The implementation of a translational study involving a primary care based behavioral program to improve blood pressure control: The HTN-IMPROVE study protocol (01295).

BACKGROUND: Despite the impact of hypertension and widely accepted target values for blood pressure (BP), interventions to improve BP control have had limited success. OBJECTIVES: We describe the design of a 'translational' study that examines the implementation, impact, sustainability, and cost of an evidence-based nurse-delivered tailored behavioral self-management intervention to improve BP control as it moves from a research context to healthcare delivery. The study addresses four specific aims: assess the implementation of an evidence-based behavioral self-management intervention to improve BP levels; evaluate the clinical impact of the intervention as it is implemented; assess organizational factors associated with the sustainability of the intervention; and assess the cost of implementing and sustaining the intervention. METHODS: The project involves three geographically diverse VA intervention facilities and nine control sites. We first conduct an evaluation of barriers and facilitators for implementing the intervention at intervention sites. We examine the impact of the intervention by comparing 12-month pre/post changes in BP control between patients in intervention sites versus patients in the matched control sites. Next, we examine the sustainability of the intervention and organizational factors facilitating or hindering the sustained implementation. Finally, we examine the costs of intervention implementation. Key outcomes are acceptability and costs of the program, as well as changes in BP. Outcomes will be assessed using mixed methods (e.g., qualitative analyses--pattern matching; quantitative methods--linear mixed models). DISCUSSION: The study results will provide information about the challenges and costs to implement and sustain the intervention, and what clinical impact can be expected.

Genome-wide association study of Lp-PLA(2) activity and mass in the Framingham Heart Study.

Lipoprotein-associated phospholipase A(2) (Lp-PLA(2)) is an emerging risk factor and therapeutic target for cardiovascular disease. The activity and mass of this enzyme are heritable traits, but major genetic determinants have not been explored in a systematic, genome-wide fashion. We carried out a genome-wide association study of Lp-PLA(2) activity and mass in 6,668 Caucasian subjects from the population-based Framingham Heart Study. Clinical data and genotypes from the Affymetrix 550K SNP array were obtained from the open-access Framingham SHARe project. Each polymorphism that passed quality control was tested for associations with Lp-PLA(2) activity and mass using linear mixed models implemented in the R statistical package, accounting for familial correlations, and controlling for age, sex, smoking, lipid-lowering-medication use, and cohort. For Lp-PLA(2) activity, polymorphisms at four independent loci reached genome-wide significance, including the APOE/APOC1 region on chromosome 19 (p = 6 x 10(-24)); CELSR2/PSRC1 on chromosome 1 (p = 3 x 10(-15)); SCARB1 on chromosome 12 (p = 1x10(-8)) and ZNF259/BUD13 in the APOA5/APOA1 gene region on chromosome 11 (p = 4 x 10(-8)). All of these remained significant after accounting for associations with LDL cholesterol, HDL cholesterol, or triglycerides. For Lp-PLA(2) mass, 12 SNPs achieved genome-wide significance, all clustering in a region on chromosome 6p12.3 near the PLA2G7 gene. Our analyses demonstrate that genetic polymorphisms may contribute to inter-individual variation in Lp-PLA(2) activity and mass.

Missing data in randomized clinical trials for weight loss: scope of the problem, state of the field, and performance of statistical methods.

BACKGROUND: Dropouts and missing data are nearly-ubiquitous in obesity randomized controlled trails, threatening validity and generalizability of conclusions. Herein, we meta-analytically evaluate the extent of missing data, the frequency with which various analytic methods are employed to accommodate dropouts, and the performance of multiple statistical methods. METHODOLOGY/PRINCIPAL FINDINGS: We searched PubMed and Cochrane databases (2000-2006) for articles published in English and manually searched bibliographic references. Articles of pharmaceutical randomized controlled trials with weight loss or weight gain prevention as major endpoints were included. Two authors independently reviewed each publication for inclusion. 121 articles met the inclusion criteria. Two authors independently extracted treatment, sample size, drop-out rates, study duration, and statistical method used to handle missing data from all articles and resolved disagreements by consensus. In the meta-analysis, drop-out rates were substantial with the survival (non-dropout) rates being approximated by an exponential decay curve (e(-lambdat)) where lambda was estimated to be .0088 (95% bootstrap confidence interval: .0076 to .0100) and t represents time in weeks. The estimated drop-out rate at 1 year was 37%. Most studies used last observation carried forward as the primary analytic method to handle missing data. We also obtained 12 raw obesity randomized controlled trial datasets for empirical analyses. Analyses of raw randomized controlled trial data suggested that both mixed models and multiple imputation performed well, but that multiple imputation may be more robust when missing data are extensive. CONCLUSION/SIGNIFICANCE: Our analysis offers an equation for predictions of dropout rates useful for future study planning. Our raw data analyses suggests that multiple imputation is better than other methods for handling missing data in obesity randomized controlled trials, followed closely by mixed models. We suggest these methods supplant last observation carried forward as the primary method of analysis.

