Multivariate generalized linear mixed models for continuous bounded outcomes: Analyzing the body fat percentage data.

We propose a multivariate regression model to handle multiple continuous bounded outcomes. We adopted the maximum likelihood approach for parameter estimation and inference. The model is specified by the product of univariate probability distributions and the correlation between the response variables is obtained through the correlation matrix of the random intercepts. For modeling continuous bounded variables on the interval (0,1) we considered the beta and unit gamma distributions. The main advantage of the proposed model is that we can easily combine different marginal distributions for the response variable vector. The computational implementation is performed using Template Model Builder, which combines the Laplace approximation with automatic differentiation. Therefore, the proposed approach allows us to estimate the model parameters quickly and efficiently. We conducted a simulation study to evaluate the computational implementation and the properties of the maximum likelihood estimators under different scenarios. Moreover, we investigate the impact of distribution misspecification in the proposed model. Our model was motivated by a data set with multiple continuous bounded outcomes, which refer to the body fat percentage measured at five regions of the body. Simulation studies and data analysis showed that the proposed model provides a general and rich framework to deal with multiple continuous bounded outcomes.

Familial Risk and Heritability of Hematologic Malignancies in the Nordic Twin Study of Cancer.

We aimed to explore the genetic and environmental contributions to variation in the risk of hematologic malignancies and characterize familial dependence within and across hematologic malignancies. The study base included 316,397 individual twins from the Nordic Twin Study of Cancer with a median of 41 years of follow-up: 88,618 (28%) of the twins were monozygotic, and 3459 hematologic malignancies were reported. We estimated the cumulative incidence by age, familial risk, and genetic and environmental variance components of hematologic malignancies accounting for competing risk of death. The lifetime risk of any hematologic malignancy was 2.5% (95% CI 2.4-2.6%), as in the background population. This risk was elevated to 4.5% (95% CI 3.1-6.5%) conditional on hematologic malignancy in a dizygotic co-twin and was even greater at 7.6% (95% CI 4.8-11.8%) if a monozygotic co-twin had a hematologic malignancy. Heritability of the liability to develop any hematologic malignancy was 24% (95% CI 14-33%). This estimate decreased across age, from approximately 55% at age 40 to about 20-25% after age 55, when it seems to stabilize. In this largest ever studied twin cohort with the longest follow-up, we found evidence for familial risk of hematologic malignancies. The discovery of decreasing familial predisposition with increasing age underscores the importance of cancer surveillance in families with hematological malignancies.

Multivariate quasi-beta regression models for continuous bounded data.

We propose a multivariate regression model to deal with multiple continuous bounded data. The proposed model is based on second-moment assumptions, only. We adopted the quasi-score and Pearson estimating functions for estimation of the regression and dispersion parameters, respectively. Thus, the proposed approach does not require a multivariate probability distribution for the variable response vector. The multivariate quasi-beta regression model can easily handle multiple continuous bounded outcomes taking into account the correlation between the response variables. Furthermore, the model allows us to analyze continuous bounded data on the interval [0, 1], including zeros and/or ones. Simulation studies were conducted to investigate the behavior of the NORmal To Anything (NORTA) algorithm and to check the properties of the estimating function estimators to deal with multiple correlated response variables generated from marginal beta distributions. The model was motivated by a data set concerning the body fat percentage, which was measured at five regions of the body and represent the response variables. We analyze each response variable separately and compare it with the fit of the multivariate proposed model. The multivariate quasi-beta regression model provides better fit than its univariate counterparts, as well as allows us to measure the correlation between response variables. Finally, we adapted diagnostic tools to the proposed model. In the supplementary material, we provide the data set and R code.

Double Poisson-Tweedie Regression Models.

In this paper, we further extend the recently proposed Poisson-Tweedie regression models to include a linear predictor for the dispersion as well as for the expectation of the count response variable. The family of the considered models is specified using only second-moments assumptions, where the variance of the count response has the form µ+ϕµp $\mu + \phi \mu^p$, where µ is the expectation, ϕ and p are the dispersion and power parameters, respectively. Parameter estimations are carried out using an estimating function approach obtained by combining the quasi-score and Pearson estimating functions. The performance of the fitting algorithm is investigated through simulation studies. The results showed that our estimating function approach provides consistent estimators for both mean and dispersion parameters. The class of models is motivated by a data set concerning CD4 counting in HIV-positive pregnant women assisted in a public hospital in Curitiba, Paraná, Brazil. Specifically, we investigate the effects of a set of covariates in both expectation and dispersion structures. Our results showed that women living out of the capital Curitiba, with viral load equal or larger than 1000 copies and with previous diagnostic of HIV infection, present lower levels of CD4 cell count. Furthermore, we detected that the time to initiate the antiretroviral therapy decreases the data dispersion. The data set and R code are available as supplementary materials.

Effect of pegylated phosphatidylserine-containing liposomes in experimental chronic arthritis.

BACKGROUND: Phosphatidylserine-containing liposomes (PSL) have been shown to reduce inflammation in experimental models of acute arthritis, by mimicking the apoptotic process. The aim of this study was to evaluate the effect of pegylated PSL (PEG-PSL) on chronic inflammation of collagen induced arthritis (CIA) in DBA/1J mice. METHODS: CIA was induced in 24 DBA/1J mice (n = 6/group), which were divided into control (0.9 % saline) or treated with PEG-PSL (5, 10 and 15 mg/kg/day, subcutaneously for 20 days). Clinical score, limb histology and measurement of cytokines in knee joints of animals by ELISA and cytometric bead array (CBA) were evaluated. The in vitro study employed macrophage cultures stimulated with 100 ng/ml of LPS plus 10 ng/ml of PMA and treated with 100 µM PEG-PSL. RESULTS: Resolution of the disease in vivo and the inflammatory process in vitro were not observed. PEG-PSL, in doses of 10 and 15 mg/kg, were not shown to reduce the score of the disease in animals, whereas with the dose of 5 mg/kg, the animals did not show the advanced stage of the disease when compared to the controls. The PEG- PSL 5, 10 and 15 mg/kg treatment groups did not show significant reduction of TNF-α, IL-1ß, IL-6, IL-2 and IFN-γ when compared to the controls. Disease incidence and animal weights were not affected by treatment. Regarding the paw histology, PEG-PSL did not yield any reductions in the infiltrating mononuclear, synovial hyperplasia, extension of pannus formation, synovial fibrosis, erosion of cartilage, bone erosion or cartilage degradation. The concentration of 100 µM of PEG-PSL has not been shown to reduce inflammation induced by LPS/PMA in the in vitro study. Treated groups did not show any reduction in inflammatory cytokines in the knee joints of animals affected by the disease compared to the control, although there were higher concentrations of TGF-ß1 in all experimental groups. CONCLUSION: The experimental model showed an expression of severe arthritis after the booster. TGF-ß1 as well other pro inflammatory cytokines were presented in high concentrations in all groups. PEG-PSL had no impact on the clinical score, the histopathology from tibial-tarsal joints or the production of cytokines in the knee joints. Other alternatives such as dosage, route of administration, and as an adjunct to a drug already on the market, should be evaluated to support the use of PEG-PSL as a new therapeutic tool in inflammatory diseases.