Daowen Zhang

Anti-Mullerian Hormone and Inhibin B in the Definition of Ovarian Aging and the Menopause Transition

CONTEXT/OBJECTIVE The objective of the study was to determine whether anti-Mullerian hormone (AMH) and inhibin B are viable endocrine biomarkers for framing the menopause transition from initiation to the final menstrual period (FMP). DESIGN We assayed AMH, inhibin B, and FSH in 300 archival follicular phase specimens from 50 women with six consecutive annual visits commencing in 1993 when all women were in the pre- and perimenopausal menopause stages. Subsequently each woman had a documented FMP. The assay results were fitted as individual-woman profiles and then related to time to FMP and age at FMP as outcomes. RESULTS Based on annual values from six time points prior to the FMP, (log)AMH longitudinal profiles declined and were highly associated with a time point 5 yr prior to FMP [including both observed and values below detection (P < 0.0001 and P = 0.0001, respectively)]. Baseline AMH profiles were also associated with age at FMP (P = 0.035). Models of declining (log)inhibin B profiles (including both observed and values below detection) were associated with time to FMP (P < 0.0001 and P = 0.0003, respectively). There was no significant association of (log)inhibin B profiles with age at FMP. CONCLUSIONS AMH, an endocrine marker that reflects the transition of resting primordial follicles to growing follicles, declined to a time point 5 yr prior to the FMP; this may represent a critical biological juncture in the menopause transition. Low and nondetectable levels inhibin B levels also were observed 4-5 yr prior to the FMP but were less predictive of time to FMP or age at FMP.

Semiparametric Stochastic Mixed Models for Longitudinal Data

Abstract We consider inference for a semiparametric stochastic mixed model for longitudinal data. This model uses parametric fixed effects to represent the covariate effects and an arbitrary smooth function to model the time effect and accounts for the within-subject correlation using random effects and a stationary or nonstationary stochastic process. We derive maximum penalized likelihood estimators of the regression coefficients and the nonparametric function. The resulting estimator of the nonparametric function is a smoothing spline. We propose and compare frequentist inference and Bayesian inference on these model components. We use restricted maximum likelihood to estimate the smoothing parameter and the variance components simultaneously. We show that estimation of all model components of interest can proceed by fitting a modified linear mixed model. We illustrate the proposed method by analyzing a hormone dataset and evaluate its performance through simulations.

Randomized COMparison of Platelet Inhibition With Abciximab, TiRofiban and Eptifibatide During Percutaneous Coronary Intervention in Acute Coronary Syndromes The COMPARE Trial

Background—The relative anti-aggregatory effects of currently prescribed platelet glycoprotein IIb/IIIa receptor antagonists during and after percutaneous coronary intervention for acute coronary syndromes have not been established. Methods and Results—We randomized 70 acute coronary syndrome patients undergoing percutaneous coronary intervention to receive abciximab, eptifibatide, or tirofiban at doses used in the Evaluation of Platelet IIb/IIIa Inhibitor for STENTing (EPISTENT), Platelet glycoprotein IIb/IIIa in Unstable angina Receptor Suppression Using Integrilin Therapy (PURSUIT), and Platelet Receptor Inhibition in ischemic Syndrome Management in Patients Limited by Unstable Signs and symptoms (PRISM-PLUS)/Randomized Efficacy Study of Tirofiban for Outcomes and Restenosis (RESTORE) trials, respectively. Platelet aggregation (PA) in response to 20 &mgr;mol/L of adenosine diphosphate was measured with turbidimetric aggregometry in both D-phenylalanyl-l-prolyl-l-arginine chloromethylketone and citrate-anticoagulated blood early (15 and 30 minutes) and late (4, 12, and 18 to 24 hours) after drug initiation. At 15 and 30 minutes, PA was significantly less inhibited by the tirofiban-RESTORE regimen compared with abciximab (P =0.028) and eptifibatide regimens (P =0.0001). The abciximab regimen, however, showed increasingly varied anti-aggregatory effects during continued infusion for ≥4 hours. Citrate exaggerated ex vivo platelet inhibition after eptifibatide and tirofiban, but had the opposite effect on abciximab. Of all regimens evaluated, the eptifibatide regimen inhibited PA most consistently throughout both the early and late periods. Conclusions—Currently recommended drug regimens to inhibit the platelet glycoprotein IIb/IIIa receptor have distinct pharmacodynamic profiles that might affect their relative efficacy in acute coronary syndromes and percutaneous coronary intervention.

Variable Selection for Semiparametric Mixed Models in Longitudinal Studies

We propose a double-penalized likelihood approach for simultaneous model selection and estimation in semiparametric mixed models for longitudinal data. Two types of penalties are jointly imposed on the ordinary log-likelihood: the roughness penalty on the nonparametric baseline function and a nonconcave shrinkage penalty on linear coefficients to achieve model sparsity. Compared to existing estimation equation based approaches, our procedure provides valid inference for data with missing at random, and will be more efficient if the specified model is correct. Another advantage of the new procedure is its easy computation for both regression components and variance parameters. We show that the double-penalized problem can be conveniently reformulated into a linear mixed model framework, so that existing software can be directly used to implement our method. For the purpose of model inference, we derive both frequentist and Bayesian variance estimation for estimated parametric and nonparametric components. Simulation is used to evaluate and compare the performance of our method to the existing ones. We then apply the new method to a real data set from a lactation study.

