Comparação entre a dopplervelocimetria das artérias uterinas e a impedância bioelétrica na predição de hipertensao na gestação e restrição de crescimento intrauterino

Pós-graduação em Ginecologia, Obstetrícia e Mastologia - FMB

NIRS and iSPA-PLS for predicting total anthocyanin content in jaboticaba fruit

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients

Background: Tuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for predicting pulmonary TB in hospitalized patients in a high prevalence area in order to contribute to a more rational use of isolation rooms without increasing the risk of transmission. Methods: Cross sectional study of patients admitted to CFFH from March 2003 to December 2004. A classification and regression tree (CART) model was generated and validated. The area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values were used to evaluate the performance of model. Validation of the model was performed with a different sample of patients admitted to the same hospital from January to December 2005. Results: We studied 290 patients admitted with clinical suspicion of TB. Diagnosis was confirmed in 26.5% of them. Pulmonary TB was present in 83.7% of the patients with TB (62.3% with positive sputum smear) and HIV/AIDS was present in 56.9% of patients. The validated CART model showed sensitivity, specificity, positive predictive value and negative predictive value of 60.00%, 76.16%, 33.33%, and 90.55%, respectively. The AUC was 79.70%. Conclusions: The CART model developed for these hospitalized patients with clinical suspicion of TB had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but our model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.

Bagging k-dependence probabilistic networks: An alternative powerful fraud detection tool

Fraud is a global problem that has required more attention due to an accentuated expansion of modern technology and communication. When statistical techniques are used to detect fraud, whether a fraud detection model is accurate enough in order to provide correct classification of the case as a fraudulent or legitimate is a critical factor. In this context, the concept of bootstrap aggregating (bagging) arises. The basic idea is to generate multiple classifiers by obtaining the predicted values from the adjusted models to several replicated datasets and then combining them into a single predictive classification in order to improve the classification accuracy. In this paper, for the first time, we aim to present a pioneer study of the performance of the discrete and continuous k-dependence probabilistic networks within the context of bagging predictors classification. Via a large simulation study and various real datasets, we discovered that the probabilistic networks are a strong modeling option with high predictive capacity and with a high increment using the bagging procedure when compared to traditional techniques. (C) 2012 Elsevier Ltd. All rights reserved.

Learning with Kernels on Graphs: DAG-based kernels, data streams and RNA function prediction.

In many application domains data can be naturally represented as graphs. When the application of analytical solutions for a given problem is unfeasible, machine learning techniques could be a viable way to solve the problem. Classical machine learning techniques are defined for data represented in a vectorial form. Recently some of them have been extended to deal directly with structured data. Among those techniques, kernel methods have shown promising results both from the computational complexity and the predictive performance point of view. Kernel methods allow to avoid an explicit mapping in a vectorial form relying on kernel functions, which informally are functions calculating a similarity measure between two entities. However, the definition of good kernels for graphs is a challenging problem because of the difficulty to find a good tradeoff between computational complexity and expressiveness. Another problem we face is learning on data streams, where a potentially unbounded sequence of data is generated by some sources. There are three main contributions in this thesis. The first contribution is the definition of a new family of kernels for graphs based on Directed Acyclic Graphs (DAGs). We analyzed two kernels from this family, achieving state-of-the-art results from both the computational and the classification point of view on real-world datasets. The second contribution consists in making the application of learning algorithms for streams of graphs feasible. Moreover,we defined a principled way for the memory management. The third contribution is the application of machine learning techniques for structured data to non-coding RNA function prediction. In this setting, the secondary structure is thought to carry relevant information. However, existing methods considering the secondary structure have prohibitively high computational complexity. We propose to apply kernel methods on this domain, obtaining state-of-the-art results.

Predicting adverse events in children with fever and chemotherapy-induced neutropenia: the prospective multicenter SPOG 2003 FN study

