To estimate the net (i.e., overall) effect of highly active antiretroviral therapy (HAART) on time to acquired immunodeficiency syndrome (AIDS) or death, the authors used inverse probability-of-treatment weighted estimation of a marginal structural model, which can appropriately adjust for time-varying confounders affected by prior treatment or exposure. Human immunodeficiency virus (HIV)-positive men and women (n = 1,498) were followed in two ongoing cohort studies between 1995 and 2002. Sixty-one percent (n = 918) of the participants initiated HAART during 6,763 person-years of follow-up, and 382 developed AIDS or died. Strong confounding by indication for HAART was apparent; the unadjusted hazard ratio for AIDS or death was 0.98. The hazard ratio from a standard time-dependent Cox model that included time-varying CD4 cell count, HIV RNA level, and other time-varying and fixed covariates as regressors was 0.81 (95% confidence interval: 0.61, 1.07). In contrast, the hazard ratio from a marginal structural survival model was 0.54 (robust 95% confidence interval: 0.38, 0.78), suggesting a clinically meaningful net benefit of HAART. Standard Cox analysis failed to detect a clear net benefit, because it does not appropriately adjust for time-dependent covariates, such as HIV RNA level and CD4 cell count, that are simultaneously confounders and intermediate variables.
"Marginal structural modeling (MSM) can control for time-dependent confounders affected by prior treatment . Under some conditions, the treatment estimate from a MSM can have the same causal interpretation as an estimate from a randomized clinical trial . Only the Tentori et al. study reported detailed data regarding the survival advantage of patients treated with active vitamin D. The unadjusted baseline Cox model and time-varying MSM models demonstrated a 16% and 22%, respectively, reduction of all-cause mortality associated with active vitamin D treatment. "
[Show abstract][Hide abstract] ABSTRACT: Vitamin D insufficiency correlates with mortality risk among patients with chronic kidney disease (CKD). The survival benefits of active vitamin D treatment have been assessed in patients with CKD not requiring dialysis and in patients with end stage renal disease (ESRD) requiring dialysis.
MEDLINE, Embase, the Cochrance Library, and article reference lists were searched for relevant observational trials. The quality of the studies was evaluated using the Newcastle-Ottawa Scale (NOS) checklist. Pooled effects were calculated as hazard ratios (HR) using random-effects models.
Twenty studies (11 prospective cohorts, 6 historical cohorts and 3 retrospective cohorts) were included in the meta-analysis., Participants receiving vitamin D had lower mortality compared to those with no treatment (adjusted case mixed baseline model: HR, 0.74; 95% confidence interval [95%CI], 0.67-0.82; P <0.001; time-dependent Cox model: HR, 0.71; 95%CI, 0.57-0.89; P <0.001). Participants that received calcitriol (HR, 0.63; 95%CI, 0.50-0.79; P <0.001) and paricalcitol (HR, 0.43 95%CI, 0.29-0.63; P <0.001) had a lower cardiovascular mortality. Patients receiving paricalcitol had a survival advantage over those that received calcitriol (HR, 0.95; 95%CI, 0.91-0.99; P <0.001).
Vitamin D treatment was associated with decreased risk of all-cause and cardiovascular mortality in patients with CKD not requiring dialysis and patients with end stage renal disease (ESRD) requiring dialysis. There was a slight difference in survival depending on the type of vitamin D analogue. Well-designed randomized controlled trials are necessary to assess the survival benefits of vitamin D.
"conceptually similar to methodology for addressing differential censoring in the context of propensity score weighting : inverse probability of censoring weights is multiplied by propensity score weights and this composite weight is used in the final analysis ( Cole et al . 2003 , 2010 ; Cain and Cole 2009 ) . It is also similar to the multiplication of survey sampling weights by nonresponse adjustment weights , as is commonly performed in survey analysis ( Groves et al . 2004 ) . EXAMPLE 1 : SIMULATION STUDY We first describe a simple simulation study used to assess the performance of propensity score methods "
[Show abstract][Hide abstract] ABSTRACT: OBJECTIVE: To provide a tutorial for using propensity score methods with complex survey data.
DATA SOURCES: Simulated data and the 2008 Medical Expenditure Panel Survey.
STUDY DESIGN: Using simulation, we compared the following methods for estimating the treatment effect: a naïve estimate (ignoring both survey weights and propensity scores), survey weighting, propensity score methods (nearest neighbor matching, weighting, and subclassification), and propensity score methods in combination with survey weighting. Methods are compared in terms of bias and 95 percent confidence interval coverage. In Example 2, we used these methods to estimate the effect on health care spending of having a generalist versus a specialist as a usual source of care.
PRINCIPAL FINDINGS: In general, combining a propensity score method and survey weighting is necessary to achieve unbiased treatment effect estimates that are generalizable to the original survey target population.
CONCLUSIONS: Propensity score methods are an essential tool for addressing confounding in observational studies. Ignoring survey weights may lead to results that are not generalizable to the survey target population. This paper clarifies the appropriate inferences for different propensity score methods and suggests guidelines for selecting an appropriate propensity score method based on a researcher's goal.
Health Services Research 07/2013; 49(1). DOI:10.1111/1475-6773.12090 · 2.78 Impact Factor
"In our models for || , , 0, , we summarized the dependence on by V and L t , the most recently available values of CD4 cell count (restricted cubic spline with five knots) and HIV-1 RNA (<10,000, 10,000-100,000, ≥100,000 copies/mL) at time t, and months between time t and the most recent laboratory measurement (0, 1-2, 3-4, 5-6, ≥7). Like in previous analyses of observational HIV data (Cole et al., 2003; Hernán et al., 2000; Hernán et al., 2002; Sterne et al., 2005) we assumed that treatment was never stopped once initiated. Therefore, for each individual, the factors in the denominator of the weights W t were set to 1 for times t subsequent to treatment initiation, and estimated from the data for all other times, i.e., times when 0. The conditional probability of treatment initiation was estimated by fitting the pooled logistic regression model logit Prrr 1| 0, 0, , ′ ′ where is a month-specific intercept (restricted cubic splines with four knots), ′ and ′ are the transposes of the column vectors of log hazard ratios for the components of the baseline covariates V and the time-varying covariates L t , respectively. "
[Show abstract][Hide abstract] ABSTRACT: Dynamic treatment regimes are the type of regime most commonly used in clinical practice. For example, physicians may initiate combined antiretroviral therapy the first time an individual's recorded CD4 cell count drops below either 500 cells/mm3 or 350 cells/mm3. This paper describes an approach for using observational data to emulate randomized clinical trials that compare dynamic regimes of the form “initiate treatment within a certain time period of some time-varying covariate first crossing a particular threshold." We applied this method to data from the French Hospital database on HIV (FHDH-ANRS CO4), an observational study of HIV-infected patients, in order to compare dynamic regimes of the form "initiate treatment within m months after the recorded CD4 cell count first drops below x cells/mm3" where x takes values from 200 to 500 in increments of 10 and m takes values 0 or 3. We describe the method in the context of this example and discuss some complications that arise in emulating a randomized experiment using observational data.
The International Journal of Biostatistics 01/2010; 6(2):Article 18. DOI:10.2202/1557-4679.1212 · 0.74 Impact Factor
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.