Predictive models for chronic renal disease using decision trees, naïve bayes and case-based methods

Data mining can be used in healthcare industry to “mine” clinical data to discover hidden information for intelligent and affective decision making. Discovery of hidden patterns and relationships often goes intact, yet advanced data mining techniques can be helpful as remedy to this scenario. This thesis mainly deals with Intelligent Prediction of Chronic Renal Disease (IPCRD). Data covers blood, urine test, and external symptoms applied to predict chronic renal disease. Data from the database is initially transformed to Weka (3.6) and Chi-Square method is used for features section. After normalizing data, three classifiers were applied and efficiency of output is evaluated. Mainly, three classifiers are analyzed: Decision Tree, Naïve Bayes, K-Nearest Neighbour algorithm. Results show that each technique has its unique strength in realizing the objectives of the defined mining goals. Efficiency of Decision Tree and KNN was almost same but Naïve Bayes proved a comparative edge over others. Further sensitivity and specificity tests are used as statistical measures to examine the performance of a binary classification. Sensitivity (also called recall rate in some fields) measures the proportion of actual positives which are correctly identified while Specificity measures the proportion of negatives which are correctly identified. CRISP-DM methodology is applied to build the mining models. It consists of six major phases: business understanding, data understanding, data preparation, modeling, evaluation, and deployment.

Reservoir Management For Flood And Drought Protection Using Infinite Horizon Model Predictive Control

Model Predictive Control (MPC) is a control method that solves in real time an optimal control problem over a finite horizon. The finiteness of the horizon is both the reason of MPC's success and its main limitation. In operational water resources management, MPC has been in fact successfully employed for controlling systems with a relatively short memory, such as canals, where the horizon length is not an issue. For reservoirs, which have generally a longer memory, MPC applications are presently limited to short term management only. Short term reservoir management can be effectively used to deal with fast process, such as floods, but it is not capable of looking sufficiently ahead to handle long term issues, such as drought. To overcome this limitation, we propose an Infinite Horizon MPC (IH-MPC) solution that is particularly suitable for reservoir management. We propose to structure the input signal by use of orthogonal basis functions, therefore reducing the optimization argument to a finite number of variables, and making the control problem solvable in a reasonable time. We applied this solution for the management of the Manantali Reservoir. Manantali is a yearly reservoir located in Mali, on the Senegal river, affecting water systems of Mali, Senegal, and Mauritania. The long term horizon offered by IH-MPC is necessary to deal with the strongly seasonal climate of the region.

Seguimento clinoceletrográfico de criançcas e adolescentes com crise epiléptica única não-provocada

Os fenômenos convulsivos despertaram o interesse de estudiosos e pensadores já na Antigüidade, quando aspectos mágicos e sobrenaturais eram a eles associados. No século XIX foram lançadas as bases dos conceitos atuais sobre a desestruturação funcional cerebral na epilepsia, e Berger, em 1929, marcou definitivamente a história com a descoberta dos ritmos cerebrais. Crise epiléptica e epilepsia não são sinônimos, já que o último termo refere-se a crises recorrentes espontâneas. Ela costuma iniciar na infância, daí a preocupação com o risco de repetição do primeiro episódio e com a decisão de instituir tratamento medicamentoso. Fatores prognósticos são apontados, mas não há consenso. No Brasil existem poucas pesquisas nesta linha, tanto de prevalência da epilepsia como de fatores envolvidos na recorrência de crises. Este estudo teve como objetivo geral avaliar aspectos clinicoeletrográficos capazes de auxiliar no prognóstico e no manejo da epilepsia da criança e do adolescente. Foram objetivos específicos determinar a incidência de crise epiléptica não provocada recorrente; identificar fatores remotos implicados na ocorrência de crise epiléptica; relacionar tipo de crise com achados eletrencefalográficos; relacionar tipo de crise, duração da crise, estado vigília/sono no momento da crise e achados eletrencefalográficos com possibilidade de recorrência; e identificar os fatores de risco para epilepsia. Foram acompanhados 109 pacientes com idades entre 1 mês e 16 anos, com primeira crise não-provocada, em média por 24 meses, a intervalos trimestrais, no Hospital de Clínicas de Porto Alegre (HCPA). Foram realizados eletrencefalogramas (EEG) após a primeira crise; depois, solicitados anualmente. Não foram incluídos casos com epilepsia ou síndrome epiléptica bem definida, ou que fizeram uso prévio de drogas antiepilépticas. A média de idade foi 6 anos, com predomínio da faixa etária de 6 a 12 anos. Setenta eram meninos e 39, meninas. Os indivíduos brancos eram 92, e os não-brancos, 17. O nível de escolaridade dos casos esteve de acordo com a distribuição da idade e, entre os responsáveis, predominaram 8 anos de escolaridade. Foi possível concluir que as crises únicas não-provocadas mais freqüentes foram generalizadas, e sem predomínio significativo do tipo de EEG. A incidência de crise não-provocada recorrente foi 51,4%. História de intercorrências pré-natais maternas aumentou em 2 vezes o risco de repetição de crises. Via de nascimento, escore de Apgar no 5º minuto, relação peso ao nascer/idade gestacional, intercorrências no período pós-natal imediato e desenvolvimento neuropsicomotor não tiveram influência na recorrência. História familiar de crises mostrou tendência à significância estatística para repetição dos episódios, com risco de 1,7. Não foi encontrada associação entre tipo de crise e achado eletrencefalográfico. A maioria das crises foi de curta duração (até 5 minutos), mas este dado não esteve relacionado com a recorrência. Estado de vigília teve efeito protetor na recorrência. Se a primeira crise foi parcial, o risco de repetição foi 1,62, com tendência à significância. Quando o primeiro EEG foi alterado, houve relação significativa com primeira crise tanto generalizada como parcial. O primeiro EEG com alterações paroxísticas focais apontou risco de repetição de 2,90. Quando as variáveis envolvidas na repetição de crises foram ajustadas pelo modelo de regressão de Cox, EEG alterado mostrou risco de 2,48, com riscos acumulados de 50%, 60%, 62% e 68%; com EEG normal, os riscos foram 26%, 32%, 34% e 36% em 6, 12, 18 e 24 meses respectivamente.

