Using data mining for prediction of hospital length of stay: an application of the CRISP-DM Methodology

Hospitals are nowadays collecting vast amounts of data related with patient records. All this data hold valuable knowledge that can be used to improve hospital decision making. Data mining techniques aim precisely at the extraction of useful knowledge from raw data. This work describes an implementation of a medical data mining project approach based on the CRISP-DM methodology. Recent real-world data, from 2000 to 2013, were collected from a Portuguese hospital and related with inpatient hospitalization. The goal was to predict generic hospital Length Of Stay based on indicators that are commonly available at the hospitalization process (e.g., gender, age, episode type, medical specialty). At the data preparation stage, the data were cleaned and variables were selected and transformed, leading to 14 inputs. Next, at the modeling stage, a regression approach was adopted, where six learning methods were compared: Average Prediction, Multiple Regression, Decision Tree, Artificial Neural Network ensemble, Support Vector Machine and Random Forest. The best learning model was obtained by the Random Forest method, which presents a high quality coefficient of determination value (0.81). This model was then opened by using a sensitivity analysis procedure that revealed three influential input attributes: the hospital episode type, the physical service where the patient is hospitalized and the associated medical specialty. Such extracted knowledge confirmed that the obtained predictive model is credible and with potential value for supporting decisions of hospital managers.

Lightweight adjustable partition system: evaluation of resistance to horizontal loads and functional failure from impacts

This paper presents and discusses the results of the serviciability and use condition tests carried on an innovative solution for partitions, designated AdjustMembrane developed within a research project. The proposed system is a modular non-loadbearing wall, tensioned between the pavements and ceiling slabs, which are used as anchoring elements. It allows several advantages, related with the weight reduction to achieve a good sustainable performance, such as the reduction of construction costs, energy, and materials, and it is easy to recycle and to reuse, allowing self-construction. Apart from a general presentation of the partition technology, this paper presents and discusses the results of experimental tests carried out. From the results obtained, it is possible to conclude that the solution fulfils the requirements for this typology of wall in terms of resistance to horizontal loads induced by soft and hard body impacts.

Tempos sociais e o mundo contemporâneo: as crises, as fases e as ruturas

(Excerto) O presente ebook compõe-se do conjunto de comunicações apresentadas no seminário “Tempos Sociais e o mundo contemporâneo – fases, crises e ruturas”, realizado em novembro de 2013, na Universidade do Minho. Os textos que se apresentam vertem as influências disciplinares dos diversos autores, apresentando pontos de vista específicos sobre diversos fenómenos analisados, na perspetiva do tempo e das temporalidades. Michelle Bastian afirma que o tempo não é um recipiente neutro para a vida social, mas uma fonte de valores, conceitos e lógicas que são usados para negociar a complexidade da vida social. Com efeito, as sociedades atuais são marcadas por vários processos de transformação que implicam alterações significativas na forma de perceber e de usar o tempo. Algumas das palavras mais frequentes usadas na classificação do estado do social e do político são crise, fase e rutura. Trata-se de palavras aplicadas aos mais diversos níveis. Porque são socialmente constituídas, traduzem os modos pelos quais a sociedade se pensa e analisa a si própria. É nesse sentido que merecem ser estudadas. Qualquer uma destas palavras contém a ideia de corte num determinado processo temporal com caraterísticas próprias e qualquer uma delas contem, em potência, a sua superação. Tem primeiramente, um papel substantivo na forma como permitem uma certa leitura da sociedade atual. Um número crescente de autores tem vindo a dar atenção ao surgimento de novas experiências e expressões de tempo que consideram ser um resultado de tendências contemporâneas que caracterizam a expansão da sociedade em rede, da digitalização, das novas formas de interação e mediatização individual e institucional, assim como da aceleração (Hassan, 2010; Hope, 2009; Rosa, 2005; Scheuerman, 2004). Ideias tais como o fim do futuro, recessão, desigualdades temporais, surgimento de identidades em fluxo, e, ainda, as novas percepções sobre o passado, o presente e o futuro são exemplos das temáticas em discussão.

Finite integration methods for isospectral flows

In this paper we consider the approximate computation of isospectral flows based on finite integration methods( FIM) with radial basis functions( RBF) interpolation,a new algorithm is developed. Our method ensures the symmetry of the solutions. Numerical experiments demonstrate that the solutions have higher accuracy by our algorithm than by the second order Runge- Kutta( RK2) method.