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.

Fractional pennes' bioheat equation: theoretical and numerical studies

In this work we provide a new mathematical model for the Pennes’ bioheat equation, assuming a fractional time derivative of single order. Alternative versions of the bioheat equation are studied and discussed, to take into account the temperature-dependent variability in the tissue perfusion, and both finite and infinite speed of heat propagation. The proposed bioheat model is solved numerically using an implicit finite difference scheme that we prove to be convergent and stable. The numerical method proposed can be applied to general reaction diffusion equations, with a variable diffusion coefficient. The results obtained with the single order fractional model, are compared with the original models that use classical derivatives.

Fractional bioheat equation

In this work we develop a new mathematical model for the Pennes’ bioheat equation assuming a fractional time derivative of single order. A numerical method for the solu- tion of such equations is proposed, and, the suitability of the new model for modelling real physical problems is studied and discussed

Comparison of different numerical methods for the solution of the time-fractional reaction-diffusion equation with variable diffusion coefficient

In this work we perform a comparison of two different numerical schemes for the solution of the time-fractional diffusion equation with variable diffusion coefficient and a nonlinear source term. The two methods are the implicit numerical scheme presented in [M.L. Morgado, M. Rebelo, Numerical approximation of distributed order reaction- diffusion equations, Journal of Computational and Applied Mathematics 275 (2015) 216-227] that is adapted to our type of equation, and a colocation method where Chebyshev polynomials are used to reduce the fractional differential equation to a system of ordinary differential equations

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.

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

Quantum field theory approach to the optical conductivity of strained and deformed graphene

The computation of the optical conductivity of strained and deformed graphene is discussed within the framework of quantum field theory in curved spaces. The analytical solutions of the Dirac equation in an arbitrary static background geometry for one dimensional periodic deformations are computed, together with the corresponding Dirac propagator. Analytical expressions are given for the optical conductivity of strained and deformed graphene associated with both intra and interbrand transitions. The special case of small deformations is discussed and the result compared to the prediction of the tight-binding model.

Factores Críticos del Desarrollo Local y Regional Integrado zona serrana y Norte de la Provincia de Córdoba-. Validación causal estadística de Modelos de Ecuaciones Estructurales. Identificación de problemas normativos de las OSC.Critical Factors of Local and Regional Development in north of the Province of Córdoba. Causal validation with Structural Equation Modeling. Legal regulations of civil society.

En la investigación anterior -en la zona pampeana de la Provincia de Córdoba- se demostró teórica y empíricamente, que el desarrollo de la Sociedad Civil muchas veces libradas a su suerte y con limitaciones legales apoyan decididamente el desarrollo local, sin embargo han logrado solo parcialmente sus objetivos, por lo que es necesario comenzar un camino de fortalecimiento en los nuevos roles que deben asumir. Los gobiernos locales, a la vez, intentan trabajosamente con contados éxitos detener el procesos de descapitalización social -financiera y humana- de sus comunidades locales y regionales, peregrinando con escaso éxito a los centros concentrados del poder político y económico, para procurar los recursos financieros y humanos necesarios que no alcanzan a reponer los que se fugan desde hace décadas de sus localidades. Las empresas, con ciclos recurrentes de crecimiento y decrecimiento vinculados a los mercados en que colocan sus productos, también se debaten en la búsqueda de los escasos recursos, financieros y humanos, que les permitan consolidar un desarrollo a mediano y largo plazo. El desarrollo alcanzado en Sistemas de información, instrumentos de relevamiento, análisis y elaboración de propuestas para el Desarrollo Local, nos permite avanzar en: 1. La confirmación empírica de las hipótesis iniciales - factores exógenos y endógenos - en la zona Norte y Serrana de la provincia 2. La validación científica -mediante el Análisis de ecuaciones estructurales. de tales supuestos, para el conjunto de las poblaciones analizadas en ambas etapas. 3. La identificación de los problemas normativos que afectan el desarrollo de las Organizaciones de la Sociedad Civil (OSC). METODOLOGÍA Respecto la validación empírica en la zona norte y serrana 1. Selección de las 4 localidades a relevar de acuerdo a las categorías definidas 2. Elaboración de acuerdos con autoridades e instituciones locales. 3. Relevamiento cualitativo con líderes locales y fuentes de datos secundarias. 4. Adaptación de instrumentos de relevamiento a las realidades locales y estudios previos 5. Relevamiento cuantitativo de campo, capacitación de encuestadores y supervisores. 6. Procesamiento y elaboración de informes finales locales. Respecto de la construcción de modelos de desarrollo 1. Desarrollar las dimensiones especificas y las variables (items) de cada factor crítico. 2. Revisar el instrumento con expertos de cada una de las dimensiones. 3. Validar a nivel exploratorio por medio de un Análisis de Componentes Principales 4. Someter a los expertos la evaluación de una serie de localidades que representan cada uno. Respecto de la identificación de las normas legales que afectan a la Sociedad Civil 1.Relevamiento documental de normas 2. Relevamiento con líderes de instituciones de la Sociedad Civil 3. Análisis de las normas vigentes 4. Elaboración de Informes Finales y Transferencia a líderes e instituciones

