Search

In this paper, we present a method for conducting global sensitivity analysis of randomized trials in which binary outcomes are scheduled to be collected on participants at prespecified points in time after randomization and these outcomes may be missing in a nonmonotone fashion. We introduce a class of missing data assumptions, indexed by sensitivity parameters, which are anchored around the missing not at random assumption introduced by Robins (Statistics in Medicine, 1997). For each assumption in the class, we establish that the joint distribution of the outcomes is identifiable from the distribution of the observed data. Our estimation procedure uses the plug‐in principle, where the distribution of the observed data is estimated using random forests. We establish n$\sqrt {n}$ asymptotic properties for our estimation procedure. We illustrate our methodology in the context of a randomized trial designed to evaluate a new approach to reducing substance use, assessed by testing urine samples twice weekly, among patients entering outpatient addiction treatment. We evaluate the finite sample properties of our method in a realistic simulation study. Our methods have been implemented in an R package entitled slabm. [ABSTRACT FROM AUTHOR]

We develop a Bayesian nonparametric (BNP) approach to evaluate the causal effect of treatment in a randomized trial where a nonterminal event may be censored by a terminal event, but not vice versa (i.e., semi-competing risks). Based on the idea of principal stratification, we define a novel estimand for the causal effect of treatment on the nonterminal event. We introduce identification assumptions, indexed by a sensitivity parameter, and show how to draw inference using our BNP approach. We conduct simulation studies and illustrate our methodology using data from a brain cancer trial. The R code implementing our model and algorithm is available for download at https://github.com/YanxunXu/BaySemiCompeting. [ABSTRACT FROM AUTHOR]

Randomized trials are often designed to collect outcomes at fixed points in time after randomization. In practice, the number and timing of outcome assessments can vary among participants (i.e. irregular assessment). In fact, the timing of assessments may be associated with the outcome of interest (i.e. informative assessment). For example, in a trial evaluating the effectiveness of treatments for major depressive disorder, not only did the timings of outcome assessments vary among participants but symptom scores were associated with assessment frequency. This type of informative observation requires appropriate statistical analysis. Although analytic methods have been developed, they are rarely used. In this article, we review the literature on irregular assessments with a view toward developing recommendations for analyzing trials with irregular and potentially informative assessment times. We show how the choice of analytic approach hinges on assumptions about the relationship between the assessment and outcome processes. We argue that irregular assessment should be treated with the same care as missing data, and we propose that trialists adopt strategies to minimize the extent of irregularity; describe the extent of irregularity in assessment times; make their assumptions about the relationships between assessment times and outcomes explicit; adopt analytic techniques that are appropriate to their assumptions; and assess the sensitivity of trial results to their assumptions. [ABSTRACT FROM AUTHOR]

Huang proposes a method for assessing the impact of a point treatment on mortality either directly or mediated by occurrence of a nonterminal health event, based on data from a prospective cohort study in which the occurrence of the nonterminal health event may be preemptied by death but not vice versa. The author uses a causal mediation framework to formally define causal quantities known as natural (in)direct effects. The novelty consists of adapting these concepts to a continuous‐time modeling framework based on counting processes. In an effort to posit "scientifically interpretable estimands," statistical and causal assumptions are introduced for identification. In this commentary, we argue that these assumptions are not only difficult to interpret and justify, but are also likely violated in the hepatitis B motivating example and other survival/time to event settings as well. [ABSTRACT FROM AUTHOR]

