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.

Analytical approach for the flexural analysis of RC beams strengthened with prestressed CFRP

The objective of this paper is to propose a simplified analytical approach to predict the flexural behavior of simply supported reinforced-concrete (RC) beams flexurally strengthened with prestressed carbon fiber reinforced polymer (CFRP) reinforcements using either externally bonded reinforcing (EBR) or near surface mounted (NSM) techniques. This design methodology also considers the ultimate flexural capacity of NSM CFRP strengthened beams when concrete cover delamination is the governing failure mode. A moment–curvature (M–χ) relationship formed by three linear branches corresponding to the precracking, postcracking, and postyielding stages is established by considering the four critical M–χ points that characterize the flexural behavior of CFRP strengthened beams. Two additional M–χ points, namely, concrete decompression and steel decompression, are also defined to assess the initial effects of the prestress force applied by the FRP reinforcement. The mid-span deflection of the beams is predicted based on the curvature approach, assuming a linear curvature variation between the critical points along the beam length. The good predictive performance of the analytical model is appraised by simulating the force–deflection response registered in experimental programs composed of RC beams strengthened with prestressed NSM CFRP reinforcements.

Thermo-compression molding of chitosan with a deep eutectic mixture for biofilms development

Supplementary information available at: http://www.rsc.org/suppdata/c5/gc/c5gc02231b/c5gc02231b1.pdf

Evaluation of seismic vulnerability assessment parameters for portuguese vernacular constructions with nonlinear numerical analysis

Considering that vernacular architecture may bear important lessons on hazard mitigation and that well-constructed examples showing traditional seismic resistant features can present far less vulnerability than expected, this study aims at understanding the resisting mechanisms and seismic behavior of vernacular buildings through detailed finite element modeling and nonlinear static (pushover) analysis. This paper focuses specifically on a type of vernacular rammed earth constructions found in the Portuguese region of Alentejo. Several rammed earth constructions found in the region were selected and studied in terms of dimensions, architectural layout, structural solutions, construction materials and detailing and, as a result, a reference model was built, which intends to be a simplified representative example of these constructions, gathering the most common characteristics. Different parameters that may affect the seismic response of this type of vernacular constructions have been identified and a numerical parametric study was defined aiming at evaluating and quantifying their influence in the seismic behavior of this type of vernacular buildings. This paper is part of an ongoing research which includes the development of a simplified methodology for assessing the seismic vulnerability of vernacular buildings, based on vulnerability index evaluation methods.

Analysis and selection of indicators for a sustainability assessment method for school buildings based on SBTool ‐ PT

Nowadays, the sustainability of buildings has an extreme importance. This concept goes towards the European aims of the Program Horizon 2020, which concerns about the reduction of the environmental impacts through such aspects as the energy efficiency and renewable technologies, among others. Sustainability is an extremely broad concept but, in this work, it is intended to include the concept of sustainability in buildings. Within the concept that aims the integration of environmental, social and economic levels towards the preservation of the planet and the integrity of the users, there are, currently, several types of tools of environmental certification that are applicable to the construction industry (LEED, BREEAM, DGNB, SBTool, among others). Within this context, it is highlighted the tool SBTool (Sustainable Building Tool) that is employed in several countries and can be subject to review in institutions of basic education, which are the base for the formation of the critical masses and for the development of a country. The main aim of this research is to select indicators that can be used in a methodology for sustainability assessment (SBTool) of school buildings in Portugal and in Brazil. In order to achieve it, it will also be analyzed other methodologies that already incorporate parameters directly related with the schools environment, such as BREEAM or LEED.

Development of a methodology to incorporate risk and uncertainty in electricity power planning

Dissertação de mestrado em Engenharia Industrial

Dynamic modelling and analysis of hydraulic forces in radial blood pumps

Dissertação de mestrado integrado em Biomedical Engineering Biomaterials, Biomechanics and Rehabilitation

Cerebral perfusion and automated individual analysis using SPECT among an obsessive-compulsive population

OBJECTIVE: To make individual assessments using automated quantification methodology in order to screen for perfusion abnormalities in cerebral SPECT examinations among a sample of subjects with OCD. METHODS: Statistical parametric mapping (SPM) was used to compare 26 brain SPECT images from patients with OCD individually with an image bank of 32 normal subjects, using the statistical threshold of p < 0.05 (corrected for multiple comparisons at the level of individual voxels or clusters). The maps were analyzed, and regions presenting voxels that remained above this threshold were sought. RESULTS: Six patients from a sample of 26 OCD images showed abnormalities at cluster or voxel level, considering the criteria described above, which represented 23.07%. However, seven images from the normal group of 32 were also indicated as cases of perfusional abnormality, representing 21.8% of the sample. CONCLUSION: The automated quantification method was not considered to be a useful tool for clinical practice, for analyses complementary to visual inspection.