A randomized clinical trial of a coping improvement group intervention for HIV-infected older adults.

This research tested if a 12-session coping improvement group intervention (n = 104) reduced depressive symptoms in HIV-infected older adults compared to an interpersonal support group intervention (n = 105) and an individual therapy upon request (ITUR) control condition (n = 86). Participants were 295 HIV-infected men and women 50-plus years of age living in New York City, Cincinnati, OH, and Columbus, OH. Using A-CASI assessment methodology, participants provided data on their depressive symptoms using the Geriatric Depression Screening Scale (GDS) at pre-intervention, post-intervention, and 4- and 8-month follow-up. Whether conducted with all participants (N = 295) or only a subset of participants diagnosed with mild, moderate, or severe depressive symptoms (N = 171), mixed models analyses of repeated measures found that both coping improvement and interpersonal support group intervention participants reported fewer depressive symptoms than ITUR controls at post-intervention, 4-month follow-up, and 8-month follow-up. The effect sizes of the differences between the two active interventions and the control group were greater when outcome analyses were limited to those participants with mild, moderate, or severe depressive symptoms. At no assessment period did coping improvement and interpersonal support group intervention participants differ in depressive symptoms.

Bayesian Gaussian Copula Factor Models for Mixed Data.

Gaussian factor models have proven widely useful for parsimoniously characterizing dependence in multivariate data. There is a rich literature on their extension to mixed categorical and continuous variables, using latent Gaussian variables or through generalized latent trait models acommodating measurements in the exponential family. However, when generalizing to non-Gaussian measured variables the latent variables typically influence both the dependence structure and the form of the marginal distributions, complicating interpretation and introducing artifacts. To address this problem we propose a novel class of Bayesian Gaussian copula factor models which decouple the latent factors from the marginal distributions. A semiparametric specification for the marginals based on the extended rank likelihood yields straightforward implementation and substantial computational gains. We provide new theoretical and empirical justifications for using this likelihood in Bayesian inference. We propose new default priors for the factor loadings and develop efficient parameter-expanded Gibbs sampling for posterior computation. The methods are evaluated through simulations and applied to a dataset in political science. The models in this paper are implemented in the R package bfa.

Conductance of quantum impurity models from quantum monte carlo

The conductance of two Anderson impurity models, one with twofold and another with fourfold degeneracy, representing two types of quantum dots, is calculated using a world-line quantum Monte Carlo (QMC) method. Extrapolation of the imaginary time QMC data to zero frequency yields the linear conductance, which is then compared to numerical renormalization-group results in order to assess its accuracy. We find that the method gives excellent results at low temperature (T TK) throughout the mixed-valence and Kondo regimes but it is unreliable for higher temperature. © 2010 The American Physical Society.

Lognormal and gamma mixed negative binomial regression

In regression analysis of counts, a lack of simple and efficient algorithms for posterior computation has made Bayesian approaches appear unattractive and thus underdeveloped. We propose a lognormal and gamma mixed negative binomial (NB) regression model for counts, and present efficient closed-form Bayesian inference; unlike conventional Poisson models, the proposed approach has two free parameters to include two different kinds of random effects, and allows the incorporation of prior information, such as sparsity in the regression coefficients. By placing a gamma distribution prior on the NB dispersion parameter r, and connecting a log-normal distribution prior with the logit of the NB probability parameter p, efficient Gibbs sampling and variational Bayes inference are both developed. The closed-form updates are obtained by exploiting conditional conjugacy via both a compound Poisson representation and a Polya-Gamma distribution based data augmentation approach. The proposed Bayesian inference can be implemented routinely, while being easily generalizable to more complex settings involving multivariate dependence structures. The algorithms are illustrated using real examples. Copyright 2012 by the author(s)/owner(s).