A5063240084- Health Systems, Economic Evaluations, Quality of Life
- Advanced Causal Inference Techniques
- Statistical Methods in Clinical Trials
- Pharmacovigilance and Adverse Drug Reactions
- COVID-19 Clinical Research Studies
- Pharmaceutical Practices and Patient Outcomes
- SARS-CoV-2 and COVID-19 Research
- Pharmaceutical Economics and Policy
- Healthcare Policy and Management
- Meta-analysis and systematic reviews
- Antiplatelet Therapy and Cardiovascular Diseases
- Pharmaceutical studies and practices
- Cardiac, Anesthesia and Surgical Outcomes
- Statistical Methods and Bayesian Inference
- Sepsis Diagnosis and Treatment
- Atrial Fibrillation Management and Outcomes
- Acute Myocardial Infarction Research
- Medication Adherence and Compliance
- Bariatric Surgery and Outcomes
- Drug-Induced Hepatotoxicity and Protection
- Venous Thromboembolism Diagnosis and Management
- Biomedical Ethics and Regulation
- Long-Term Effects of COVID-19
- Coronary Interventions and Diagnostics
- SARS-CoV-2 detection and testing
Aetion (United States)
2015-2023
Engineering Information Foundation
2022
University at Buffalo, State University of New York
2021
University of Toronto
2020-2021
Jacobs (United States)
2020
Brigham and Women's Hospital
2008-2016
Harvard University
2006-2014
Division of Chemistry
2013
Pharmacoeconomics and Health Outcomes Research Iberia (Spain)
2009-2012
Boca Raton Regional Hospital
2012
In Brief Background: Adjusting for large numbers of covariates ascertained from patients' health care claims data may improve control confounding, as these variables collectively be proxies unobserved factors. Here, we develop and test an algorithm that empirically identifies candidate covariates, prioritizes integrates them into a propensity-score-based confounder adjustment model. Methods: We developed multistep to implement high-dimensional proxy in data. Steps include (1) identifying...
ABSTRACT Background Among the large number of cohort studies that employ propensity score matching, most match patients 1:1. Increasing matching ratio is thought to improve precision but may come with a trade‐off respect bias. Objective To evaluate several methods in through simulation and empirical analyses. Methods We simulated cohorts 20 000 exposure prevalence 10%–50%. five dichotomous continuous confounders. estimated scores matched using digit‐based greedy (“greedy”), pairwise nearest...
Epidemiologic studies are increasingly used to investigate the safety and effectiveness of medical products interventions. Appropriate adjustment for confounding in such is challenging because exposure determined by a complex interaction patient, physician, healthcare system factors. The challenges control particularly acute using utilization databases where information on many potential factors lacking meaning variables often unclear. We discuss advantages disadvantages different approaches...
Understanding the effect of serum antibodies to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) on susceptibility infection is important for identifying at-risk populations and could have implications vaccine deployment.
Recent theoretical studies have shown that conditioning on an instrumental variable (IV), a is associated with exposure but not outcome except through exposure, can increase both bias and variance of effect estimates. Although these findings obvious implications in cases known IVs, their meaning remains unclear the more common scenario where investigators are uncertain whether measured covariate meets criteria for IV or rather confounder. The authors present results from two simulation...
Inferring causation from non‐randomized studies of exposure requires that groups can be balanced with respect to prognostic factors for the outcome. Although there is broad agreement in literature balance should checked, confusion regarding appropriate metric. We present a simulation study compares several metrics strength their association bias estimation effect binary on binary, count, or continuous The simulations utilize matching propensity score successively decreasing calipers produce...
Severe nonmalignant pain affects a large proportion of adults. Optimal treatment is not clear, and opioids are an important option for analgesia. However, there relatively little information about the comparative safety opioids. Therefore, we sought to compare commonly used pain.We devised propensity-matched cohort analysis that health care utilization data collected from January 1, 1996, through December 31, 2005. Study participants were Medicare beneficiaries 2 US states who new initiators...
