We describe semiparametric estimation and inference for causal effects using observational data from a single social network. Our asymptotic results are the first to allow for dependence of each observation on a growing number of other units as sample size increases. In addition, while previous methods have implicitly permitted only one of two possible sources of dependence among social network observations, we allow for both dependence due to transmission of information across network ties and for dependence due to latent similarities among nodes sharing ties. We propose new causal effects that are specifically of interest in social network settings, such as interventions on network ties and network structure. We use our methods to reanalyze an influential and controversial study that estimated causal peer effects of obesity using social network data from the Framingham Heart Study; after accounting for network structure we find no evidence for causal peer effects.
Background: Despite potential harm that can result from polypharmacy, real-world data on polypharmacy in the setting of heart failure (HF) are limited. We sought to address this knowledge gap by studying older adults hospitalized for HF derived from the REGARDS study (Reasons for Geographic and Racial Differences in Stroke). Methods: We examined 558 older adults aged ≥65 years with adjudicated HF hospitalizations from 380 hospitals across the United States. We collected and examined data from the REGARDS baseline assessment, medical charts from HF-adjudicated hospitalizations, the American Hospital Association annual survey database, and Medicare’s Hospital Compare website. We counted the number of medications taken at hospital admission and discharge; and classified each medication as HF-related, non-HF cardiovascular-related, or noncardiovascular-related. Results: The vast majority of participants (84% at admission and 95% at discharge) took ≥5 medications; and 42% at admission and 55% at discharge took ≥10 medications. The prevalence of taking ≥10 medications (polypharmacy) increased over the study period. As the number of total medications increased, the number of noncardiovascular medications increased more rapidly than the number of HF-related or non-HF cardiovascular medications. Conclusions: Defining polypharmacy as taking ≥10 medications might be more ideal in the HF population as most patients already take ≥5 medications. Polypharmacy is common both at admission and hospital discharge, and its prevalence is rising over time. The majority of medications taken by older adults with HF are noncardiovascular medications. There is a need to develop strategies that can mitigate the negative effects of polypharmacy among older adults with HF.
1 September 2021 in Journal of the American Statistical Association
Most causal inference methods consider counterfactual variables under interventions that set the exposure to a fixed value. With continuous or multi-valued treatments or exposures, such counterfactuals may be of little practical interest because no feasible intervention can be implemented that would bring them about. Longitudinal modified treatment policies (LMTPs) are a recently developed nonparametric alternative that yield effects of immediate practical relevance with an interpretation in terms of meaningful interventions such as reducing or increasing the exposure by a given amount. LMTPs also have the advantage that they can be designed to satisfy the positivity assumption required for causal inference. We present a novel sequential regression formula that identifies the LMTP causal effect, study properties of the LMTP statistical estimand such as the efficient influence function and the efficiency bound, and propose four different estimators. Two of our estimators are efficient, and one is sequentially doubly robust in the sense that it is consistent if, for each time point, either an outcome regression or a treatment mechanism is consistently estimated. We perform numerical studies of the estimators, and present the results of our motivating study on hypoxemia and mortality in intubated Intensive Care Unit (ICU) patients. Software implementing our methods is provided in the form of the open source R package lmtp freely available on GitHub (https://github.com/nt-williams/lmtp) and CRAN.
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.
22 September 2023 in Journal of Clinical and Translational Science
Increasing emphasis on the use of real-world evidence (RWE) to support clinical policy and regulatory decision-making has led to a proliferation of guidance, advice, and frameworks from regulatory agencies, academia, professional societies, and industry. A broad spectrum of studies use real-world data (RWD) to produce RWE, ranging from randomized trials with outcomes assessed using RWD to fully observational studies. Yet, many proposals for generating RWE lack sufficient detail, and many analyses of RWD suffer from implausible assumptions, other methodological flaws, or inappropriate interpretations. TheCausal Roadmapis an explicit, itemized, iterative process that guides investigators to prespecify study design and analysis plans; it addresses a wide range of guidance within a single framework. By supporting the transparent evaluation of causal assumptions and facilitating objective comparisons of design and analysis choices based on prespecified criteria, theRoadmapcan help investigators to evaluate the quality of evidence that a given study is likely to produce, specify a study to generate high-quality RWE, and communicate effectively with regulatory agencies and other stakeholders. This paper aims to disseminate and extend theCausal Roadmapframework for use by clinical and translational researchers; three companion papers demonstrate applications of theCausal Roadmapfor specific use cases.
Background and Purpose: Mechanical thrombectomy helps prevent disability in patients with acute ischemic stroke involving occlusion of a large cerebral vessel. Thrombectomy requires procedural expertise and not all hospitals have the staff to perform this intervention. Few population-wide data exist regarding access to mechanical thrombectomy. Methods: We examined access to thrombectomy for ischemic stroke using discharge data from calendar years 2016 to 2018 from all nonfederal emergency departments and acute care hospitals across 11 US states encompassing 80 million residents. Facilities were classified as hubs if they performed mechanical thrombectomy, gateways if they transferred patients who ultimately underwent mechanical thrombectomy, and gaps otherwise. We used standard descriptive statistics and unadjusted logistic regression models in our primary analyses. Results: Among 205 681 patients with ischemic stroke, 100 139 (48.7% [95% CI, 48.5%–48.9%]) initially received care at a thrombectomy hub, 72 534 (35.3% [95% CI, 35.1%–35.5%]) at a thrombectomy gateway, and 33 008 (16.0% [95% CI, 15.9%–16.2%]) at a thrombectomy gap. Patients who initially received care at thrombectomy gateways were substantially less likely to ultimately undergo thrombectomy than patients who initially received care at thrombectomy hubs (odds ratio, 0.27 [95% CI, 0.25–0.28]). Rural patients had particularly limited access: 27.7% (95% CI, 26.9%–28.6%) of such patients initially received care at hubs versus 69.5% (95% CI, 69.1%–69.9%) of urban patients. For 93.8% (95% CI, 93.6%–94.0%) of patients with stroke at gateways, their initial facility was capable of delivering intravenous thrombolysis, compared with 76.3% (95% CI, 75.8%–76.7%) of patients at gaps. Our findings were unchanged in models adjusted for demographics and comorbidities and persisted across multiple sensitivity analyses, including analyses adjusting for estimated stroke severity. Conclusions: We found that a substantial proportion of patients with ischemic stroke across the United States lacked access to thrombectomy even after accounting for interhospital transfers. US systems of stroke care require further development to optimize thrombectomy access.