Absence motivated by illness: A non-concurrent prospective study of physical education teachers in the municipal education system of the city of Campinas, São Paulo, Brazil

The object of this investigation was to identify and analize aspects of the health status related to absenteism in physical education teachers in the municipal education system of the city of Campinas, Brazil, as related to the medical leave program. The non-concurrent prospective study was accomplished by means of a comparison with teachers who work only in the classroom, refering to a three year period. In the variables of greatest interest, the Pearson non-parametric chi-square (X2) statistical test was adopted. Calculations of relative risk and level of confidence were made using the Epi-info computer program. Significant differences were observed in the following diagnostic groups favoring the not exposed group: i) Supplementary Classification of factors that exercise influence over the health status and access to health services and ii) Digestive system illness; while the physical education teachers showed a significant difference in: i) diseases of the musculoskeletal and connective tissue system and ii) Injuries and poisoing. Possible explications for some of the adverse effects as well as the protective ones that were observed include physical activity as a way of life along with being a physical education teacher and on the other side, peculiar behavior of epidemiological descriptive characteristics, like sex and age, within the socio-economic context of the country. © Copyright Moreira Jr. Editora.

Métodos de bootstrap e aplicações em problemas biológicos

Pós-graduação em Matemática Universitária - IGCE

Home ranges of Guiana dolphins (Sotalia guianensis) (Cetacea: Delphinidae) in the Cananeia estuary, Brazil

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

Clinicopathologic findings in thoroughbred horses during a high speed – short term competition

The aim of this study was to examine whether a real high speed-short term competition influences clinicopathological data focusing on muscle enzymes, iron profile and Acute Phase Proteins. 30 Thoroughbred racing horses (15 geldings and 15 females) aged between 4-12 years (mean 7 years), were used for the study. All the animals performed a high speed-short term competition for a total distance of 154 m in about 12 seconds, repeated 8 times, within approximately one hour (Niballo Horse Race). Blood samples were obtained 24 hours before and within 30 minutes after the end of the races. On all samples were performed a complete blood count (CBC), biochemical and haemostatic profiles. The post-race concentrations for the single parameter were corrected using an estimation of the plasma volume contraction according to the individual Alb concentration. Data were analysed with descriptive statistics and the percentage of variation from the baseline values were recorded. Pre- and post-race results were compared with non-parametric statistics (Mann Whitney U test). A difference was considered significant at p<0.05. A significant plasma volume contraction after the race was detected (Hct, Alb; p<0.01). Other relevant findings were increased concentrations of muscular enzymes (CK, LDH; p<0.01), Crt (p<0.01), significant increased uric acid (p<0.01), a significant decrease of haptoglobin (p<0.01) associated to an increase of ferritin concentrations (p<0.01), significant decrease of fibrinogen (p<0.05) accompanied by a non-significant increase of D-Dimers concentrations (p=0.08). This competition produced relevant abnormalities on clinical pathology in galloping horses. This study confirms a significant muscular damage, oxidative stress, intravascular haemolysis and subclinical hemostatic alterations. Further studies are needed to better understand the pathogenesis, the medical relevance and the impact on performance of these alterations in equine sport medicine.

Studio del metodo "systolic volume balance" per la stima non invasiva della portata media cardiaca

