaluation measured the usability of the model, as the ease of use and utility where most of users had considered that inferrence information can help on daily treatments.

Automatic data extraction from medical legacy systems into archetype-based systems is analyzed, developed and tested in this work. Electronic health record system (EHRS) is a must in today’s healthcare environment. Lots of up-to-date medical systems are still built with classic development approaches, with semantics hard coded into systems. Modern EHRS standards propose new “two-level” methodology, which is based on separation of knowledge and information levels. This work suggests a methodology for heterogenic medical legacy systems that exist today to be transformed into ones, built with “two-level” methodology. Transformation is based on knowledge, residing in new system. By creating a comprehensive transformation scheme, it is possible to analyze and extract relevant data from semi structured or unstructured text fields with mixed information. Suggested methodology is tested with software prototype by extracting laboratory results of clinical blood test from semi structured fields of cardiology database. Achieved results are about 95% of data successfully transferred from legacy system. This approach preserves medical data accumulated during long years of work and transforms it into more useful form, creating structured data from unstructured text fields. It allows an automatic means of information technologies to be used by medicine expert to analyze and interpret legacy data (draw charts, calculate statistics and so on).