Quantifying and Comparing the Accuracy of Binary Biomarkers When Predicting a Failure Time Outcome

The positive and negative predictive value are standard measures used to quantify the predictive accuracy of binary biomarkers when the outcome being predicted is also binary. When the biomarkers are instead being used to predict a failure time outcome, there is no standard way of quantifying predictive accuracy. We propose a natural extension of the traditional predictive values to accommodate censored survival data. We discuss not only quantifying predictive accuracy using these extended predictive values, but also rigorously comparing the accuracy of two biomarkers in terms of their predictive values. Using a marginal regression framework, we describe how to estimate differences in predictive accuracy and how to test whether the observed difference is statistically significant.

Motives for cannabis use as a moderator variable of distress among young adults

This study examined the moderating effect of social and coping motives on distress among young cannabis-using adults. A random sample of 2031 young Swiss adults was interviewed by means of a computer-assisted telephone interview. Cannabis users showed more distress, less positive health behaviour and higher hedonism compared to non-users. Taking motive for use as a moderator variable into consideration, it became evident that only cannabis users with coping motives showed lower mental health, more symptoms of psychopathology, more psychosocial distress and more life events than non-users. Young adults with social motives for use on the other hand did not differ from non-users in terms of distress. These differences between cannabis users with social and those with coping motives remained stable over two years. In both subgroups, participants with regular cannabis use at baseline did not increase distress nor did participants with higher distress at baseline increase the frequency of their cannabis use. Our results suggest that secondary prevention for cannabis users should target especially young adults with coping motives for use.

Model Evaluation Based on the Distribution of Estimated Absolute Prediction Error

The construction of a reliable, practically useful prediction rule for future response is heavily dependent on the "adequacy" of the fitted regression model. In this article, we consider the absolute prediction error, the expected value of the absolute difference between the future and predicted responses, as the model evaluation criterion. This prediction error is easier to interpret than the average squared error and is equivalent to the mis-classification error for the binary outcome. We show that the distributions of the apparent error and its cross-validation counterparts are approximately normal even under a misspecified fitted model. When the prediction rule is "unsmooth", the variance of the above normal distribution can be estimated well via a perturbation-resampling method. We also show how to approximate the distribution of the difference of the estimated prediction errors from two competing models. With two real examples, we demonstrate that the resulting interval estimates for prediction errors provide much more information about model adequacy than the point estimates alone.

Semiparametric Latent Variable Regression Models for Spatio-temporal Modeling of Mobile Source Particles in the Greater Boston Area

Traffic particle concentrations show considerable spatial variability within a metropolitan area. We consider latent variable semiparametric regression models for modeling the spatial and temporal variability of black carbon and elemental carbon concentrations in the greater Boston area. Measurements of these pollutants, which are markers of traffic particles, were obtained from several individual exposure studies conducted at specific household locations as well as 15 ambient monitoring sites in the city. The models allow for both flexible, nonlinear effects of covariates and for unexplained spatial and temporal variability in exposure. In addition, the different individual exposure studies recorded different surrogates of traffic particles, with some recording only outdoor concentrations of black or elemental carbon, some recording indoor concentrations of black carbon, and others recording both indoor and outdoor concentrations of black carbon. A joint model for outdoor and indoor exposure that specifies a spatially varying latent variable provides greater spatial coverage in the area of interest. We propose a penalised spline formation of the model that relates to generalised kringing of the latent traffic pollution variable and leads to a natural Bayesian Markov Chain Monte Carlo algorithm for model fitting. We propose methods that allow us to control the degress of freedom of the smoother in a Bayesian framework. Finally, we present results from an analysis that applies the model to data from summer and winter separately

A BAYESIAN SHRINKAGE MODEL FOR INCOMPLETE LONGITUDINAL BINARY DATA WITH APPLICATION TO THE BREAST CANCER PREVENTION TRIAL

We consider inference in randomized studies, in which repeatedly measured outcomes may be informatively missing due to drop out. In this setting, it is well known that full data estimands are not identified unless unverified assumptions are imposed. We assume a non-future dependence model for the drop-out mechanism and posit an exponential tilt model that links non-identifiable and identifiable distributions. This model is indexed by non-identified parameters, which are assumed to have an informative prior distribution, elicited from subject-matter experts. Under this model, full data estimands are shown to be expressed as functionals of the distribution of the observed data. To avoid the curse of dimensionality, we model the distribution of the observed data using a Bayesian shrinkage model. In a simulation study, we compare our approach to a fully parametric and a fully saturated model for the distribution of the observed data. Our methodology is motivated and applied to data from the Breast Cancer Prevention Trial.