La portata media cardiaca, (cardiac output “CO”) è un parametro essenziale per una buona gestione dei pazienti o per il monitoraggio degli stessi durante la loro permanenza nell’unità di terapia intensiva. La stesura di questo elaborato prende spunto sull’articolo di Theodore G. Papaioannou, Orestis Vardoulis, and Nikos Stergiopulos dal titolo “ The “systolic volume balance” method for the non invasive estimation of cardiac output based on pressure wave analysis” pubblicato sulla rivista American Journal of Physiology-Heart and Circulatory Physiology nel Marzo 2012. Nel sopracitato articolo si propone un metodo per il monitoraggio potenzialmente non invasivo della portata media cardiaca, basato su principi fisici ed emodinamici, che usa l’analisi della forma d’onda di pressione e un metodo non invasivo di calibrazione e trova la sua espressione ultima nell’equazione Qsvb=(C*PPao)/(T-(Psm,aorta*ts)/Pm). Questa formula è stata validata dagli autori, con buoni risultati, solo su un modello distribuito della circolazione sistemica e non è ancora stato validato in vivo. Questo elaborato si pone come obiettivo quello di un’analisi critica di questa formula per la stima della portata media cardiaca Qsvb. La formula proposta nell'articolo verrà verificata nel caso in cui la circolazione sistemica sia approssimata con modelli di tipo windkessel. Dallo studio svolto emerge il fatto che la formula porta risultati con errori trascurabili solo se si approssima la circolazione sistemica con il modello windkessel classico a due elementi (WK2) e la portata aortica con un’onda rettangolare. Approssimando la circolazione sistemica con il modello windkessel a tre elementi (WK3), o descrivendo la portata aortica con un’onda triangolare si ottengono risultati con errori non più trascurabili che variano dal 7%-9% nel caso del WK2 con portata aortica approssimata con onda triangolare ad errori più ampi del 20% nei i casi del WK3 per entrambe le approssimazioni della portata aortica.

Mechanical non-surgical treatment of peri-implantitis: a single-blinded randomized longitudinal clinical study. II. Microbiological results

BACKGROUND: Peri-implantitis is common in patients with dental implants. We performed a single-blinded longitudinal randomized study to assess the effects of mechanical debridement on the peri-implant microbiota in peri-implantitis lesions. MATERIALS AND METHODS: An expanded checkerboard DNA-DNA hybridization assay encompassing 79 different microorganisms was used to study bacterial counts before and during 6 months following mechanical treatment of peri-implantitis in 17 cases treated with curettes and 14 cases treated with an ultrasonic device. Statistics included non-parametric tests and GLM multivariate analysis with p<0001 indicating significance and 80% power. RESULTS: At selected implant test sites, the most prevalent bacteria were: Fusobacterium nucleatum sp., Staphylococci sp., Aggregatibacter actinomycetemcomitans, Helicobacter pylori, and Tannerella forsythia. 30 min. after treatment with curettes, A. actinomycetemcomitans (serotype a), Lactobacillus acidophilus, Streptococcus anginosus, and Veillonella parvula were found at lower counts (p<0.001). No such differences were found for implants treated with the ultrasonic device. Inconsistent changes occurred following the first week. No microbiological differences between baseline and 6-month samples were found for any species or between treatment study methods in peri-implantitis. CONCLUSIONS: Both methods failed to eliminate or reduce bacterial counts in peri-implantitis. No group differences were found in the ability to reduce the microbiota in peri-implantitis.

First trimester markers for pre-eclampsia: placental vs. non-placental protein serum levels

BACKGROUND/AIM: Parallel investigation, in a matched case-control study, of the association of different first-trimester markers with the risk of subsequent pre-eclampsia (PE). METHOD: The levels of different first trimester serum markers and fetal nuchal translucency thickness were compared between 52 cases of PE and 104 control women by non-parametric two-group comparisons and by calculating matched odds ratios. RESULTS: In univariable analysis increased concentrations of inhibin A and activin A were associated with subsequent PE (p < 0.02). Multivariable conditional logistic regression models revealed an association between increased risk of PE and increased inhibin A and translucency thickness and respectively reduced pregnancy-associated plasma protein A (PAPP-A) and placental lactogen . However, these associations varied with the gestational age at sample collection. For blood samples taken in pregnancy weeks 12 and 13 only, increased levels of activin A, inhibin A and nuchal translucency thickness, and lower levels of placenta growth factor and PAPP-A were associated with an increased risk of PE. CONCLUSIONS: Members of the inhibin family and to some extent PAPP-A and placental growth factor are superior to other serum markers, and the predictive value of these depends on the gestational age at blood sampling. The availability of a single, early pregnancy 'miracle' serum marker for PE risk assessment seems unlikely in the near future.