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.

Data mining in diagnostic charts and treatment outcome prediction for vision restoration therapy

Data Mining, Vision Restoration, Treatment outcome prediction, Self-Organising-Map

Hemorheological and Glycemic Parameters and HDL Cholesterol for the Prediction of Cardiovascular Events

Abstract Background: Hemorheological and glycemic parameters and high density lipoprotein (HDL) cholesterol are used as biomarkers of atherosclerosis and thrombosis. Objective: To investigate the association and clinical relevance of erythrocyte sedimentation rate (ESR), fibrinogen, fasting glucose, glycated hemoglobin (HbA1c), and HDL cholesterol in the prediction of major adverse cardiovascular events (MACE) and coronary heart disease (CHD) in an outpatient population. Methods: 708 stable patients who visited the outpatient department were enrolled and followed for a mean period of 28.5 months. Patients were divided into two groups, patients without MACE and patients with MACE, which included cardiac death, acute myocardial infarction, newly diagnosed CHD, and cerebral vascular accident. We compared hemorheological and glycemic parameters and lipid profiles between the groups. Results: Patients with MACE had significantly higher ESR, fibrinogen, fasting glucose, and HbA1c, while lower HDL cholesterol compared with patients without MACE. High ESR and fibrinogen and low HDL cholesterol significantly increased the risk of MACE in multivariate regression analysis. In patients with MACE, high fibrinogen and HbA1c levels increased the risk of multivessel CHD. Furthermore, ESR and fibrinogen were significantly positively correlated with HbA1c and negatively correlated with HDL cholesterol, however not correlated with fasting glucose. Conclusion: Hemorheological abnormalities, poor glycemic control, and low HDL cholesterol are correlated with each other and could serve as simple and useful surrogate markers and predictors for MACE and CHD in outpatients.

Risk Prediction of Cardiovascular Complications in Pregnant Women With Heart Disease

Abstract Background: Heart disease in pregnancy is the leading cause of non- obstetric maternal death. Few Brazilian studies have assessed the impact of heart disease during pregnancy. Objective: To determine the risk factors associated with cardiovascular and neonatal complications. Methods: We evaluated 132 pregnant women with heart disease at a High-Risk Pregnancy outpatient clinic, from January 2005 to July 2010. Variables that could influence the maternal-fetal outcome were selected: age, parity, smoking, etiology and severity of the disease, previous cardiac complications, cyanosis, New York Heart Association (NYHA) functional class > II, left ventricular dysfunction/obstruction, arrhythmia, drug treatment change, time of prenatal care beginning and number of prenatal visits. The maternal-fetal risk index, Cardiac Disease in Pregnancy (CARPREG), was retrospectively calculated at the beginning of prenatal care, and patients were stratified in its three risk categories. Results: Rheumatic heart disease was the most prevalent (62.12%). The most frequent complications were heart failure (11.36%) and arrhythmias (6.82%). Factors associated with cardiovascular complications on multivariate analysis were: drug treatment change (p = 0.009), previous cardiac complications (p = 0.013) and NYHA class III on the first prenatal visit (p = 0.041). The cardiovascular complication rates were 15.22% in CARPREG 0, 16.42% in CARPREG 1, and 42.11% in CARPREG > 1, differing from those estimated by the original index: 5%, 27% and 75%, respectively. This sample had 26.36% of prematurity. Conclusion: The cardiovascular complication risk factors in this population were drug treatment change, previous cardiac complications and NYHA class III at the beginning of prenatal care. The CARPREG index used in this sample composed mainly of patients with rheumatic heart disease overestimated the number of events in pregnant women classified as CARPREG 1 and > 1, and underestimated it in low-risk patients (CARPREG 0).