Time is of the essence in evaluating potential drugs and biologics for the treatment and prevention of COVID‐19. There are currently 876 randomized clinical trials (phase 2 and 3) of treatments for COVID‐19 registered on clinicaltrials.gov. Covariate adjustment is a statistical analysis method with potential to improve precision and reduce the required sample size for a substantial number of these trials. Though covariate adjustment is recommended by the U.S. Food and Drug Administration and the European Medicines Agency, it is underutilized, especially for the types of outcomes (binary, ordinal, and time‐to‐event) that are common in COVID‐19 trials. To demonstrate the potential value added by covariate adjustment in this context, we simulated two‐arm, randomized trials comparing a hypothetical COVID‐19 treatment versus standard of care, where the primary outcome is binary, ordinal, or time‐to‐event. Our simulated distributions are derived from two sources: longitudinal data on over 500 patients hospitalized at Weill Cornell Medicine New York Presbyterian Hospital and a Centers for Disease Control and Prevention preliminary description of 2449 cases. In simulated trials with sample sizes ranging from 100 to 1000 participants, we found substantial precision gains from using covariate adjustment–equivalent to 4–18% reductions in the required sample size to achieve a desired power. This was the case for a variety of estimands (targets of inference). From these simulations, we conclude that covariate adjustment is a low‐risk, high‐reward approach to streamlining COVID‐19 treatment trials. We provide an R package and practical recommendations for implementation. [ABSTRACT FROM AUTHOR]

Rejoinder: Improving precision and power in randomized trials for COVID-19 treatments using covariate adjustment, for binary, ordinal, and time-to-event outcomes An alternative estimator to consider for time-to-event outcomes is the augmented, inverse probability weighted estimator from Díaz I et al i . M. Zhang and B. Zhang describe a general approach for constructing covariate adjusted estimators that applies to many estimands. [Extracted from the article]

Summary: Whereas generic drugs offer a cost‐effective alternative to brand name drugs, regulators need a method to assess therapeutic equivalence in a post‐market setting. We develop such a method in the context of assessing the therapeutic equivalence of immediate release venlafaxine, based on a large insurance claims data set provided by OptumLabs\circledR. To address this question properly, our methodology must deal with issues of non‐adherence, secular trends in health outcomes and lack of treatment overlap due to sharp uptake of the generic drug once it becomes available. We define, identify (under assumptions) and estimate (using G‐computation) a causal effect for a time‐to‐event outcome by extending regression discontinuity to survival curves. We do not find evidence for a lack of therapeutic equivalence of brand and generic immediate release venlafaxine. [ABSTRACT FROM AUTHOR]

Identifiability of statistical models is a fundamental regularity condition that is required for valid statistical inference. Investigation of model identifiability is mathematically challenging for complex models such as latent class models. Jones et al. used Goodman's technique to investigate the identifiability of latent class models with applications to diagnostic tests in the absence of a gold standard test. The tool they used was based on examining the singularity of the Jacobian or the Fisher information matrix, in order to obtain insights into local identifiability (ie, there exists a neighborhood of a parameter such that no other parameter in the neighborhood leads to the same probability distribution as the parameter). In this paper, we investigate a stronger condition: global identifiability (ie, no two parameters in the parameter space give rise to the same probability distribution), by introducing a powerful mathematical tool from computational algebra: the Gröbner basis. With several existing well‐known examples, we argue that the Gröbner basis method is easy to implement and powerful to study global identifiability of latent class models, and is an attractive alternative to the information matrix analysis by Rothenberg and the Jacobian analysis by Goodman and Jones et al. [ABSTRACT FROM AUTHOR]

Summary: In practice, both testable and untestable assumptions are generally required to draw inference about the mean outcome measured at the final scheduled visit in a repeated measures study with drop‐out. Scharfstein et al. (2014) proposed a sensitivity analysis methodology to determine the robustness of conclusions within a class of untestable assumptions. In their approach, the untestable and testable assumptions were guaranteed to be compatible; their testable assumptions were based on a fully parametric model for the distribution of the observable data. While convenient, these parametric assumptions have proven especially restrictive in empirical research. Here, we relax their distributional assumptions and provide a more flexible, semi‐parametric approach. We illustrate our proposal in the context of a randomized trial for evaluating a treatment of schizoaffective disorder. [ABSTRACT FROM AUTHOR]