Comparison of two non-bronchoscopic methods for evaluating inflammation in patients with acute hypoxaemic respiratory failure

INTRODUCTION: The simple bedside method for sampling undiluted distal pulmonary edema fluid through a normal suction catheter (s-Cath) has been experimentally and clinically validated. However, there are no data comparing non-bronchoscopic bronchoalveolar lavage (mini-BAL) and s-Cath for assessing lung inflammation in acute hypoxaemic respiratory failure. We designed a prospective study in two groups of patients, those with acute lung injury (ALI)/acute respiratory distress syndrome (ARDS) and those with acute cardiogenic lung edema (ACLE), designed to investigate the clinical feasibility of these techniques and to evaluate inflammation in both groups using undiluted sampling obtained by s-Cath. To test the interchangeability of the two methods in the same patient for studying the inflammation response, we further compared mini-BAL and s-Cath for agreement of protein concentration and percentage of polymorphonuclear cells (PMNs). METHODS: Mini-BAL and s-Cath sampling was assessed in 30 mechanically ventilated patients, 21 with ALI/ARDS and 9 with ACLE. To analyse agreement between the two sampling techniques, we considered only simultaneously collected mini-BAL and s-Cath paired samples. The protein concentration and polymorphonuclear cell (PMN) count comparisons were performed using undiluted sampling. Bland-Altman plots were used for assessing the mean bias and the limits of agreement between the two sampling techniques; comparison between groups was performed by using the non-parametric Mann-Whitney-U test; continuous variables were compared by using the Student t-test, Wilcoxon signed rank test, analysis of variance or Student-Newman-Keuls test; and categorical variables were compared by using chi-square analysis or Fisher exact test. RESULTS: Using protein content and PMN percentage as parameters, we identified substantial variations between the two sampling techniques. When the protein concentration in the lung was high, the s-Cath was a more sensitive method; by contrast, as inflammation increased, both methods provided similar estimates of neutrophil percentages in the lung. The patients with ACLE showed an increased PMN count, suggesting that hydrostatic lung edema can be associated with a concomitant inflammatory process. CONCLUSIONS: There are significant differences between the s-Cath and mini-BAL sampling techniques, indicating that these procedures cannot be used interchangeably for studying the lung inflammatory response in patients with acute hypoxaemic lung injury.

Mechanical non-surgical treatment of peri-implantitis: a double-blind randomized longitudinal clinical study. I: clinical results

BACKGROUND: Peri-implantitis is a frequent finding in patients with dental implants. The present study compared two non-surgical mechanical debridement methods of peri-implantitis. MATERIAL AND METHODS: Thirty-seven subjects (mean age 61.5; S.D+/-12.4), with one implant each, demonstrating peri-implantitis were randomized, and those treated either with titanium hand-instruments or with an ultrasonic device were enrolled. Data were obtained before treatment, and at 1, 3, and 6 months. Parametric and non-parametric statistics were used. RESULTS: Thirty-one subjects completed the study. The mean bone loss at implants in both groups was 1.5 mm (SD +/-1.2 mm). No group differences for plaque or gingival indices were found at any time point. Baseline and 6-month mean probing pocket depths (PPD) at implants were 5.1 and 4.9 mm (p=0.30) in both groups. Plaque scores at treated implants decreased from 73% to 53% (p<0.01). Bleeding scores also decreased (p<0.01), with no group differences. No differences in the total bacterial counts were found over time. Higher total bacterial counts were found immediately after treatment (p<0.01) and at 1 week for ultrasonic-treated implants (p<0.05). CONCLUSIONS: No group differences were found in the treatment outcomes. While plaque and bleeding scores improved, no effects on PPD were identified.

Reflectance Transfer for Material Editing and Relighting

We present a new approach to diffuse reflectance estimation for dynamic scenes. Non-parametric image statistics are used to transfer reflectance properties from a static example set to a dynamic image sequence. The approach allows diffuse reflectance estimation for surface materials with inhomogeneous appearance, such as those which commonly occur with patterned or textured clothing. Material editing is also possible by transferring edited reflectance properties. Material reflectance properties are initially estimated from static images of the subject under multiple directional illuminations using photometric stereo. The estimated reflectance together with the corresponding image under uniform ambient illumination form a prior set of reference material observations. Material reflectance properties are then estimated for video sequences of a moving person captured under uniform ambient illumination by matching the observed local image statistics to the reference observations. Results demonstrate that the transfer of reflectance properties enables estimation of the dynamic surface normals and subsequent relighting combined with material editing. This approach overcomes limitations of previous work on material transfer and relighting of dynamic scenes which was limited to surfaces with regions of homogeneous reflectance. We evaluate our approach for relighting 3D model sequences reconstructed from multiple view video. Comparison to previous model relighting demonstrates improved reproduction of detailed texture and shape dynamics.

