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.

Using customer lifetime value to improve the prediction of bank deposit subscription in telemarketing campaigns

Customer lifetime value (LTV) enables using client characteristics, such as recency, frequency and monetary (RFM) value, to describe the value of a client through time in terms of profitability. We present the concept of LTV applied to telemarketing for improving the return-on-investment, using a recent (from 2008 to 2013) and real case study of bank campaigns to sell long- term deposits. The goal was to benefit from past contacts history to extract additional knowledge. A total of twelve LTV input variables were tested, un- der a forward selection method and using a realistic rolling windows scheme, highlighting the validity of five new LTV features. The results achieved by our LTV data-driven approach using neural networks allowed an improvement up to 4 pp in the Lift cumulative curve for targeting the deposit subscribers when compared with a baseline model (with no history data). Explanatory knowledge was also extracted from the proposed model, revealing two highly relevant LTV features, the last result of the previous campaign to sell the same product and the frequency of past client successes. The obtained results are particularly valuable for contact center companies, which can improve pre- dictive performance without even having to ask for more information to the companies they serve.

Equations for defining the mismatch between students and school furniture: A systematic review

The present study reviews the scientific literature that describes the criteria equations for defining the mismatch between students and school furniture. This mismatch may negatively affect students' performance and comfort. Seventeen studies met the criteria of this review and twenty-one equations to test six furniture dimensions were identified. There was substantial mismatch between the relative heights of chairs and tables. Some systematic errors have been found during the application of the different equations, such as the assumption that students are sitting on chairs with a proper seat height. Only one study considered the cumulative fit. Finally, some equations are based on contradictory criteria and need to develop and evaluate new equations for these cases. Relevance to industry: Ultimately, the present work is a contribution toward improving the evaluation of school furniture and could be used to design ergonomic-oriented classroom furniture.

Dispersion of fillers in viscoelastic polymer matrices using Eulerian-Lagrangian approaches

Understanding the behavior of c omplex composite materials using mixing procedures is fundamental in several industrial processes. For instance, polymer composites are usually manufactured using dispersion of fillers in polymer melt matrices. The success of the filler dispersion depends both on the complex flow patterns generated and on the polymer melt rheological behavior. Consequently, the availability of a numerical tool that allow to model both fluid and particle would be very useful to increase the process insight. Nowadays there ar e computational tools that allow modeling the behavior of filled systems, taking into account both the behavior of the fluid (Computational Rheology) and the particles (Discrete Element Method). One example is the DPMFoam solver of the OpenFOAM ® framework where the averaged volume fraction momentum and mass conservation equations are used to describe the fluid (continuous phase) rheology, and the Newton’s second law of motion is used to compute the particles (discrete phase) movement. In this work the refer red solver is extended to take into account the elasticity of the polymer melts for the continuous phase. The solver capabilities will be illustrated by studying the effect of the fluid rheology on the filler dispersion, taking into account different fluid types (generalized Newtonian or viscoelastic) and particles volume fraction and size. The results obtained are used to evaluate the relevance of considering the fluid complex rheology for the prediction of the composites morphology

Impact performance prediction of injection-molded talc-filled polypropylene through thermomechanical environment assessment

Due to the fact that different injection molding conditions tailor the mechanical response of the thermoplastic material, such effect must be considered earlier in the product development process. The existing approaches implemented in different commercial software solutions are very limited in their capabilities to estimate the influence of processing conditions on the mechanical properties. Thus, the accuracy of predictive simulations could be improved. In this study, we demonstrate how to establish straightforward processing-impact property relationships of talc-filled injection-molded polypropylene disc-shaped parts by assessing the thermomechanical environment (TME). To investigate the relationship between impact properties and the key operative variables (flow rate, melt and mold temperature, and holding pressure), the design of experiments approach was applied to systematically vary the TME of molded samples. The TME is characterized on computer flow simulation outputsanddefined bytwo thermomechanical indices (TMI): the cooling index (CI; associated to the core features) and the thermo-stress index (TSI; related to the skin features). The TMI methodology coupled to an integrated simulation program has been developed as a tool to predict the impact response. The dynamic impact properties (peak force, peak energy, and puncture energy) were evaluated using instrumented falling weight impact tests and were all found to be similarly affected by the imposed TME. The most important molding parameters affecting the impact properties were found to be the processing temperatures (melt andmold). CI revealed greater importance for the impact response than TSI. The developed integrative tool provided truthful predictions for the envisaged impact properties.