In randomized studies involving severely ill patients, functional outcomes are often unobserved due to missed clinic visits, premature withdrawal, or death. It is well known that if these unobserved functional outcomes are not handled properly, biased treatment comparisons can be produced. In this article, we propose a procedure for comparing treatments that is based on a composite endpoint that combines information on both the functional outcome and survival. We further propose a missing data imputation scheme and sensitivity analysis strategy to handle the unobserved functional outcomes not due to death. Illustrations of the proposed method are given by analyzing data from a recent non-small cell lung cancer clinical trial and a recent trial of sedation interruption among mechanically ventilated patients. [ABSTRACT FROM AUTHOR]

We address estimation of intervention effects in experimental designs in which (a) interventions are assigned at the cluster level; (b) clusters are selected to form pairs, matched on observed characteristics; and (c) intervention is assigned to one cluster at random within each pair. One goal of policy interest is to estimate the average outcome if all clusters in all pairs are assigned control versus if all clusters in all pairs are assigned to intervention. In such designs, inference that ignores individual level covariates can be imprecise because cluster-level assignment can leave substantial imbalance in the covariate distribution between experimental arms within each pair. However, most existing methods that adjust for covariates have estimands that are not of policy interest. We propose a methodology that explicitly balances the observed covariates among clusters in a pair, and retains the original estimand of interest. We demonstrate our approach through the evaluation of the Guided Care program. [ABSTRACT FROM AUTHOR]

Summary. We develop and implement a methodology for drawing inference about subgroup effects in a two-arm randomized trial when subgroup status is known only for a non-random sample in each of the trial arms. Since the subgroup effects are not point identified from the distribution of the observed data, we show how to compute bounds on these effects by using scientifically plausible assumptions. We characterize the uncertainty of our procedure by using the Bayesian paradigm. The methodology is developed in the context of the second Multicenter Automatic Defibrillator Intervention Trial, which was a randomized trial designed to evaluate the effectiveness of implantable defibrillators on survival. [ABSTRACT FROM AUTHOR]

Summary. Acute lung injury is a condition that is characterized by acute onset of severe hypoxaemia and bilateral pulmonary infiltrates. Patients typically require mechanical ventilation in an intensive care unit. Low tidal volume ventilation (LTVV), which is a time varying dynamic treatment regime, has been recommended as an effective ventilation strategy. This recommendation was based on the results of a randomized clinical trial designed to compare low versus high tidal volume strategies by the Acute Respiratory Distress Syndrome Network. After publication of the trial, some critics focused on the high non-adherence rates in the LTVV arm suggesting that non-adherence occurred because treating physicians felt that deviating from the prescribed regime would improve patients' outcomes. We seek to address this controversy by estimating the survival distribution in the counterfactual setting where all patients assigned to LTVV followed the regime. Inference is based on a fully Bayesian implementation of Robins's G-computation formula. In addition to reanalysing data from the original trial, we also apply our methodology to data from a subsequent trial, which implemented the LTVV regime in both of its study arms and also suffered from non-adherence. [ABSTRACT FROM AUTHOR]

Background. The optimal blood pressure level to minimize the risk of ischemic stroke (IS) in older adults is undetermined. Cerebral white matter lesions (WML), prevalent in older adults, may be a marker for vulnerability to IS. We aimed at determining the relationship between diastolic blood pressure (DBP) levels and IS in the presence of WML. Methods. The Cardiovascular Health Study population (N = 3,345, age ≥ 65 years, N = 3,345) was followed between 1989 and 2002 for IS incidence. Survival analysis included quintiles of DBP analyzed within WML levels controlling for age and cardiovascular disease. Results. DBP had no effect on IS incidence in low WML levels but had a marginally significant J-curve relationship with IS in high WML levels: the adjusted hazard ratio for IS in the lowest (<63 mmHg) and highest (≥80) DBP quintiles compared with the third (nadir, 69–73 mmHg) was 1.64 (95% confidence interval: 0.93–2.9) and 1.83 (95% confidence interval: 1.06–3.15), respectively. Conclusions. In older adults with low-grade WML, low DBP may not pose a risk for IS. However, in high-grade WML, IS risk may increase in DBP less than 69 mmHg but is highest more than 80 mmHg. People with high-grade WML may be at risk of IS in high and low DBP. [ABSTRACT FROM PUBLISHER]