Sustainability assessment of envelope wall solutions using MAXergy methodology

Projeto de investigação integrado de International Master in Sustainable Built Environment

Analysis of the risk factors for allograft vasculopathy in asymptomatic patients after cardiac transplantation

OBJECTIVE: To study the influence of immune and nonimmune risk factors on the development of allograft vasculopathy after cardiac transplantation. METHODS: We studied 39 patients with a mean age of 46±12 years. The following variables were analyzed: weight (kg), body mass index (kg/m²), donor's age and sex, rejection episodes in the first and second years after transplantation, systolic and diastolic blood pressures (mmHg), total cholesterol and fractions (mg/dL), triglycerides (mg/dL), diabetes, and cytomegalovirus infection. The presence of allograft vasculopathy was established through coronary angiography. RESULTS: Allograft vasculopathy was observed in 15 (38%) patients. No statistically significant difference was observed between the two groups in regard to hypertension, cytomegalovirus infection, diabetes, donor's sex and age, rejection episodes in the first and second years after transplantation, and cholesterol levels. We observed a tendency toward higher levels of triglycerides in the group with disease. Univariate and multivariate analyses showed statistically significant differences between the two groups when we analyzed the body mass index (24.53±4.3 versus 28.11±4.6; p=0.019). CONCLUSION: Body mass index was an important marker of allograft vasculopathy in the population studied.

An R package for the integrated analysis of metabolomics and spectral data

Recently, there has been a growing interest in the field of metabolomics, materialized by a remarkable growth in experimental techniques, available data and related biological applications. Indeed, techniques as Nuclear Magnetic Resonance, Gas or Liquid Chromatography, Mass Spectrometry, Infrared and UV-visible spectroscopies have provided extensive datasets that can help in tasks as biological and biomedical discovery, biotechnology and drug development. However, as it happens with other omics data, the analysis of metabolomics datasets provides multiple challenges, both in terms of methodologies and in the development of appropriate computational tools. Indeed, from the available software tools, none addresses the multiplicity of existing techniques and data analysis tasks. In this work, we make available a novel R package, named specmine, which provides a set of methods for metabolomics data analysis, including data loading in different formats, pre-processing, metabolite identification, univariate and multivariate data analysis, machine learning, and feature selection. Importantly, the implemented methods provide adequate support for the analysis of data from diverse experimental techniques, integrating a large set of functions from several R packages in a powerful, yet simple to use environment. The package, already available in CRAN, is accompanied by a web site where users can deposit datasets, scripts and analysis reports to be shared with the community, promoting the efficient sharing of metabolomics data analysis pipelines.

Participação estudantil no Facebook: processos, modalidades e motivações

Tese de Doutoramento em Ciências da Comunicação.

An analysis of the use of photogrammetric sorting to audit construction and demolition waste production on site

This study analyses the area of construction and demolition waste (C & D W) auditing. The production of C&DW has grown year after year since the Environmental Protection Agency (EPA) first published a report in 1996 which provided data for C&D W quantities for 1995 (EPA, 1996a). The most recent report produced by the EPA is based on data for 2005 (EPA, 2006). This report estimated that the quantity of C&DW produced for that period to be 14 931 486 tonnes. However, this is a ‘data update’ report containing an update on certain waste statistics so any total provided would not be a true reflection of the waste produced for that period. This illustrates that a more construction site-specific form of data is required. The Department of Building and Civil Engineering in the Galway-Mayo Institute of Technology have carried out two recent research projects (Grimes, 2005; Kelly, 2006) in this area, which have produced waste production indicators based on site-specific data. This involved the design and testing of an original auditing tool based on visual characterisation and the application of conversion factors. One of the main recommendations of these studies was to compare this visual characterisation approach with a photogrammetric sorting methodology. This study investigates the application of photogrammetric sorting on a residential construction site in the Galway region. A visual characterisation study is also carried out on the same project to compare the two methodologies and assess the practical application in a construction site environment. Data collected from the waste management contractor on site was also used to provide further evaluation. From this, a set of waste production indicators for new residential construction was produced: □ 50.8 kg/m2 for new residential construction using data provided by the visual characterisation method and the Landfill Levy conversion factors. □ 43 kg/m2 for new residential construction using data provided by the photogrammetric sorting method and the Landfill Levy conversion factors. □ 23.8 kg/m2 for new residential construction using data provided by Waste Management Contractor (WMC). The acquisition of the data from the waste management contractor was a key element for testing of the information produced by the visual characterisation and photogrammetric sorting methods. The actual weight provided by the waste management contractor shows a significant difference between the quantities provided.

The effectiveness of methods of shape analysis / Cliff A. Lemen.

n.s. no.15(1983)

A Methodology to measure shareholder value orientation and shareholder value creation aimed at providing a research basis to investigate the link between both magnitudes

Does shareholder value orientation lead to shareholder value creation? This article proposes methods to quantify both, shareholder value orientation and shareholder value creation. Through the application of these models it is possible to quantify both dimensions and examine statistically in how far shareholder value orientation explains shareholder value creation. The scoring model developed in this paper allows quantifying the orientation of managers towards the objective to maximize wealth of shareholders. The method evaluates information that comes from the companies and scores the value orientation in a scale from 0 to 10 points. Analytically the variable value orientation is operationalized expressing it as the general attitude of managers toward the objective of value creation, investment policy and behavior, flexibility and further eight value drivers. The value creation model works with market data such as stock prices and dividend payments. Both methods where applied to a sample of 38 blue chip companies: 32 firms belonged to the share index IBEX 35 on July 1st, 1999, one company represents the “new economy” listed in the Spanish New Market as per July 1st, 2001, and 5 European multinational groups formed part of the EuroStoxx 50 index also on July 1st, 2001. The research period comprised the financial years 1998, 1999, and 2000. A regression analysis showed that between 15.9% and 23.4% of shareholder value creation can be explained by shareholder value orientation.