A unified approach to modeling multivariate binary data using copulas over partitions

Many seemingly disparate approaches for marginal modeling have been developed in recent years. We demonstrate that many current approaches for marginal modeling of correlated binary outcomes produce likelihoods that are equivalent to the proposed copula-based models herein. These general copula models of underlying latent threshold random variables yield likelihood based models for marginal fixed effects estimation and interpretation in the analysis of correlated binary data. Moreover, we propose a nomenclature and set of model relationships that substantially elucidates the complex area of marginalized models for binary data. A diverse collection of didactic mathematical and numerical examples are given to illustrate concepts.

A Mechanistic Latent Variable Model for Estimating Drug Concentrations in the Male Genital Tract

The purpose of this study is to develop statistical methodology to facilitate indirect estimation of the concentration of antiretroviral drugs and viral loads in the prostate gland and the seminal vesicle. The differences in antiretroviral drug concentrations in these organs may lead to suboptimal concentrations in one gland compared to the other. Suboptimal levels of the antiretroviral drugs will not be able to fully suppress the virus in that gland, lead to a source of sexually transmissible virus and increase the chance of selecting for drug resistant virus. This information may be useful selecting antiretroviral drug regimen that will achieve optimal concentrations in most of male genital tract glands. Using fractionally collected semen ejaculates, Lundquist (1949) measured levels of surrogate markers in each fraction that are uniquely produced by specific male accessory glands. To determine the original glandular concentrations of the surrogate markers, Lundquist solved a simultaneous series of linear equations. This method has several limitations. In particular, it does not yield a unique solution, it does not address measurement error, and it disregards inter-subject variability in the parameters. To cope with these limitations, we developed a mechanistic latent variable model based on the physiology of the male genital tract and surrogate markers. We employ a Bayesian approach and perform a sensitivity analysis with regard to the distributional assumptions on the random effects and priors. The model and Bayesian approach is validated on experimental data where the concentration of a drug should be (biologically) differentially distributed between the two glands. In this example, the Bayesian model-based conclusions are found to be robust to model specification and this hierarchical approach leads to more scientifically valid conclusions than the original methodology. In particular, unlike existing methods, the proposed model based approach was not affected by a common form of outliers.

Wide QRS-complex tachycardia with variable VA-conduction: what is the mechanism?

We describe the case of a 16-year-old woman with a surgically corrected tetralogy of Fallot presenting with recurrent wide-QRS-complex tachycardia. The tachycardia could be induced and terminated with ventricular stimulation only. QRS morphology during sinus rhythm and tachycardia was identical and variable VA-conduction was observed. Mapping of the tachycardia showed that variations of HH intervals preceded VV intervals. Therefore, a mechanism involving re-entry within the bundle branches was suggested. However, detailed mapping showed cranial to caudal depolarization of the His bundle, leading to the diagnosis of atrioventricular node re-entrant tachycardia. The tachycardia was abolished by radiofrequency catheter ablation of the slow AV nodal pathway. We conclude that variable VA conduction can occur in patients with atrioventricular node re-entrant tachycardia. The atrial tissue is not always an integral part of the re-entrant circuit.

Precise pose recovery of distal locking holes from single calibrated fluoroscopic image via a novel variable decomposition approach

This paper presents a novel variable decomposition approach for pose recovery of the distal locking holes using single calibrated fluoroscopic image. The problem is formulated as a model-based optimal fitting process, where the control variables are decomposed into two sets: (a) the angle between the nail axis and its projection on the imaging plane, and (b) the translation and rotation of the geometrical model of the distal locking hole around the nail axis. By using an iterative algorithm to find the optimal values of the latter set of variables for any given value of the former variable, we reduce the multiple-dimensional model-based optimal fitting problem to a one-dimensional search along a finite interval. We report the results of our in vitro experiments, which demonstrate that the accuracy of our approach is adequate for successful distal locking of intramedullary nails.