Purpose: Guided Care (GC) is a model of health care for multimorbid older adults that is provided by a registered nurse who works with the patients’ primary care physician (PCP). The purpose of this study was to determine whether GC improves patients’ primary caregivers’ depressive symptoms, strain, productivity, and perceptions of the quality of care recipients’ chronic illness care. Design and Methods: A cluster-randomized controlled trial of GC was conducted within 14 PCP teams. The study sample included 196 primary caregivers who completed baseline and 18-month surveys and whose care recipients remained alive and enrolled in the GC study for 18 months. Caregiver outcomes included the following: depressive symptoms (Center for Epidemiological Studies-Depression scale), strain (Modified Caregiver Strain Index), the quality of care recipients’ chronic illness care [Patient Assessment of Chronic Illness Care (PACIC)], and personal productivity (Work Productivity and Activity Impairment questionnaire, adapted for caregiving). Results: In multivariate regression models, between-group differences in depression, strain, work productivity, and regular activity productivity were not statistically significant after 18 months, but GC caregivers reported the overall quality of their recipients’ chronic illness care to be significantly higher (adjusted beta = 0.40, 95% confidence interval : 0.14–0.67). Quality was significantly higher in 4 of 5 PACIC subscales, reflecting the dimensions of goal setting, coordination of care, decision support, and patient activation. Implications: GC improved the quality of chronic illness care received by multimorbid care recipients but did not improve caregivers’ depressive symptoms, affect, or productivity. [ABSTRACT FROM PUBLISHER]

We consider estimation of the causal effect of a treatment on an outcome from observational data collected in two phases. In the first phase, a simple random sample of individuals is drawn from a population. On these individuals, information is obtained on treatment, outcome and a few low dimensional covariates. These individuals are then stratified according to these factors. In the second phase, a random subsample of individuals is drawn from each stratum, with known stratum-specific selection probabilities. On these individuals, a rich set of covariates is collected. In this setting, we introduce five estimators: simple inverse weighted; simple doubly robust; enriched inverse weighted; enriched doubly robust; locally efficient. We evaluate the finite sample performance of these estimators in a simulation study. We also use our methodology to estimate the causal effect of trauma care on in-hospital mortality by using data from the National Study of Cost and Outcomes of Trauma. [ABSTRACT FROM AUTHOR]

Background. The Guided Care Program for Families and Friends (GCPFF) is one component of "Guided Care" (GC), a model of primary care for chronically ill older adults that is facilitated by a registered nurse who has completed a supplemental educational curriculum. Methods. The GCPFF melds support for family caregivers with the delivery of coordinated and comprehensive chronic care and seeks to improve the health and well-being of both patients and their family caregivers. The GCPFF encompasses (a) an initial meeting between the nurse and the patient's primary caregiver, (b) education and referral to community resources, (c) ongoing "coaching," (d) a six-session group Caregiver Workshop, and (e) monthly Support Group meetings, all facilitated by the patient's GC nurse. Results. A cluster-randomized controlled trial of GC is underway in 14 primary care physician teams. Of 904 consented patients, 450 (49.8%) identified a primary caregiver; 308 caregivers met eligibility criteria, consented to participate, and completed a baseline interview. At 6-month follow-up, intervention group caregivers' mean Center for Epiderniological Studies Depression (CESD) and Caregiver Strain Index (CSl) scores were respectively 0.97 points (p = .14) and 1.14 points (p = .06) lower than control group caregivers'. Among caregivers who provided more than 14 hours of weekly assistance at baseline, intervention group caregivers' mean CESD and CSI scores were respectively 1.23 points (p = .20) and 1.83 points (p = .04) lower than control group caregivers'. Conclusions. The GCPFF may benefit family caregivers of chronically ill older adults. Outcomes will continue to be monitored at 18-months follow-up. [ABSTRACT FROM AUTHOR]