Biomass equations for forest regrowth in the eastern Amazon using randomized branch sampling

Forest regrowth occupies an extensive and increasing area in the Amazon basin, but accurate assessment of the impact of regrowth on carbon and nutrient cycles has been hampered by a paucity of available allometric equations. We develop pooled and species-specific equations for total aboveground biomass for a study site in the eastern Amazon that had been abandoned for 15 years. Field work was conducted using randomized branch sampling, a rapid technique that has seen little use in tropical forests. High consistency of sample paths in randomized branch sampling, as measured by the standard error of individual paths (14%), suggests the method may provide substantial efficiencies when compared to traditional procedures. The best fitting equations in this study used the traditional form Y=a×DBHb, where Y is biomass, DBH is diameter at breast height, and a and b are both species-specific parameters. Species-specific equations of the form Y=a(BA×H), where Y is biomass, BA is tree basal area, H is tree height, and a is a species-specific parameter, fit almost as well. Comparison with previously published equations indicated errors from -33% to +29% would have occurred using off-site relationships. We also present equations for stemwood, twigs, and foliage as biomass components.

Prediction of drug targets in human pathogens

The identification of new and druggable targets in bacteria is a critical endeavour in pharmaceutical research of novel antibiotics to fight infectious agents. The rapid emergence of resistant bacteria makes today's antibiotics more and more ineffective, consequently increasing the need for new pharmacological targets and novel classes of antibacterial drugs. A new model that combines the singular value decomposition technique with biological filters comprised of a set of protein properties associated with bacterial drug targets and similarity to protein-coding essential genes of E. coli has been developed to predict potential drug targets in the Enterobacteriaceae family [1]. This model identified 99 potential target proteins amongst the studied bacterial family, exhibiting eight different functions that suggest that the disruption of the activities of these proteins is critical for cells. Out of these candidates, one was selected for target confirmation. To find target modulators, receptor-based pharmacophore hypotheses were built and used in the screening of a virtual library of compounds. Postscreening filters were based on physicochemical and topological similarity to known Gram-negative antibiotics and applied to the retrieved compounds. Screening hits passing all filters were docked into the proteins catalytic groove and 15 of the most promising compounds were purchased from their chemical vendors to be experimentally tested in vitro. To the best of our knowledge, this is the first attempt to rationalize the search of compounds to probe the relevance of this candidate as a new pharmacological target.

The Data Mining applied for the prediction of highway roughness due to overloaded trucks

Currently, the quality of the Indonesian national road network is inadequate due to several constraints, including overcapacity and overloaded trucks. The high deterioration rate of the road infrastructure in developing countries along with major budgetary restrictions and high growth in traffic have led to an emerging need for improving the performance of the highway maintenance system. However, the high number of intervening factors and their complex effects require advanced tools to successfully solve this problem. The high learning capabilities of Data Mining (DM) are a powerful solution to this problem. In the past, these tools have been successfully applied to solve complex and multi-dimensional problems in various scientific fields. Therefore, it is expected that DM can be used to analyze the large amount of data regarding the pavement and traffic, identify the relationship between variables, and provide information regarding the prediction of the data. In this paper, we present a new approach to predict the International Roughness Index (IRI) of pavement based on DM techniques. DM was used to analyze the initial IRI data, including age, Equivalent Single Axle Load (ESAL), crack, potholes, rutting, and long cracks. This model was developed and verified using data from an Integrated Indonesia Road Management System (IIRMS) that was measured with the National Association of Australian State Road Authorities (NAASRA) roughness meter. The results of the proposed approach are compared with the IIRMS analytical model adapted to the IRI, and the advantages of the new approach are highlighted. We show that the novel data-driven model is able to learn (with high accuracy) the complex relationships between the IRI and the contributing factors of overloaded trucks

Development of computational and experimental methods for biomass composition and evaluation of its impact in genome-scale models prediction

The use of genome-scale metabolic models has been rapidly increasing in fields such as metabolic engineering. An important part of a metabolic model is the biomass equation since this reaction will ultimately determine the predictive capacity of the model in terms of essentiality and flux distributions. Thus, in order to obtain a reliable metabolic model the biomass precursors and their coefficients must be as precise as possible. Ideally, determination of the biomass composition would be performed experimentally, but when no experimental data are available this is established by approximation to closely related organisms. Computational methods however, can extract some information from the genome such as amino acid and nucleotide compositions. The main objectives of this study were to compare the biomass composition of several organisms and to evaluate how biomass precursor coefficients affected the predictability of several genome-scale metabolic models by comparing predictions with experimental data in literature. For that, the biomass macromolecular composition was experimentally determined and the amino acid composition was both experimentally and computationally estimated for several organisms. Sensitivity analysis studies were also performed with the Escherichia coli iAF1260 metabolic model concerning specific growth rates and flux distributions. The results obtained suggest that the macromolecular composition is conserved among related organisms. Contrasting, experimental data for amino acid composition seem to have no similarities for related organisms. It was also observed that the impact of macromolecular composition on specific growth rates and flux distributions is larger than the impact of amino acid composition, even when data from closely related organisms are used.