Identifying Individual and Group Effects in the Presence of Sorting: A Neighborhood Effects Application

Researchers have long recognized that the non-random sorting of individuals into groups generates correlation between individual and group attributes that is likely to bias naive estimates of both individual and group effects. This paper proposes a non-parametric strategy for identifying these effects in a model that allows for both individual and group unobservables, applying this strategy to the estimation of neighborhood effects on labor market outcomes. The first part of this strategy is guided by a robust feature of the equilibrium in the canonical vertical sorting model of Epple and Platt (1998), that there is a monotonic relationship between neighborhood housing prices and neighborhood quality. This implies that under certain conditions a non- parametric function of neighborhood housing prices serves as a suitable control function for the neighborhood unobservable in the labor market outcome regression. The second part of the proposed strategy uses aggregation to develop suitable instruments for both exogenous and endogenous group attributes. Instrumenting for each individual's observed neighborhood attributes with the average neighborhood attributes of a set of observationally identical individuals eliminates the portion of the variation in neighborhood attributes due to sorting on unobserved individual attributes. The neighborhood effects application is based on confidential microdata from the 1990 Decennial Census for the Boston MSA. The results imply that the direct effects of geographic proximity to jobs, neighborhood poverty rates, and average neighborhood education are substantially larger than the conditional correlations identified using OLS, although the net effect of neighborhood quality on labor market outcomes remains small. These findings are robust across a wide variety of specifications and robustness checks.

Regularization for sparsity in statistical analysis and machine learning

Pragmatism is the leading motivation of regularization. We can understand regularization as a modification of the maximum-likelihood estimator so that a reasonable answer could be given in an unstable or ill-posed situation. To mention some typical examples, this happens when fitting parametric or non-parametric models with more parameters than data or when estimating large covariance matrices. Regularization is usually used, in addition, to improve the bias-variance tradeoff of an estimation. Then, the definition of regularization is quite general, and, although the introduction of a penalty is probably the most popular type, it is just one out of multiple forms of regularization. In this dissertation, we focus on the applications of regularization for obtaining sparse or parsimonious representations, where only a subset of the inputs is used. A particular form of regularization, L1-regularization, plays a key role for reaching sparsity. Most of the contributions presented here revolve around L1-regularization, although other forms of regularization are explored (also pursuing sparsity in some sense). In addition to present a compact review of L1-regularization and its applications in statistical and machine learning, we devise methodology for regression, supervised classification and structure induction of graphical models. Within the regression paradigm, we focus on kernel smoothing learning, proposing techniques for kernel design that are suitable for high dimensional settings and sparse regression functions. We also present an application of regularized regression techniques for modeling the response of biological neurons. Supervised classification advances deal, on the one hand, with the application of regularization for obtaining a na¨ıve Bayes classifier and, on the other hand, with a novel algorithm for brain-computer interface design that uses group regularization in an efficient manner. Finally, we present a heuristic for inducing structures of Gaussian Bayesian networks using L1-regularization as a filter. El pragmatismo es la principal motivación de la regularización. Podemos entender la regularización como una modificación del estimador de máxima verosimilitud, de tal manera que se pueda dar una respuesta cuando la configuración del problema es inestable. A modo de ejemplo, podemos mencionar el ajuste de modelos paramétricos o no paramétricos cuando hay más parámetros que casos en el conjunto de datos, o la estimación de grandes matrices de covarianzas. Se suele recurrir a la regularización, además, para mejorar el compromiso sesgo-varianza en una estimación. Por tanto, la definición de regularización es muy general y, aunque la introducción de una función de penalización es probablemente el método más popular, éste es sólo uno de entre varias posibilidades. En esta tesis se ha trabajado en aplicaciones de regularización para obtener representaciones dispersas, donde sólo se usa un subconjunto de las entradas. En particular, la regularización L1 juega un papel clave en la búsqueda de dicha dispersión. La mayor parte de las contribuciones presentadas en la tesis giran alrededor de la regularización L1, aunque también se exploran otras formas de regularización (que igualmente persiguen un modelo disperso). Además de presentar una revisión de la regularización L1 y sus aplicaciones en estadística y aprendizaje de máquina, se ha desarrollado metodología para regresión, clasificación supervisada y aprendizaje de estructura en modelos gráficos. Dentro de la regresión, se ha trabajado principalmente en métodos de regresión local, proponiendo técnicas de diseño del kernel que sean adecuadas a configuraciones de alta dimensionalidad y funciones de regresión dispersas. También se presenta una aplicación de las técnicas de regresión regularizada para modelar la respuesta de neuronas reales. Los avances en clasificación supervisada tratan, por una parte, con el uso de regularización para obtener un clasificador naive Bayes y, por otra parte, con el desarrollo de un algoritmo que usa regularización por grupos de una manera eficiente y que se ha aplicado al diseño de interfaces cerebromáquina. Finalmente, se presenta una heurística para inducir la estructura de redes Bayesianas Gaussianas usando regularización L1 a modo de filtro.

