Felipe Mancini

Application of the Intelligent Techniques in Transplantation Databases: A Review of Articles Published in 2009 and 2010

The replacement of defective organs with healthy ones is an old problem, but only a few years ago was this issue put into practice. Improvements in the whole transplantation process have been increasingly important in clinical practice. In this context are clinical decision support systems (CDSSs), which have reflected a significant amount of work to use mathematical and intelligent techniques. The aim of this article was to present consideration of intelligent techniques used in recent years (2009 and 2010) to analyze organ transplant databases. To this end, we performed a search of the PubMed and Institute for Scientific Information (ISI) Web of Knowledge databases to find articles published in 2009 and 2010 about intelligent techniques applied to transplantation databases. Among 69 retrieved articles, we chose according to inclusion and exclusion criteria. The main techniques were: Artificial Neural Networks (ANN), Logistic Regression (LR), Decision Trees (DT), Markov Models (MM), and Bayesian Networks (BN). Most articles used ANN. Some publications described comparisons between techniques or the use of various techniques together. The use of intelligent techniques to extract knowledge from databases of healthcare is increasingly common. Although authors preferred to use ANN, statistical techniques were equally effective for this enterprise.

Evaluation of Learning in Oncology of Undergraduate Nursing with the Use of Concept Mapping.

This study aims to identify whether the use of concept mapping (CM) strategy assists a student to extend and revise their expertise in oncology and analyze the abilities developed in a student in order to go through theoretical to practical knowledge. This study is descriptive and qualitative, with 20 undergraduate students of the Undergraduate Nursing Course of Paulista School of Nursing of Federal University of São Paulo, Brazil. The critical incident technique and content analysis were used. There were 12 categories represented by facilities, difficulties, and learning applicability in oncology provided by CM strategy during the surgical and clinical nursing discipline. The graphics resource, CMapTools®, and the clinical case data arranged in mapping for resolution generated an active search and exercise of self-learning in oncology. Despite the challenges of the use of CM as a teaching strategy—pedagogical, the results suggested an increase of autonomy and clinical reasoning in nursing practice.

Artificial Intelligence Techniques: Predicting Necessity for Biopsy in Renal Transplant Recipients Suspected of Acute Cellular Rejection or Nephrotoxicity

The gold standard for nephrotoxicity and acute cellular rejection (ACR) is a biopsy, an invasive and expensive procedure. More efficient strategies to screen patients for biopsy are important from the clinical and financial points of view. The aim of this study was to evaluate various artificial intelligence techniques to screen for the need for a biopsy among patients suspected of nephrotoxicity or ACR during the first year after renal transplantation. We used classifiers like artificial neural networks (ANN), support vector machines (SVM), and Bayesian inference (BI) to indicate if the clinical course of the event suggestive of the need for a biopsy. Each classifier was evaluated by values of sensitivity and area under the ROC curve (AUC) for each of the classifiers. The technique that showed the best sensitivity value as an indicator for biopsy was SVM with an AUC of 0.79 and an accuracy rate of 79.86%. The results were better than those described in previous works. The accuracy for an indication of biopsy screening was efficient enough to become useful in clinical practice.

Aplicação de Redes Neurais Artificiais na Classificação de Padrões Posturais em Crianças Respiradoras Bucais e Nasais

A respiracao e a primeira funcao vital desenvolvida por ocasiao do nascimento, estabelecendo-se como principal funcao do organismo. A respiracao bucal cronica pode provocar alteracoes posturais, alem de incitar um menor esforco do musculo diafragma. Este artigo tem por objetivo apresentar resultados sobre a aplicacao de um modelo de rede neural artificial nao-supervisionado, especificamente o mapa auto-organizavel ( self-organizing map , SOM), para auxiliar no diagnostico e na avaliacao da evolucao clinica da postura de criancas respiradoras bucais e nasais. Apresentamos como padrao de entrada ao SOM as variaveis de postura e distância da excursao do musculo diafragma de 30 criancas respiradoras bucais e 22 criancas respiradoras nasais. O SOM apresentou taxa de acerto de 95% no diagnostico de criancas respiradoras bucais e nasais. Da topologia resultante foi possivel definir categorizacoes da postura dos pacientes.

Ergonomic Evaluation of the Portal of the Repository in the Health Area of UNIFESP: Proposal of Specifications and Ergonomic Recommendations for Its Interface

The Internet, together with the Digital Information and Communication Technologies (DICT), make it possible to create digital documents (DD) that are responsible for the preservation of cultural heritage, dissemination of information and strengthen the construction of knowledge. These DD allow a wide production, dissemination and preservation of information and, with the help of DICT, enable the communication between researchers and scientists, especially regarding the sharing of research results. Digital repositories are informational environments for managing and controlling the scientific and academic production of institutions and/or communities. They offer advantages such as unrestricted access, data interoperability and long-term information preservation. However, they may have gaps such as browsing failures, poor usability and accessibility, limited searches, poor disclosure of the environment, and little or no use of customizable services. In 2015, the institutional digital repository of the Federal University of Sao Paulo (UNIFESP) was implemented the digital repository in the health area of UNIFESP (RDUNIFESP). Their construction was not user-centered, prototyping tests were not performed, the authors felt difficulty in their navigation and, therefore, it is important to apply an ergonomic evaluation in the RDUNIFESP using the inspection techniques and usability tests, with the objective of supporting users in the development of their activities in a productive, intuitive and safe way. In this way, this work will evaluate and identify points of suitability and inadequacy of usability in RDUNIFESP, and propose specifications and ergonomic recommendations and contribute to the improvement of its interface.

AVALIAÇÃO ERGONÔMICA DE REPOSITÓRIOS DIGITAIS INSTITUCIONAIS

Repositórios digitais são ambientes informacionais para gerenciamento e controle da produção científica e acadêmica de instituições e/ou comunidades. Oferecem vantagens como acesso irrestrito, interoperabilidade dos dados e preservação da informação em longo prazo. Entretanto, eles podem possuir lacunas como falhas de navegação, baixa usabilidade e acessibilidade, buscas limitadas, pouca divulgação do ambiente e pouca ou nenhuma utilização de serviços personalizáveis. A partir desse contexto torna-se necessária uma avaliação ergonômica dos repositórios digitais institucionais. Esta avaliação pode ser realizada utilizando as técnicas de inspeção e testes de usabilidade a fim de propor um conjunto de especificações e recomendações ergonômicas para a sua interface. Pode realizada uma avaliação qualitativa, com abordagem preditiva, com coleta de dados de opinião, e interpretação do laudo emitido pelas ferramentas escolhidas na finalização da aplicação do checklist, para avaliar os repositórios digitais institucionais. E então pode ser realizada uma avaliação qualitativa experimental utilizando cenários de interação com tarefas a serem cumpridas por usuários frequentes. Com os resultados obtidos torna-se possível a identificação e listagem dos pontos de adequação e inadequação de usabilidade, e baseados nesses, poderá ser proposto um conjunto de especificações e recomendações ergonômicas para os repositórios digitais institucionais. As principais contribuições tecnológicas obtidas são a identificação e listagem dos pontos de adequação e inadequação, bem como sugerir um conjunto de especificações e recomendações de melhoria de usabilidade dos repositórios digitais institucionais. As principais contribuições científicas são a divulgação de resultados empíricos com a abordagem e foco na avaliação de usabilidade, e a criação de conjunto de especificações e recomendações para criação e avaliação de repositórios digitais institucionais.