PURPOSE To develop a score predicting the risk of adverse events (AEs) in pediatric patients with cancer who experience fever and neutropenia (FN) and to evaluate its performance. PATIENTS AND METHODS Pediatric patients with cancer presenting with FN induced by nonmyeloablative chemotherapy were observed in a prospective multicenter study. A score predicting the risk of future AEs (ie, serious medical complication, microbiologically defined infection, radiologically confirmed pneumonia) was developed from a multivariate mixed logistic regression model. Its cross-validated predictive performance was compared with that of published risk prediction rules. Results An AE was reported in 122 (29%) of 423 FN episodes. In 57 episodes (13%), the first AE was known only after reassessment after 8 to 24 hours of inpatient management. Predicting AE at reassessment was better than prediction at presentation with FN. A differential leukocyte count did not increase the predictive performance. The score predicting future AE in 358 episodes without known AE at reassessment used the following four variables: preceding chemotherapy more intensive than acute lymphoblastic leukemia maintenance (weight = 4), hemoglobin > or = 90 g/L (weight = 5), leukocyte count less than 0.3 G/L (weight = 3), and platelet count less than 50 G/L (weight = 3). A score (sum of weights) > or = 9 predicted future AEs. The cross-validated performance of this score exceeded the performance of published risk prediction rules. At an overall sensitivity of 92%, 35% of the episodes were classified as low risk, with a specificity of 45% and a negative predictive value of 93%. CONCLUSION This score, based on four routinely accessible characteristics, accurately identifies pediatric patients with cancer with FN at risk for AEs after reassessment.

Predictors of functional decline in elderly patients undergoing transcatheter aortic valve implantation (TAVI)

Aims This study aimed to assess functional course in elderly patients undergoing transcatheter aortic valve implantation (TAVI) and to find predictors of functional decline. Methods and results In this prospective cohort, functional course was assessed in patients ≥70 years using basic activities of daily living (BADL) before and 6 months after TAVI. Baseline EuroSCORE, STS score, and a frailty index (based on assessment of cognition, mobility, nutrition, instrumental and basic activities of daily living) were evaluated to predict functional decline (deterioration in BADL) using logistic regression models. Functional decline was observed in 22 (20.8%) of 106 surviving patients. EuroSCORE (OR per 10% increase 1.18, 95% CI: 0.83-1.68, P = 0.35) and STS score (OR per 5% increase 1.64, 95% CI: 0.87-3.09, P = 0.13) weakly predicted functional decline. In contrast, the frailty index strongly predicted functional decline in univariable (OR per 1 point increase 1.57, 95% CI: 1.20-2.05, P = 0.001) and bivariable analyses (OR: 1.56, 95% CI: 1.20-2.04, P = 0.001 controlled for EuroSCORE; OR: 1.53, 95% CI: 1.17-2.02, P = 0.002 controlled for STS score). Overall predictive performance was best for the frailty index [Nagelkerke's R(2) (NR(2)) 0.135] and low for the EuroSCORE (NR(2) 0.015) and STS score (NR(2) 0.034). In univariable analyses, all components of the frailty index contributed to the prediction of functional decline. Conclusion Over a 6-month period, functional status worsened only in a minority of patients surviving TAVI. The frailty index, but not established risk scores, was predictive of functional decline. Refinement of this index might help to identify patients who potentially benefit from additional geriatric interventions after TAVI.

Survival Analysis with Large Dimensional Covariates: An Application in Microarray Studies

Use of microarray technology often leads to high-dimensional and low- sample size data settings. Over the past several years, a variety of novel approaches have been proposed for variable selection in this context. However, only a small number of these have been adapted for time-to-event data where censoring is present. Among standard variable selection methods shown both to have good predictive accuracy and to be computationally efficient is the elastic net penalization approach. In this paper, adaptation of the elastic net approach is presented for variable selection both under the Cox proportional hazards model and under an accelerated failure time (AFT) model. Assessment of the two methods is conducted through simulation studies and through analysis of microarray data obtained from a set of patients with diffuse large B-cell lymphoma where time to survival is of interest. The approaches are shown to match or exceed the predictive performance of a Cox-based and an AFT-based variable selection method. The methods are moreover shown to be much more computationally efficient than their respective Cox- and AFT- based counterparts.

Practical Large-Scale Spatio-Temporal Modeling of Particulate Matter Concentrations

The last two decades have seen intense scientific and regulatory interest in the health effects of particulate matter (PM). Influential epidemiological studies that characterize chronic exposure of individuals rely on monitoring data that are sparse in space and time, so they often assign the same exposure to participants in large geographic areas and across time. We estimate monthly PM during 1988-2002 in a large spatial domain for use in studying health effects in the Nurses' Health Study. We develop a conceptually simple spatio-temporal model that uses a rich set of covariates. The model is used to estimate concentrations of PM10 for the full time period and PM2.5 for a subset of the period. For the earlier part of the period, 1988-1998, few PM2.5 monitors were operating, so we develop a simple extension to the model that represents PM2.5 conditionally on PM10 model predictions. In the epidemiological analysis, model predictions of PM10 are more strongly associated with health effects than when using simpler approaches to estimate exposure. Our modeling approach supports the application in estimating both fine-scale and large-scale spatial heterogeneity and capturing space-time interaction through the use of monthly-varying spatial surfaces. At the same time, the model is computationally feasible, implementable with standard software, and readily understandable to the scientific audience. Despite simplifying assumptions, the model has good predictive performance and uncertainty characterization.