Automatic model selection for partially linear models

We propose and study a unified procedure for variable selection in partially linear models. A new type of double-penalized least squares is formulated, using the smoothing spline to estimate the nonparametric part and applying a shrinkage penalty on parametric components to achieve model parsimony. Theoretically we show that, with proper choices of the smoothing and regularization parameters, the proposed procedure can be as efficient as the oracle estimator (Fan and Li, 2001). We also study the asymptotic properties of the estimator when the number of parametric effects diverges with the sample size. Frequentist and Bayesian estimates of the covariance and confidence intervals are derived for the estimators. One great advantage of this procedure is its linear mixed model (LMM) representation, which greatly facilitates its implementation by using standard statistical software. Furthermore, the LMM framework enables one to treat the smoothing parameter as a variance component and hence conveniently estimate it together with other regression coefficients. Extensive numerical studies are conducted to demonstrate the effective performance of the proposed procedure.

Power and sample size calculation for log-rank test with a time lag in treatment effect

The log-rank test is the most powerful non-parametric test for detecting a proportional hazards alternative and thus is the most commonly used testing procedure for comparing time-to-event distributions between different treatments in clinical trials. When the log-rank test is used for the primary data analysis, the sample size calculation should also be based on the test to ensure the desired power for the study. In some clinical trials, the treatment effect may not manifest itself right after patients receive the treatment. Therefore, the proportional hazards assumption may not hold. Furthermore, patients may discontinue the study treatment prematurely and thus may have diluted treatment effect after treatment discontinuation. If a patients treatment termination time is independent of his/her time-to-event of interest, the termination time can be treated as a censoring time in the final data analysis. Alternatively, we may keep collecting time-to-event data until study termination from those patients who discontinued the treatment and conduct an intent-to-treat analysis by including them in the original treatment groups. We derive formulas necessary to calculate the asymptotic power of the log-rank test under this non-proportional hazards alternative for the two data analysis strategies. Simulation studies indicate that the formulas provide accurate power for a variety of trial settings. A clinical trial example is used to illustrate the application of the proposed methods.

Flexible modeling of survival data with covariates subject to detection limits via multiple imputation

Models for survival data generally assume that covariates are fully observed. However, in medical studies it is not uncommon for biomarkers to be censored at known detection limits. A computationally-efficient multiple imputation procedure for modeling survival data with covariates subject to detection limits is proposed. This procedure is developed in the context of an accelerated failure time model with a flexible seminonparametric error distribution. The consistency and asymptotic normality of the multiple imputation estimator are established and a consistent variance estimator is provided. An iterative version of the proposed multiple imputation algorithm that approximates the EM algorithm for maximum likelihood is also suggested. Simulation studies demonstrate that the proposed multiple imputation methods work well while alternative methods lead to estimates that are either biased or more variable. The proposed methods are applied to analyze the dataset from a recently-conducted GenIMS study.

Assessing Gene-Environment Interactions for Common and Rare Variants with Binary Traits Using Gene-Trait Similarity Regression

Accounting for gene–environment (G×E) interactions in complex trait association studies can facilitate our understanding of genetic heterogeneity under different environmental exposures, improve the ability to discover susceptible genes that exhibit little marginal effect, provide insight into the biological mechanisms of complex diseases, help to identify high-risk subgroups in the population, and uncover hidden heritability. However, significant G×E interactions can be difficult to find. The sample sizes required for sufficient power to detect association are much larger than those needed for genetic main effects, and interactions are sensitive to misspecification of the main-effects model. These issues are exacerbated when working with binary phenotypes and rare variants, which bear less information on association. In this work, we present a similarity-based regression method for evaluating G×E interactions for rare variants with binary traits. The proposed model aggregates the genetic and G×E information across markers, using genetic similarity, thus increasing the ability to detect G×E signals. The model has a random effects interpretation, which leads to robustness against main-effect misspecifications when evaluating G×E interactions. We construct score tests to examine G×E interactions and a computationally efficient EM algorithm to estimate the nuisance variance components. Using simulations and data applications, we show that the proposed method is a flexible and powerful tool to study the G×E effect in common or rare variant studies with binary traits.

Interpregnancy weight retention patterning in women who breastfed

This study compares weight change in lactating women with an 18-month interpregnancy interval with woman who also breastfed but did not have an immediate subsequent pregnancy. Cases were women who breastfed an index infant for 6 months and subsequently became pregnant within 18 months (cases = 25), and the controls also breastfed an index infant for 6 months but had no ensuing pregnancy (controls = 20) within 18 months. The pattern of postpartum weight retention following the initial pregnancy was not statistically different in cases compared to the controls. However, following their ensuing subsequent pregnancy, cases were 1.3 kg heavier than their average weight after their baseline pregnancy (P = 0.02). The best predictor of this greater weight was their weight change during the interpregnancy interval (P = 0.03). Total weight gain during the gestational period of the subsequent pregnancy was not associated with the greater weight following the subsequent pregnancy. Likewise, estimates of the amount of energy as calories or physical activity levels were not significant predictors of this greater weight following the subsequent pregnancy. These findings suggest that monitoring of postpartum weight, even in breastfeeding women, is essential. These findings indicate that breastfeeding women begin the next postpartum interval weighing more than the amount observed in the initial postpartum period.

A flexible model for the mean and variance functions, with application to medical cost data.

Medical cost data are often skewed to the right and heteroscedastic, having a nonlinear relation with covariates. To tackle these issues, we consider an extension to generalized linear models by assuming nonlinear associations of covariates in the mean function and allowing the variance to be an unknown but smooth function of the mean. We make no further assumption on the distributional form. The unknown functions are described by penalized splines, and the estimation is carried out using nonparametric quasi-likelihood. Simulation studies show the flexibility and advantages of our approach. We apply the model to the annual medical costs of heart failure patients in the clinical data repository at the University of Virginia Hospital System.