We focus on estimation of the causal effect of treatment on the functional status of individuals at a fixed point in time t* after they have experienced a catastrophic event, from observational data with the following features: (i) treatment is imposed shortly after the event and is nonrandomized, (ii) individuals who survive to t* are scheduled to be interviewed, (iii) there is interview nonresponse, (iv) individuals who die prior to t* are missing information on preevent confounders, and (v) medical records are abstracted on all individuals to obtain information on postevent, pretreatment confounding factors. To address the issue of survivor bias, we seek to estimate the survivor average causal effect (SACE), the effect of treatment on functional status among the cohort of individuals who would survive to t* regardless of whether or not assigned to treatment. To estimate this effect from observational data, we need to impose untestable assumptions, which depend on the collection of all confounding factors. Because preevent information is missing on those who die prior to t*, it is unlikely that these data are missing at random. We introduce a sensitivity analysis methodology to evaluate the robustness of SACE inferences to deviations from the missing at random assumption. We apply our methodology to the evaluation of the effect of trauma center care on vitality outcomes using data from the National Study on Costs and Outcomes of Trauma Care. [ABSTRACT FROM AUTHOR]

Background. The quality of health care for older Americans with multiple chronic conditions is suboptimal. We designed "Guided Care" (GC) to enhance quality of care by integrating a registered nurse, intensively trained in chronic care, into primary care practices to work with physicians in providing comprehensive chronic care to 50-60 multimorbid older patients. Methods. We hypothesized that GC would improve the quality of health care for this population. In 2006, we began a cluster-randomized controlled trial of GC at eight practices (n = 49 physicians). Older patients of these practices were eligible to participate if they were at risk for using health services heavily during the coming year. Teams of two to five physicians and their at-risk older patients were randomized to either GC or usual care (UC). Six months after baseline, participants rated the quality of their health care by answering validated closed-ended questions from telephone interviewers who were masked to group assignment. Results. Of the 13,534 older patients screened, 2391 (17.7%) were eligible to participate in the study, of which 904 (37.8%) gave informed consent and were cluster-randomized. After 6 months, 93.8% and 93.2% of the GC and UC participants who remained alive and eligible completed telephone interviews. GC participants were more likely than UC participants to rate their care highly (adjusted odds ratio = 2.0, 95% confidence interval, 1.2-3.4, p = .006), and primary care physicians were more likely to be satisfied with their interactions with chronically ill older patients and their families (p < .05). Conclusions. GC improves important aspects of the quality of health care for multimorbid older persons. Additional data will become available as this trial continues. [ABSTRACT FROM AUTHOR]

Logically defined outcomes are commonly used in medical diagnoses and epidemiological research. When missing values in the original outcomes exist, the method of handling the missingness can have unintended consequences, even if the original outcomes are missing completely at random. In this note, we consider 2 binary original outcomes, which are missing completely at random. For estimating the prevalence of a logically defined "or" outcome, we discuss the properties of 4 estimators: the complete-case estimator, the available-case estimator, the maximum likelihood estimator (MLE), and a moment-based estimator. With the exception of the available-case case estimator, all the estimators are consistent. The MLE exhibits superior performance and should be generally adopted. [ABSTRACT FROM AUTHOR]

We derive estimators of the survival curve of a failure time in the presence of competing right censoring mechanisms. Our approach allows for the possibility that some or all of the competing censoring mechanisms are associated with the end point, even after adjustment for recorded prognostic factors. It also allows the degree of residual association to be possibly different for distinct censoring processes. Our methods generalize from one to several competing censoring mechanisms the methods of Scharfstein and Robins. [ABSTRACT FROM AUTHOR]