Kinematic constraint equations

This chapter presents a general methodology for the formulation of the kinematic constraint equations at position, velocity and acceleration levels. Also a brief characterization of the different type of constraints is offered, namely the holonomic and nonholonomic constraints. The kinematic constraints described here are formulated using generalized coordinates. The chapter ends with a general approach to deal with the kinematic analysis of multibody systems.

Equations of motion for constrained systems

"Series title: Springerbriefs in applied sciences and technology, ISSN 2191-530X"

Methods to solve the equations of motion

"Series title: Springerbriefs in applied sciences and technology, ISSN 2191-530X"

Stabilized finite element methods applied to transient convection-diffusion-reaction and population balance equations

Magdeburg, Univ., Fak. für Mathematik, Diss., 2011

Left Atrial Volume Index and Prediction of Events in Acute Coronary Syndrome: Solar Registry

Background: According to some international studies, patients with acute coronary syndrome (ACS) and increased left atrial volume index (LAVI) have worse long-term prognosis. However, national Brazilian studies confirming this prediction are still lacking. Objective: To evaluate LAVI as a predictor of major cardiovascular events (MCE) in patients with ACS during a 365-day follow-up. Methods: Prospective cohort of 171 patients diagnosed with ACS whose LAVI was calculated within 48 hours after hospital admission. According to LAVI, two groups were categorized: normal LAVI (≤ 32 mL/m2) and increased LAVI (> 32 mL/m2). Both groups were compared regarding clinical and echocardiographic characteristics, in- and out-of-hospital outcomes, and occurrence of ECM in up to 365 days. Results: Increased LAVI was observed in 78 patients (45%), and was associated with older age, higher body mass index, hypertension, history of myocardial infarction and previous angioplasty, and lower creatinine clearance and ejection fraction. During hospitalization, acute pulmonary edema was more frequent in patients with increased LAVI (14.1% vs. 4.3%, p = 0.024). After discharge, the occurrence of combined outcome for MCE was higher (p = 0.001) in the group with increased LAVI (26%) as compared to the normal LAVI group (7%) [RR (95% CI) = 3.46 (1.54-7.73) vs. 0.80 (0.69-0.92)]. After Cox regression, increased LAVI increased the probability of MCE (HR = 3.08, 95% CI = 1.28-7.40, p = 0.012). Conclusion: Increased LAVI is an important predictor of MCE in a one-year follow-up.

Physical Stress Echocardiography: Prediction of Mortality and Cardiac Events in Patients with Exercise Test showing Ischemia

Background: Studies have demonstrated the diagnostic accuracy and prognostic value of physical stress echocardiography in coronary artery disease. However, the prediction of mortality and major cardiac events in patients with exercise test positive for myocardial ischemia is limited. Objective: To evaluate the effectiveness of physical stress echocardiography in the prediction of mortality and major cardiac events in patients with exercise test positive for myocardial ischemia. Methods: This is a retrospective cohort in which 866 consecutive patients with exercise test positive for myocardial ischemia, and who underwent physical stress echocardiography were studied. Patients were divided into two groups: with physical stress echocardiography negative (G1) or positive (G2) for myocardial ischemia. The endpoints analyzed were all-cause mortality and major cardiac events, defined as cardiac death and non-fatal acute myocardial infarction. Results: G2 comprised 205 patients (23.7%). During the mean 85.6 ± 15.0-month follow-up, there were 26 deaths, of which six were cardiac deaths, and 25 non-fatal myocardial infarction cases. The independent predictors of mortality were: age, diabetes mellitus, and positive physical stress echocardiography (hazard ratio: 2.69; 95% confidence interval: 1.20 - 6.01; p = 0.016). The independent predictors of major cardiac events were: age, previous coronary artery disease, positive physical stress echocardiography (hazard ratio: 2.75; 95% confidence interval: 1.15 - 6.53; p = 0.022) and absence of a 10% increase in ejection fraction. All-cause mortality and the incidence of major cardiac events were significantly higher in G2 (p < 0. 001 and p = 0.001, respectively). Conclusion: Physical stress echocardiography provides additional prognostic information in patients with exercise test positive for myocardial ischemia.