Pharmacoepidemiologic and pharmacoeconomic analysis of health care databases has become a vital source evidence to support decision making efficient management organizations. However, makers often consider studies done in nonrandomized more difficult review than randomized trials because many design choices need be considered. This is perceived as an important barrier about the effectiveness safety medical products. Design flaws longitudinal database are avoidable but can unintentionally...
Recent studies have raised concerns about the reduced efficacy of clopidogrel when used concurrently with proton pump inhibitors (PPIs), but those may overestimated risk.We studied potential for increased risk adverse cardiovascular events among users versus without concurrent use PPIs in 3 large cohorts patients > or =65 years age, treated between 2001 and 2005. All had undergone percutaneous coronary intervention been hospitalized acute syndrome Pennsylvania, New Jersey, British Columbia,...
Comparative-effectiveness research (CER) aims to produce actionable evidence regarding the effectiveness and safety of medical products interventions as they are used outside controlled settings. Although CER medications is particularly needed shortly after market approval, key methodological challenges include (i) potential bias due channeling patients newly marketed medication because various patient-, physician-, system-related factors; (ii) rapid changes in characteristics user...
To reduce bias by residual confounding in nonrandomized database studies, the high-dimensional propensity score (hd-PS) algorithm selects and adjusts for previously unmeasured confounders. The authors evaluated whether hd-PS maintains its capabilities small cohorts that have few exposed patients or outcome events. In 4 North American pharmacoepidemiologic cohort studies between 1995 2005, repeatedly sampled data to yield increasingly smaller cohorts. They identified potential confounders...
The scientific community and decision-makers are increasingly concerned about transparency reproducibility of epidemiologic studies using longitudinal healthcare databases. We explored the extent to which published pharmacoepidemiologic commercially available databases could be reproduced by other investigators. identified a nonsystematic sample 38 descriptive or comparative safety/effectiveness cohort studies. Seven were excluded from reproduction, five because violation fundamental design...
Nonrandomized pharmacoepidemiology generally compares one medication with another. For many conditions, clinicians can benefit from comparing the safety and effectiveness of three or more appropriate treatment options. We sought to compare groups simultaneously by creating 1:1:1 propensity score-matched cohorts.We developed a technique that estimates generalized scores then creates matched sets. compared this methodology two existing approaches-construction cohorts through common-referent...
Instrumental variable analyses are increasingly used in epidemiologic studies. For dichotomous exposures and outcomes, the typical 2-stage least squares approach produces risk difference estimates rather than relative is criticized for assuming normally distributed errors. Using 2 example drug safety studies evaluated 3 cohorts from Pennsylvania (1994–2003) British Columbia, Canada (1996–2004), authors compared instrumental techniques that yield appropriate outcomes. Methods considered...
Abstract Purpose Defining a study population and creating an analytic dataset from longitudinal healthcare databases involves many decisions. Our objective was to catalogue scientific decisions underpinning execution that should be reported facilitate replication enable assessment of validity studies conducted in large databases. Methods We reviewed key investigator required operate sample macros software tools designed create analyze cohorts streams data. A panel academic, regulatory,...
Health care databases are natural sources for estimating prevalence and incidence of chronic conditions, but substantial variation in estimates limits their interpretability utility. We evaluated the effects design choices when claims electronic health record databases.Prevalence five diseases at increasing levels expected frequencies, from cystic fibrosis to COPD, were estimated Clinical Practice Research Datalink (CPRD) MarketScan 2011 2014. Estimates compared using different definitions...
Defining a study population and creating an analytic dataset from longitudinal healthcare databases involves many decisions. Our objective was to catalogue scientific decisions underpinning execution that should be reported facilitate replication enable assessment of validity studies conducted in large databases.We reviewed key investigator required operate sample macros software tools designed create analyze cohorts streams data. A panel academic, regulatory, industry experts database...
<h3>Importance</h3> Vaccination against the SARS-CoV-2 virus is critical to control pandemic. Randomized clinical trials demonstrated efficacy of single-dose Ad26.COV2.S COVID-19 vaccine, but data on longer-term protection in practice and effectiveness variants are needed. <h3>Objective</h3> To assess association between receiving vaccine COVID-19–related infections hospitalizations before during Delta variant surge. <h3>Design, Setting, Participants</h3> This cohort study included adults...