Browsing by Author "He, Zangdong"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Simultaneous variable selection for joint models of longitudinal and survival outcomes
    (Wiley Blackwell (Blackwell Publishing), 2015-03) He, Zangdong; Tu, Wanzhu; Wang, Sijian; Fu, Haoda; Yu, Zhangsheng; Department of Biostatistics, Richard M. Fairbanks School of Public Health
    Joint models of longitudinal and survival outcomes have been used with increasing frequency in clinical investigations. Correct specification of fixed and random effects is essential for practical data analysis. Simultaneous selection of variables in both longitudinal and survival components functions as a necessary safeguard against model misspecification. However, variable selection in such models has not been studied. No existing computational tools, to the best of our knowledge, have been made available to practitioners. In this article, we describe a penalized likelihood method with adaptive least absolute shrinkage and selection operator (ALASSO) penalty functions for simultaneous selection of fixed and random effects in joint models. To perform selection in variance components of random effects, we reparameterize the variance components using a Cholesky decomposition; in doing so, a penalty function of group shrinkage is introduced. To reduce the estimation bias resulted from penalization, we propose a two-stage selection procedure in which the magnitude of the bias is ameliorated in the second stage. The penalized likelihood is approximated by Gaussian quadrature and optimized by an EM algorithm. Simulation study showed excellent selection results in the first stage and small estimation biases in the second stage. To illustrate, we analyzed a longitudinally observed clinical marker and patient survival in a cohort of patients with heart failure.
  • Thumbnail Image
    Item
    Triamterene Enhances the Blood Pressure Lowering Effect of Hydrochlorothiazide in Patients with Hypertension
    (Springer, 2016-01) Tu, Wanzhu; Decker, Brian S.; He, Zangdong; Erdel, Blake L.; Eckert, George J.; Hellman, Richard N.; Murray, Michael D.; Oates, John A.; Pratt, J. Howard; Department of Biostatistics, Richard M. Fairbanks School of Public Health
    BACKGROUND: Triamterene, because of its potassium-sparing properties, is frequently used in combination with hydrochlorothiazide (HCTZ) to treat patients with hypertension. By inhibiting the epithelial sodium channel (ENaC) in the cortical collecting duct, triamterene reduces potassium secretion, thus reducing the risk of hypokalemia. Whether triamterene has an independent effect on blood pressure (BP) has not been well studied. OBJECTIVE: To determine if triamterene provides an effect to further lower BP in patients treated with HCTZ. DESIGN: We conducted an observational study using electronic medical record data from the Indiana Network for Patient Care. Participants were 17,291 patients with the diagnosis of hypertension between 2004 and 2012. MAIN MEASURES: BP was the primary outcome. We compared the BP between patients who were taking HCTZ, with and without triamterene, either alone or in combination with other antihypertensive medications, by using a propensity score analysis. For each medication combination, we estimated the propensity score (i.e., probability) of a patient receiving triamterene using a logistic regression model. Patients with similar propensity scores were stratified into subclasses and BP was compared between those taking triamterene or not within each subclass; the effect of triamterene was then assessed by combining BP differences estimated from all subclasses. KEY RESULTS: The mean systolic BP in the triamterene + HCTZ group was 3.8 mmHg lower than in the HCTZ only group (p < 0.0001); systolic BP was similarly lower for patients taking triamterene with other medication combinations. Systolic BP reduction was consistently observed for different medication combinations. The range of systolic BP reduction was between 1 and 4 mm Hg, depending on the concurrently used medications. CONCLUSIONS: In the present study, triamterene was found to enhance the effect of HCTZ to lower BP. In addition to its potassium-sparing action, triamterene's ability to lower BP should also be considered.
  • Thumbnail Image
    Item
    Variable selection and structural discovery in joint models of longitudinal and survival data
    (2014) He, Zangdong; Tu, Wanzhu; Yu, Zhangsheng; Liu, Hai; Song, Yiqing
    Joint models of longitudinal and survival outcomes have been used with increasing frequency in clinical investigations. Correct specification of fixed and random effects, as well as their functional forms is essential for practical data analysis. However, no existing methods have been developed to meet this need in a joint model setting. In this dissertation, I describe a penalized likelihood-based method with adaptive least absolute shrinkage and selection operator (ALASSO) penalty functions for model selection. By reparameterizing variance components through a Cholesky decomposition, I introduce a penalty function of group shrinkage; the penalized likelihood is approximated by Gaussian quadrature and optimized by an EM algorithm. The functional forms of the independent effects are determined through a procedure for structural discovery. Specifically, I first construct the model by penalized cubic B-spline and then decompose the B-spline to linear and nonlinear elements by spectral decomposition. The decomposition represents the model in a mixed-effects model format, and I then use the mixed-effects variable selection method to perform structural discovery. Simulation studies show excellent performance. A clinical application is described to illustrate the use of the proposed methods, and the analytical results demonstrate the usefulness of the methods.