“Ombro-cabeça-ombro”: testando a lucratividade do padrão gráfico de análise técnica no mercado de ações brasileiro

A partir de uma adaptação da metodologia de Osler e Chang (1995), este trabalho avalia, empiricamente, a lucratividade de estratégias de investimento baseadas na identificação do padrão gráfico de Análise Técnica Ombro-Cabeça-Ombro no mercado de ações brasileiro. Para isso, foram definidas diversas estratégias de investimento condicionais à identificação de padrões Ombro-Cabeça- Ombro (em suas formas padrão e invertida), por um algoritmo computadorizado, em séries diárias de preços de 47 ações no período de janeiro de 1994 a agosto de 2006. Para testar o poder de previsão de cada estratégia, foram construídos intervalos de confiança, a partir da técnica Bootstrap de inferência amostral, consistentes com a hipótese nula de que, baseado apenas em dados históricos, não é possível criar estratégias com retornos positivos. Mais especificamente, os retornos médios obtidos por cada estratégia nas séries de preços das ações, foram comparados àqueles obtidos pelas mesmas estratégias aplicadas a 1.000 séries de preços artificiais - para cada ação - geradas segundo dois modelos de preços de ações largamente utilizados: Random Walk e E-GARCH. De forma geral, os resultados encontrados mostram que é possível criar estratégias condicionais à realização dos padrões Ombro- Cabeça-Ombro com retornos positivos, indicando que esses padrões conseguem capturar nas séries históricas de preços de ações sinais a respeito da sua movimentação futura de preços, que não são explicados nem por um Random Walk e nem por um E-GARCH. No entanto, se levados em consideração os efeitos das taxas e dos custos de transação, dependendo das suas magnitudes, essas conclusões somente se mantêm para o padrão na sua forma invertida

Forecasting Brazilian inflation by its aggregate and disaggregated data: a test of predictive power by forecast horizon

This work aims to compare the forecast efficiency of different types of methodologies applied to Brazilian Consumer inflation (IPCA). We will compare forecasting models using disaggregated and aggregated data over twelve months ahead. The disaggregated models were estimated by SARIMA and will have different levels of disaggregation. Aggregated models will be estimated by time series techniques such as SARIMA, state-space structural models and Markov-switching. The forecasting accuracy comparison will be made by the selection model procedure known as Model Confidence Set and by Diebold-Mariano procedure. We were able to find evidence of forecast accuracy gains in models using more disaggregated data

Haematological and biochemical reference intervals for farmed channel catfish

The reference intervals for biochemical variables and red blood cell indices of healthy intensively bred channel catfish Ictalurus punctatus were determined. The blood variables were determined using standardized clinical methods. The reference intervals (25th and 75th percentiles) were established using a non-parametric method. Reference intervals for plasma glucose, serum total protein, sodium, potassium, calcium, magnesium, chloride concentration, primary and secondary red blood cell indices were established. The haematological and biochemical reference intervals established may allow important clinical decisions about channel catfish. (c) 2007 the Authors Journal compilation (C) 2007 the Fisheries Society of the British Isles.