A frequent problem in longitudinal studies is that subjects may miss scheduled visits or be assessed at self-selected points in time. As a result, observed outcome data may be highly unbalanced and the availability of the data may be directly related to the outcome measure and/or some auxiliary factors that are associated with the outcome. If the follow-up visit and outcome processes are correlated, then marginal regression analyses will produce biased estimates. Building on the work of Robins, Rotnitzky and Zhao, we propose a class of inverse intensity-of-visit process-weighted estimators in marginal regression models for longitudinal responses that may be observed in continuous time. This allows us to handle arbitrary patterns of missing data as embedded in a subject's visit process. We derive the large sample distribution for our inverse visit-intensity-weighted estimators and investigate their finite sample behaviour by simulation. Our approach is illustrated with a data set from a health services research study in which homeless people with mental illness were randomized to three different treatments and measures of homelessness (as percentage days homeless in the past 3 months) and other auxiliary factors were recorded at follow-up times that are not fixed by design. [ABSTRACT FROM AUTHOR]

This article is concerned with drawing inference about aspects of the population distribution of ordinal outcome data measured on a cohort of individuals on two occasions, where some subjects are missing their second measurement. We present two complementary approaches for constructing bounds under assumptions on the missing data mechanism considered plausible by scientific experts. We develop our methodology within the context of a randomized trial of the “Good Behavior Game,” an intervention designed to reduce aggressive misbehavior among children. [ABSTRACT FROM AUTHOR]

Rotnitzky, Robins, and Scharfstein (1998, Journal of the American Statistical Association 93, 1321-1339) developed a methodology for conducting sensitivity analysis of studies in which longitudinal outcome data are subject to potentially nonignorable missingness. In their approach,they specify a class of fully parametric selection models, indexed by a non- or weakly identified selection bias function that indicates the degree to which missingness depends on potentially unobservable outcomes. Estimation of the parameters of interest proceeds by varying the selection bias function over a range considered plausible by subject-matter experts. In this article, we focus on cross-sectional, univariate outcome data and extend their approach to a class of semiparametric selection models,using generalized additive restrictions. We propose a backfitting algorithm to estimate the parameters of the generalized additive selection model. For estimation of the mean outcome, we propose three types f estimating functions: simple inverse weighted, doubly robust, and orthogonal. We present the results of a data analysis and a simulation study. [ABSTRACT FROM AUTHOR]

We present a method for estimating the survival curve of a continuous failure time random variable from right‐censored data. Our method allows adjustment for informative censoring due to measured prognostic factors for time‐to‐event and censoring while simultaneously quantifying the sensitivity of the inference to residual dependence between failure and censoring due to unmeasured factors. We present the results of a simulation study and illustrate our approach using data from the AIDS Clinical Trial Group 175 study. [ABSTRACT FROM PUBLISHER]

The purpose of this study was to compare the number and types of extremity injuries treated at civilian trauma centers (CIV CENs) versus military treatment facilities (MTFs) participating in the Major Extremity Trauma Research Consortium (METRC) and to investigate the potential benefits of a clinical research network that includes both civilian trauma centers and MTFs. Two analyses were performed. First, registry data collected on all surgically treated fractures at four core MTFs and 21 CIV CENs over one year were compared. Second, actual numbers and distribution of patients by type of injury enrolled in three METRC studies were compared. While MTFs demonstrated higher percentages of severe injuries including open fractures, traumatic amputations, vascular injuries, contamination, and injuries with bone, muscle, and skin loss when compared to CIV CENS, the CIV CENs treated a substantially higher number and, more importantly, enrolled patients in almost all categories. Comparison of service members to civilians was challenged by several differences between the two patient populations including mechanism of injury, the medical care environment, and confounding factors such as age, social setting and co-morbidities. Despite these limitations, in times without active military conflict, clinical trials will likely rely on civilian trauma centers for patient enrollment; only when numbers are pooled across a large number of centers can requisite sample sizes be met. These data demonstrate the benefits of maintaining a military-civilian partnership to address the major gaps in research defined by the Military. [ABSTRACT FROM AUTHOR]