Recurrent rearrangements of chromosome 1q21.1 and variable pediatric phenotypes

BACKGROUND: Duplications and deletions in the human genome can cause disease or predispose persons to disease. Advances in technologies to detect these changes allow for the routine identification of submicroscopic imbalances in large numbers of patients. METHODS: We tested for the presence of microdeletions and microduplications at a specific region of chromosome 1q21.1 in two groups of patients with unexplained mental retardation, autism, or congenital anomalies and in unaffected persons. RESULTS: We identified 25 persons with a recurrent 1.35-Mb deletion within 1q21.1 from screening 5218 patients. The microdeletions had arisen de novo in eight patients, were inherited from a mildly affected parent in three patients, were inherited from an apparently unaffected parent in six patients, and were of unknown inheritance in eight patients. The deletion was absent in a series of 4737 control persons (P=1.1x10(-7)). We found considerable variability in the level of phenotypic expression of the microdeletion; phenotypes included mild-to-moderate mental retardation, microcephaly, cardiac abnormalities, and cataracts. The reciprocal duplication was enriched in nine children with mental retardation or autism spectrum disorder and other variable features (P=0.02). We identified three deletions and three duplications of the 1q21.1 region in an independent sample of 788 patients with mental retardation and congenital anomalies. CONCLUSIONS: We have identified recurrent molecular lesions that elude syndromic classification and whose disease manifestations must be considered in a broader context of development as opposed to being assigned to a specific disease. Clinical diagnosis in patients with these lesions may be most readily achieved on the basis of genotype rather than phenotype.

Effect of constant and variable domain glycosylation on pharmacokinetics of therapeutic antibodies in mice

Previous studies on the effect of glycosylation on the elimination rate of antibodies have produced conflicting results. Here, we performed pharmacokinetic studies in mice with two preparations of a monoclonal IgG1 antibody enriched for complex type or high mannose type oligosaccharides at the Fc glycosylation site. No significant difference in the serum half-life was found between the two antibody glycoforms, nor was any difference observed in the serum half-lives of different complex type glycoforms. To evaluate the influence of glycosylation within the variable domain, a second monoclonal antibody, glycosylated in both the Fc and Fv domains, was separated into fractions containing different amounts of Fv-associated sialic acid and administered to mice. Again, no significant difference was found in the clearance rates of variants carrying different amounts of Fv-associated sialic acid or lacking Fv-glycosylation. These results suggest that glycosylation has little or no impact on the pharmacokinetic behavior of these two monoclonal antibodies in mice.

Modeling and classifying variable width riparian zones utilizing digital elevation models, flood height data, digital soil data and national wetlands inventory : a new approach for riparian zone delineation

Riparian zones are dynamic, transitional ecosystems between aquatic and terrestrial ecosystems with well defined vegetation and soil characteristics. Development of an all-encompassing definition for riparian ecotones, because of their high variability, is challenging. However, there are two primary factors that all riparian ecotones are dependent on: the watercourse and its associated floodplain. Previous approaches to riparian boundary delineation have utilized fixed width buffers, but this methodology has proven to be inadequate as it only takes the watercourse into consideration and ignores critical geomorphology, associated vegetation and soil characteristics. Our approach offers advantages over other previously used methods by utilizing: the geospatial modeling capabilities of ArcMap GIS; a better sampling technique along the water course that can distinguish the 50-year flood plain, which is the optimal hydrologic descriptor of riparian ecotones; the Soil Survey Database (SSURGO) and National Wetland Inventory (NWI) databases to distinguish contiguous areas beyond the 50-year plain; and land use/cover characteristics associated with the delineated riparian zones. The model utilizes spatial data readily available from Federal and State agencies and geospatial clearinghouses. An accuracy assessment was performed to assess the impact of varying the 50-year flood height, changing the DEM spatial resolution (1, 3, 5 and 10m), and positional inaccuracies with the National Hydrography Dataset (NHD) streams layer on the boundary placement of the delineated variable width riparian ecotones area. The result of this study is a robust and automated GIS based model attached to ESRI ArcMap software to delineate and classify variable-width riparian ecotones.