Population pharmacokinetics of sevoflurane in conjunction with the AnaConDa: toward target-controlled infusion of volatiles into the breathing system

BACKGROUND: The Anesthetic Conserving Device (AnaConDa) uncouples delivery of a volatile anesthetic (VA) from fresh gas flow (FGF) using a continuous infusion of liquid volatile into a modified heat-moisture exchanger capable of adsorbing VA during expiration and releasing adsorbed VA during inspiration. It combines the simplicity and responsiveness of high FGF with low agent expenditures. We performed in vitro characterization of the device before developing a population pharmacokinetic model for sevoflurane administration with the AnaConDa, and retrospectively testing its performance (internal validation). MATERIALS AND METHODS: Eighteen females and 20 males, aged 31-87, BMI 20-38, were included. The end-tidal concentrations were varied and recorded together with the VA infusion rates into the device, ventilation and demographic data. The concentration-time course of sevoflurane was described using linear differential equations, and the most suitable structural model and typical parameter values were identified. The individual pharmacokinetic parameters were obtained and tested for covariate relationships. Prediction errors were calculated. RESULTS: In vitro studies assessed the contribution of the device to the pharmacokinetic model. In vivo, the sevoflurane concentration-time courses on the patient side of the AnaConDa were adequately described with a two-compartment model. The population median absolute prediction error was 27% (interquartile range 13-45%). CONCLUSION: The predictive performance of the two-compartment model was similar to that of models accepted for TCI administration of intravenous anesthetics, supporting open-loop administration of sevoflurane with the AnaConDa. Further studies will focus on prospective testing and external validation of the model implemented in a target-controlled infusion device.

On the modeling of drug induced respiratory depression in the non-steady-state

The ability of anesthetic agents to provide adequate analgesia and sedation is limited by the ventilatory depression associated with overdosing in spontaneously breathing patients. Therefore, quantitation of drug induced ventilatory depression is a pharmacokinetic-pharmacodynamic problem relevant to the practice of anesthesia. Although several studies describe the effect of respiratory depressant drugs on isolated endpoints, an integrated description of drug induced respiratory depression with parameters identifiable from clinically available data is not available. This study proposes a physiological model of CO2 disposition, ventilatory regulation, and the effects of anesthetic agents on the control of breathing. The predictive performance of the model is evaluated through simulations aimed at reproducing experimental observations of drug induced hypercarbia and hypoventilation associated with intravenous administration of a fast-onset, highly potent anesthetic mu agonist (including previously unpublished experimental data determined after administration of 1 mg alfentanil bolus). The proposed model structure has substantial descriptive capability and can provide clinically relevant predictions of respiratory inhibition in the non-steady-state to enhance safety of drug delivery in the anesthetic practice.

A simple asthma prediction tool for preschool children with wheeze or cough

BACKGROUND Many preschool children have wheeze or cough, but only some have asthma later. Existing prediction tools are difficult to apply in clinical practice or exhibit methodological weaknesses. OBJECTIVE We sought to develop a simple and robust tool for predicting asthma at school age in preschool children with wheeze or cough. METHODS From a population-based cohort in Leicestershire, United Kingdom, we included 1- to 3-year-old subjects seeing a doctor for wheeze or cough and assessed the prevalence of asthma 5 years later. We considered only noninvasive predictors that are easy to assess in primary care: demographic and perinatal data, eczema, upper and lower respiratory tract symptoms, and family history of atopy. We developed a model using logistic regression, avoided overfitting with the least absolute shrinkage and selection operator penalty, and then simplified it to a practical tool. We performed internal validation and assessed its predictive performance using the scaled Brier score and the area under the receiver operating characteristic curve. RESULTS Of 1226 symptomatic children with follow-up information, 345 (28%) had asthma 5 years later. The tool consists of 10 predictors yielding a total score between 0 and 15: sex, age, wheeze without colds, wheeze frequency, activity disturbance, shortness of breath, exercise-related and aeroallergen-related wheeze/cough, eczema, and parental history of asthma/bronchitis. The scaled Brier scores for the internally validated model and tool were 0.20 and 0.16, and the areas under the receiver operating characteristic curves were 0.76 and 0.74, respectively. CONCLUSION This tool represents a simple, low-cost, and noninvasive method to predict the risk of later asthma in symptomatic preschool children, which is ready to be tested in other populations.