Contributions to Bayesian network learning with applications to neuroscience

Neuronal morphology is a key feature in the study of brain circuits, as it is highly related to information processing and functional identification. Neuronal morphology affects the process of integration of inputs from other neurons and determines the neurons which receive the output of the neurons. Different parts of the neurons can operate semi-independently according to the spatial location of the synaptic connections. As a result, there is considerable interest in the analysis of the microanatomy of nervous cells since it constitutes an excellent tool for better understanding cortical function. However, the morphologies, molecular features and electrophysiological properties of neuronal cells are extremely variable. Except for some special cases, this variability makes it hard to find a set of features that unambiguously define a neuronal type. In addition, there are distinct types of neurons in particular regions of the brain. This morphological variability makes the analysis and modeling of neuronal morphology a challenge. Uncertainty is a key feature in many complex real-world problems. Probability theory provides a framework for modeling and reasoning with uncertainty. Probabilistic graphical models combine statistical theory and graph theory to provide a tool for managing domains with uncertainty. In particular, we focus on Bayesian networks, the most commonly used probabilistic graphical model. In this dissertation, we design new methods for learning Bayesian networks and apply them to the problem of modeling and analyzing morphological data from neurons. The morphology of a neuron can be quantified using a number of measurements, e.g., the length of the dendrites and the axon, the number of bifurcations, the direction of the dendrites and the axon, etc. These measurements can be modeled as discrete or continuous data. The continuous data can be linear (e.g., the length or the width of a dendrite) or directional (e.g., the direction of the axon). These data may follow complex probability distributions and may not fit any known parametric distribution. Modeling this kind of problems using hybrid Bayesian networks with discrete, linear and directional variables poses a number of challenges regarding learning from data, inference, etc. In this dissertation, we propose a method for modeling and simulating basal dendritic trees from pyramidal neurons using Bayesian networks to capture the interactions between the variables in the problem domain. A complete set of variables is measured from the dendrites, and a learning algorithm is applied to find the structure and estimate the parameters of the probability distributions included in the Bayesian networks. Then, a simulation algorithm is used to build the virtual dendrites by sampling values from the Bayesian networks, and a thorough evaluation is performed to show the model’s ability to generate realistic dendrites. In this first approach, the variables are discretized so that discrete Bayesian networks can be learned and simulated. Then, we address the problem of learning hybrid Bayesian networks with different kinds of variables. Mixtures of polynomials have been proposed as a way of representing probability densities in hybrid Bayesian networks. We present a method for learning mixtures of polynomials approximations of one-dimensional, multidimensional and conditional probability densities from data. The method is based on basis spline interpolation, where a density is approximated as a linear combination of basis splines. The proposed algorithms are evaluated using artificial datasets. We also use the proposed methods as a non-parametric density estimation technique in Bayesian network classifiers. Next, we address the problem of including directional data in Bayesian networks. These data have some special properties that rule out the use of classical statistics. Therefore, different distributions and statistics, such as the univariate von Mises and the multivariate von Mises–Fisher distributions, should be used to deal with this kind of information. In particular, we extend the naive Bayes classifier to the case where the conditional probability distributions of the predictive variables given the class follow either of these distributions. We consider the simple scenario, where only directional predictive variables are used, and the hybrid case, where discrete, Gaussian and directional distributions are mixed. The classifier decision functions and their decision surfaces are studied at length. Artificial examples are used to illustrate the behavior of the classifiers. The proposed classifiers are empirically evaluated over real datasets. We also study the problem of interneuron classification. An extensive group of experts is asked