Effects of different sampling intervals on apparent protein and energy digestibility of common feed ingredients by juvenile oscar fish (Astronotus ocellatus)

O presente estudo avaliou a digestibilidade aparente da proteína e da energia de ingredientes (farelo de soja, farinha de peixe, farelo de trigo e milho) por juvenis de apaiari (Astronotus ocellatus) usando dois diferentes intervalos de coleta (30 min. e 12h). Os 160 juvenis de apaiari utilizados (22,37 ± 3,06 g de peso corporal) foram divididos em quatro tanques rede plásticos e cilíndricos, cada um colocado em um tanque de alimentação de 1.000 L. O experimento foi inteiramente casualizado em esquema fatorial 2 x 4 (2 intervalos de coleta de fezes e 4 ingredientes foram) com quatro repetições. Os testes estatísticos não detectaram efeito da interação entre o intervalo de coleta e tipo de ingrediente nos coeficientes de digestibilidade. O intervalo de coleta não afetou a digestibilidade da proteína e da energia. As características físicas das fezes dos juvenis de apaiari aparentemente as tornam menos sensíveis à perda de nutrientes por lixiviação, permitindo intervalos de coleta maiores. A digestibilidade da proteína dos ingredientes avaliados foi semelhante, mostrando que a digestibilidade aparente de ingredientes animais e vegetais por juvenis de apaiari é eficiente. Os coeficientes de digestibilidade da energia foram maiores para a farinha de peixe e o farelo de soja comparado a farelo de trigo e milho. Ingredientes ricos em carboidratos (farelo de trigo e milho) apresentaram os piores coeficientes de digestibilidade da energia e, portanto, não são usados eficientemente pelos juvenis de apaiari.

A gene signature in histologically normal surgical margins is predictive of oral carcinoma recurrence

Background: Oral Squamous Cell Carcinoma (OSCC) is a major cause of cancer death worldwide, which is mainly due to recurrence leading to treatment failure and patient death. Histological status of surgical margins is a currently available assessment for recurrence risk in OSCC; however histological status does not predict recurrence, even in patients with histologically negative margins. Therefore, molecular analysis of histologically normal resection margins and the corresponding OSCC may aid in identifying a gene signature predictive of recurrence.Methods: We used a meta-analysis of 199 samples (OSCCs and normal oral tissues) from five public microarray datasets, in addition to our microarray analysis of 96 OSCCs and histologically normal margins from 24 patients, to train a gene signature for recurrence. Validation was performed by quantitative real-time PCR using 136 samples from an independent cohort of 30 patients.Results: We identified 138 significantly over-expressed genes (> 2-fold, false discovery rate of 0.01) in OSCC. By penalized likelihood Cox regression, we identified a 4-gene signature with prognostic value for recurrence in our training set. This signature comprised the invasion-related genes MMP1, COL4A1, P4HA2, and THBS2. Overexpression of this 4-gene signature in histologically normal margins was associated with recurrence in our training cohort (p = 0.0003, logrank test) and in our independent validation cohort (p = 0.04, HR = 6.8, logrank test).Conclusion: Gene expression alterations occur in histologically normal margins in OSCC. Over-expression of the 4-gene signature in histologically normal surgical margins was validated and highly predictive of recurrence in an independent patient cohort. Our findings may be applied to develop a molecular test, which would be clinically useful to help predict which patients are at a higher risk of local recurrence.

Factors predictive of inappropriateness in requests for parenteral antimicrobials for therapeutic purposes: A study in a small teaching hospital in Brazil