A comparison of Markov and generalized linear models of hospital mortality

This paper reports a comparison of three modeling strategies for the analysis of hospital mortality in a sample of general medicine inpatients in a Department of Veterans Affairs medical center. Logistic regression, a Markov chain model, and longitudinal logistic regression were evaluated on predictive performance as measured by the c-index and on accuracy of expected numbers of deaths compared to observed. The logistic regression used patient information collected at admission; the Markov model was comprised of two absorbing states for discharge and death and three transient states reflecting increasing severity of illness as measured by laboratory data collected during the hospital stay; longitudinal regression employed Generalized Estimating Equations (GEE) to model covariance structure for the repeated binary outcome. Results showed that the logistic regression predicted hospital mortality as well as the alternative methods but was limited in scope of application. The Markov chain provides insights into how day to day changes of illness severity lead to discharge or death. The longitudinal logistic regression showed that increasing illness trajectory is associated with hospital mortality. The conclusion is reached that for standard applications in modeling hospital mortality, logistic regression is adequate, but for new challenges facing health services research today, alternative methods are equally predictive, practical, and can provide new insights. ^

Predicting smoking cessation and its relapse in HIV-infected patients: the Swiss HIV Cohort Study

OBJECTIVES: The aim of the study was to assess whether prospective follow-up data within the Swiss HIV Cohort Study can be used to predict patients who stop smoking; or among smokers who stop, those who start smoking again. METHODS: We built prediction models first using clinical reasoning ('clinical models') and then by selecting from numerous candidate predictors using advanced statistical methods ('statistical models'). Our clinical models were based on literature that suggests that motivation drives smoking cessation, while dependence drives relapse in those attempting to stop. Our statistical models were based on automatic variable selection using additive logistic regression with component-wise gradient boosting. RESULTS: Of 4833 smokers, 26% stopped smoking, at least temporarily; because among those who stopped, 48% started smoking again. The predictive performance of our clinical and statistical models was modest. A basic clinical model for cessation, with patients classified into three motivational groups, was nearly as discriminatory as a constrained statistical model with just the most important predictors (the ratio of nonsmoking visits to total visits, alcohol or drug dependence, psychiatric comorbidities, recent hospitalization and age). A basic clinical model for relapse, based on the maximum number of cigarettes per day prior to stopping, was not as discriminatory as a constrained statistical model with just the ratio of nonsmoking visits to total visits. CONCLUSIONS: Predicting smoking cessation and relapse is difficult, so that simple models are nearly as discriminatory as complex ones. Patients with a history of attempting to stop and those known to have stopped recently are the best candidates for an intervention.

Role of Urbanization, Land-Use Diversity, and Livestock Intensification in Zoonotic Emerging Infectious Diseases

Emerging infectious diseases (EIDs) continue to significantly threaten human and animal health. While there has been some progress in identifying underlying proximal driving forces and causal mechanisms of disease emergence, the role of distal factors is most poorly understood. This article focuses on analyzing the statistical association between highly pathogenic avian influenza (HPAI) H5N1 and urbanization, land-use diversity and poultry intensification. A special form of the urban transition—peri-urbanization—was hypothesized as being associated with ‘hot-spots’ of disease emergence. Novel metrics were used to characterize these distal risk factors. Our models, which combined these newly proposed risk factors with previously known natural and human risk factors, had a far higher predictive performance compared to published models for the first two epidemiological waves in Viet Nam. We found that when relevant risk factors are taken into account, urbanization is generally not a significant independent risk factor. However, urbanization spatially combines other risk factors leading to peri-urban places being the most likely ‘hot-spots’. The work highlights that peri-urban areas have highest levels of chicken density, duck and geese flock size diversity, fraction of land under rice, fraction of land under aquaculture compared to rural and urban areas. Land-use diversity, which has previously never been studied in the context of HPAI H5N1, was found to be a significant risk factor. Places where intensive and extensive forms of poultry production are collocated were found to be at greater risk.