to classify a set of neurons according to their most prominent anatomical features. A web application is developed to retrieve the experts’ classifications. We compute agreement measures to analyze the consensus between the experts when classifying the neurons. Using Bayesian networks and clustering algorithms on the resulting data, we investigate the suitability of the anatomical terms and neuron types commonly used in the literature. Additionally, we apply supervised learning approaches to automatically classify interneurons using the values of their morphological measurements. Then, a methodology for building a model which captures the opinions of all the experts is presented. First, one Bayesian network is learned for each expert, and we propose an algorithm for clustering Bayesian networks corresponding to experts with similar behaviors. Then, a Bayesian network which represents the opinions of each group of experts is induced. Finally, a consensus Bayesian multinet which models the opinions of the whole group of experts is built. A thorough analysis of the consensus model identifies different behaviors between the experts when classifying the interneurons in the experiment. A set of characterizing morphological traits for the neuronal types can be defined by performing inference in the Bayesian multinet. These findings are used to validate the model and to gain some insights into neuron morphology. Finally, we study a classification problem where the true class label of the training instances is not known. Instead, a set of class labels is available for each instance. This is inspired by the neuron classification problem, where a group of experts is asked to individually provide a class label for each instance. We propose a novel approach for learning Bayesian networks using count vectors which represent the number of experts who selected each class label for each instance. These Bayesian networks are evaluated using artificial datasets from supervised learning problems. Resumen La morfología neuronal es una característica clave en el estudio de los circuitos cerebrales, ya que está altamente relacionada con el procesado de información y con los roles funcionales. La morfología neuronal afecta al proceso de integración de las señales de entrada y determina las neuronas que reciben las salidas de otras neuronas. Las diferentes partes de la neurona pueden operar de forma semi-independiente de acuerdo a la localización espacial de las conexiones sinápticas. Por tanto, existe un interés considerable en el análisis de la microanatomía de las células nerviosas, ya que constituye una excelente herramienta para comprender mejor el funcionamiento de la corteza cerebral. Sin embargo, las propiedades morfológicas, moleculares y electrofisiológicas de las células neuronales son extremadamente variables. Excepto en algunos casos especiales, esta variabilidad morfológica dificulta la definición de un conjunto de características que distingan claramente un tipo neuronal. Además, existen diferentes tipos de neuronas en regiones particulares del cerebro. La variabilidad neuronal hace que el análisis y el modelado de la morfología neuronal sean un importante reto científico. La incertidumbre es una propiedad clave en muchos problemas reales. La teoría de la probabilidad proporciona un marco para modelar y razonar bajo incertidumbre. Los modelos gráficos probabilísticos combinan la teoría estadística y la teoría de grafos con el objetivo de proporcionar una herramienta con la que trabajar bajo incertidumbre. En particular, nos centraremos en las redes bayesianas, el modelo más utilizado dentro de los modelos gráficos probabilísticos. En esta tesis hemos diseñado nuevos métodos para aprender redes bayesianas, inspirados por y aplicados al problema del modelado y análisis de datos morfológicos de neuronas. La morfología de una neurona puede ser cuantificada usando una serie de medidas, por ejemplo, la longitud de las dendritas y el axón, el número de bifurcaciones, la dirección de las dendritas y el axón, etc. Estas medidas pueden ser modeladas como datos continuos o discretos. A su vez, los datos continuos pueden ser lineales (por ejemplo, la longitud o la anchura de una dendrita) o direccionales (por ejemplo, la dirección del axón). Estos datos pueden llegar a seguir distribuciones de probabilidad muy complejas y pueden no ajustarse a ninguna distribución paramétrica conocida. El modelado de este tipo de problemas con redes bayesianas híbridas incluyendo variables discretas, lineales y direccionales presenta una serie de retos en relación al aprendizaje a partir de datos, la inferencia, etc. En esta tesis se propone un método para modelar y simular árboles dendríticos basales de neuronas piramidales usando redes bayesianas para capturar las interacciones entre las variables del