Background: The identification of patterns of inappropriate antimicrobial prescriptions in hospitals contributes to the improvement of antimicrobial stewardship programs (ASP). Methods: We conducted a cross-sectional study to identify predictors of inappropriateness in requests for parenteral antimicrobials (RPAs) in a teaching hospital with 285 beds. We reviewed 25% of RPAs for therapeutic purposes from y 2005. Appropriateness was evaluated according to current guidelines for antimicrobial therapy. We assessed predictors of inappropriateness through univariate and multivariate models. RPAs classified as 'appropriate' or 'probably appropriate' were selected as controls. Case groups comprised inappropriate RPAs, either in general or for specific errors. Results: Nine hundred and sixty-three RPAs were evaluated, 34.6% of which were considered inappropriate. In the multivariate analysis, general predictors of inappropriateness were: prescription on week-ends/holidays (odds ratio (OR) 1.67, 95% confidence interval (CI) 1.20-2.28, p = 0.002), patient in the intensive care unit (OR 1.57, 95% CI 1.11-2.23, p = 0.01), peritoneal infection (OR 2.15, 95% CI 1.27-3.65, p = 0.004), urinary tract infection (OR 1.89, 95% CI 1.25 -2.87, p = 0.01), combination therapy with 2 or more antimicrobials (OR 1.72, 95% CI 1.15-2.57, p = 0.008) and prescriptions including penicillins (OR 2.12, 95% CI 1.39-3.25, p = 0.001) or 1(st) generation cephalosporins (OR 1.74, 95% CI 1.01-3.00, p = 0.048). Previous consultation with an infectious diseases (ID) specialist had a protective effect against inappropriate prescription (OR 0.34, 95% CI 0.24-0.50, p < 0.001). Factors independently associated with specific prescription errors varied. However, consultation with an ID specialist was protective against both unnecessary antimicrobial use (OR 0.04, 95% CI 0.01-0.26, p = 0.001) and requests for agents with an insufficient antimicrobial spectrum (OR 0.14, 95% CI 0.03-0.30, p = 0.01). Conclusions: Our results demonstrate the importance of previous consultation with an ID specialist in assuring the quality of prescriptions. Also, they highlight prescription patterns that should be approached by ASP policies.

Alcohol screening instruments in elderly male: a population-based survey in metropolitan São Paulo, Brazil

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Parturition intervals and distributions of parturitions by months of buffalo in Southern and South-eastern Brazil

Reproductive rate is an important component of economic success in livestock production. Parturition interval (IEP) is a direct measure of the productivity of the animal. Long IEP reduce the number of calves produced per year. The objective this study was to determine the distribution of parturitions across month and to evaluate factors affecting IEP. The data included 7,588 parturitions of Murrah, Mediterranean and Carabobo buffalo from 10 herds in Southern and South-eastern Brazil. The analysis of distribution of parturitions evaluated the effects of month, year and their interaction on birth date of calves by using a Chi-Square test in SAS PROC FREQ (SAS Institute, Cary, NC, USA). Parturition intervals (n = 2,630) were evaluated using analysis of variance in SAS PROC GLM. The model for IEP included the fixed effects of season (December to May = 1, June to November = 2), year, season x year, sex of the preceding parturition, age of weaning of the previous calf, and herd. All sources of variation were significant (P<0.0001) except sex of the preceding parturition (P <0.85). The mean IEP was 446.7 +/- 10.4 days, for seasons 1 and 2 IEP were 419.8 +/- 11.3 and 473.6 +/- 40.7 days, respectively, a difference of 54 days. As weaning age increased there was a lengthening of IEP. Buffalo in Brazil showed seasonal parturition with calving concentrated from January to April, although the frequency by month differed across years (P<0.0001). These months also had the lowest calving interval.

The efficacy of a single chain recombinant equine luteinizing hormone (reLH) in mares: Induction of ovulation, hormone profiles, and inter-ovulatory intervals

The objectives of this study were to determine the efficacy of recombinant equine luteinizing hormone (reLH) in shortening the time to ovulation in cycling mares and to determine the effects of treatment on endogenous hormones and inter-ovulatory intervals. In study 1, mares of light horse breeds (3-20 years) were treated with either a vehicle, various doses of reLH, or human chorionic gonadotropin (hCG). Cycling mares were examined by palpation and ultrasound per rectum daily or every 12 h from the time of treatment to ovulation. In studies 2 and 3, jugular blood samples were collected daily or every 12 h from the time of treatment to ovulation for analysis of LH, follicle stimulating hormone (FSH), estradiol-17 beta (E-2), and progesterone (P-4) by radioimmunoassays (RIA). Increasing doses of reLH (0.3, 0.6, 0.75, and 0.9 mg) showed increasing effectiveness at inducing ovulation within 48 h of treatment. Treatments with the 0.75 and 0.9 mg doses of reLH resulted in 90% and 80% ovulation rates, which were similar to hCG treatment (85.7%). Except for the early rise in LH after treatment with 0.5, 0.65, and 1.0 mg of reLH, hormone profiles appeared to be similar between control and treated cycles. Inter-ovulatory intervals were similar between control and treatment cycles. In conclusion, reLH is a reliable and effective ovulatory agent that does not significantly alter endogenous hormone profiles or affect inter-ovulatory intervals.(c) 2007 Elsevier B.V. All rights reserved.