problema. Para ello, se mide un amplio conjunto de variables de las dendritas y se aplica un algoritmo de aprendizaje con el que se aprende la estructura y se estiman los parámetros de las distribuciones de probabilidad que constituyen las redes bayesianas. Después, se usa un algoritmo de simulación para construir dendritas virtuales mediante el muestreo de valores de las redes bayesianas. Finalmente, se lleva a cabo una profunda evaluaci ón para verificar la capacidad del modelo a la hora de generar dendritas realistas. En esta primera aproximación, las variables fueron discretizadas para poder aprender y muestrear las redes bayesianas. A continuación, se aborda el problema del aprendizaje de redes bayesianas con diferentes tipos de variables. Las mixturas de polinomios constituyen un método para representar densidades de probabilidad en redes bayesianas híbridas. Presentamos un método para aprender aproximaciones de densidades unidimensionales, multidimensionales y condicionales a partir de datos utilizando mixturas de polinomios. El método se basa en interpolación con splines, que aproxima una densidad como una combinación lineal de splines. Los algoritmos propuestos se evalúan utilizando bases de datos artificiales. Además, las mixturas de polinomios son utilizadas como un método no paramétrico de estimación de densidades para clasificadores basados en redes bayesianas. Después, se estudia el problema de incluir información direccional en redes bayesianas. Este tipo de datos presenta una serie de características especiales que impiden el uso de las técnicas estadísticas clásicas. Por ello, para manejar este tipo de información se deben usar estadísticos y distribuciones de probabilidad específicos, como la distribución univariante von Mises y la distribución multivariante von Mises–Fisher. En concreto, en esta tesis extendemos el clasificador naive Bayes al caso en el que las distribuciones de probabilidad condicionada de las variables predictoras dada la clase siguen alguna de estas distribuciones. Se estudia el caso base, en el que sólo se utilizan variables direccionales, y el caso híbrido, en el que variables discretas, lineales y direccionales aparecen mezcladas. También se estudian los clasificadores desde un punto de vista teórico, derivando sus funciones de decisión y las superficies de decisión asociadas. El comportamiento de los clasificadores se ilustra utilizando bases de datos artificiales. Además, los clasificadores son evaluados empíricamente utilizando bases de datos reales. También se estudia el problema de la clasificación de interneuronas. Desarrollamos una aplicación web que permite a un grupo de expertos clasificar un conjunto de neuronas de acuerdo a sus características morfológicas más destacadas. Se utilizan medidas de concordancia para analizar el consenso entre los expertos a la hora de clasificar las neuronas. Se investiga la idoneidad de los términos anatómicos y de los tipos neuronales utilizados frecuentemente en la literatura a través del análisis de redes bayesianas y la aplicación de algoritmos de clustering. Además, se aplican técnicas de aprendizaje supervisado con el objetivo de clasificar de forma automática las interneuronas a partir de sus valores morfológicos. A continuación, se presenta una metodología para construir un modelo que captura las opiniones de todos los expertos. Primero, se genera una red bayesiana para cada experto y se propone un algoritmo para agrupar las redes bayesianas que se corresponden con expertos con comportamientos similares. Después, se induce una red bayesiana que modela la opinión de cada grupo de expertos. Por último, se construye una multired bayesiana que modela las opiniones del conjunto completo de expertos. El análisis del modelo consensuado permite identificar diferentes comportamientos entre los expertos a la hora de clasificar las neuronas. Además, permite extraer un conjunto de características morfológicas relevantes para cada uno de los tipos neuronales mediante inferencia con la multired bayesiana. Estos descubrimientos se utilizan para validar el modelo y constituyen información relevante acerca de la morfología neuronal. Por último, se estudia un problema de clasificación en el que la etiqueta de clase de los datos de entrenamiento es incierta. En cambio, disponemos de un conjunto de etiquetas para cada instancia. Este problema está inspirado en el problema de la clasificación de neuronas, en el que un grupo de expertos proporciona una etiqueta de clase para cada instancia de manera individual. Se propone un método para aprender redes bayesianas utilizando vectores de cuentas, que representan el número de expertos que seleccionan cada etiqueta de clase para cada instancia. Estas redes bayesianas se evalúan utilizando bases de datos artificiales de problemas de aprendizaje supervisado.

Conditional density approximations with mixtures of polynomials

Mixtures of polynomials (MoPs) are a non-parametric density estimation technique especially designed for hybrid Bayesian networks with continuous and discrete variables. Algorithms to learn one- and multi-dimensional (marginal) MoPs from data have recently been proposed. In this paper we introduce two methods for learning MoP approximations of conditional densities from data. Both approaches are based on learning MoP approximations of the joint density and the marginal density of the conditioning variables, but they differ as to how the MoP approximation of the quotient of the two densities is found. We illustrate and study the methods using data sampled from known parametric distributions, and we demonstrate their applicability by learning models based on real neuroscience data. Finally, we compare the performance of the proposed methods with an approach for learning mixtures of truncated basis functions (MoTBFs). The empirical results show that the proposed methods generally yield models that are comparable to or significantly better than those found using the MoTBF-based method.

Carotid artery intimal medial thickness, brachial artery flow-mediated vasodilation and cardiovascular risk factors in diabetic and non-diabetic indigenous Australians

Background: Indigenous Australians are at high risk for cardiovascular disease and type 2 diabetes. Carotid artery intimal medial thickness (CIMT) and brachial artery flow-mediated vasodilation (FMD) are ultrasound imaging based surrogate markers of cardiovascular risk. This study examines the relative contributions of traditional cardiovascular risk factors on CIMT and FMD in adult Indigenous Australians with and without type 2 diabetes mellitus. Method: One hundred and nineteen Indigenous Australians were recruited. Physical and biochemical markers of cardiovascular risk, together with CIMT and FMD were meausred for all subjects. Results: Fifty-three Indigenous Australians subjects (45%) had type 2 diabetes mellitus. There was a significantly greater mean CIMT in diabetic versus non-diabetic subjects (p = 0.049). In the non-diabetic group with non-parametric analyses, there were significant correlations between CIMT and: age (r = 0.64, p < 0.001), systolic blood pressure (r = 0.47, p < 0.001) and non-smokers (r = -0.30, p = 0.018). In the diabetic group, non-parametric analysis showed correlations between CIMT, age (r = 0.36, p = 0.009) and duration of diabetes (r = 0.30, p = 0.035) only. Adjusting forage, sex, smoking and history of cardiovascular disease, Hb(A1c) became the sole significant correlate of CIMT (r = 0.35,p = 0.01) in the diabetic group. In non-parametric analysis, age was the sole significant correlate of FMD (r = -0.31,p = 0.013), and only in non-diabetic subjects. Linear regression analysis showed significant associations between CIMT and age (t = 4.6,p < 0.001), systolic blood pressure (t = 2.6, p = 0.010) and Hb(A1c) (t = 2.6, p = 0.012), smoking (t = 2.1, p = 0.04) and fasting LDL-cholesterol (t = 2.1, p = 0.04). There were no significant associations between FMD and examined cardiovascular risk factors with linear regression analysis Conclusions: CIMT appears to be a useful surrogate marker of cardiovascular risk in this sample of Indigenous Australian subjects, correlating better than FMD with established cardiovascular risk factors. A lifestyle intervention programme may alleviate the burden of cardiovascular disease in Indigenous Australians by reducing central obesity, lowering blood pressure, correcting dyslipidaemia and improving glycaemic control. CIMT may prove to be a useful tool to assess efficacy of such an intervention programme. (c) 2004 Elsevier Ireland Ltd. All rights reserved.