Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 5;194(2):524-535.
doi: 10.1093/aje/kwae234.

Use of sensitivity analyses to assess uncontrolled confounding from unmeasured variables in observational, active comparator pharmacoepidemiologic studies: a systematic review

Affiliations

Use of sensitivity analyses to assess uncontrolled confounding from unmeasured variables in observational, active comparator pharmacoepidemiologic studies: a systematic review

Chase D Latour et al. Am J Epidemiol. .

Abstract

Understanding the potential for, and direction and magnitude of uncontrolled confounding is critical for generating informative real-world evidence. Many sensitivity analyses are available to assess robustness of study results to residual confounding, but it is unclear how researchers are using these methods. We conducted a systematic review of published active-comparator cohort studies of drugs or biologics to summarize use of sensitivity analyses aimed at assessing uncontrolled confounding from an unmeasured variable. We reviewed articles in 5 medical and 7 epidemiologic journals published between January 1, 2017, and June 30, 2022. We identified 158 active-comparator cohort studies: 76 from medical and 82 from epidemiologic journals. Residual, unmeasured, or uncontrolled confounding was noted as a potential concern in 93% of studies, but only 84 (53%) implemented at least 1 sensitivity analysis to assess uncontrolled confounding from an unmeasured variable. The most common analyses were E-values among medical journal articles (21%) and restriction on measured variables among epidemiologic journal articles (22%). Researchers must rigorously consider the role of residual confounding in their analyses and the best sensitivity analyses for assessing this potential bias. This article is part of a Special Collection on Pharmacoepidemiology.

Keywords: active comparator; cohort; confounding; observational; sensitivity analyses.

PubMed Disclaimer

Conflict of interest statement

C.D.L. has received payment from Target RWE and Amgen as a consultant for unrelated projects. C.D.L., C.W., C.O.A., and I.H.S. were or currently are fellows through the Center for Pharmacoepidemiology, housed in the Department of Epidemiology, over the course of this study. C.W. received payment from Target RWE as a consultant for unrelated projects. M.D. served as a graduate research assistant over the course of this study at GlaxoSmithKline (GSK) for unrelated projects. C.O.A. was employed by Johnson & Johnson as an intern over the course of this study, working on unrelated projects. T.S. receives salary support as director of Comparative Effectiveness Research, NC TraCS Institute, University of North Carolina (UNC) Clinical and Translational Science Award (UL1TR002489); as co-director of the Human Studies Consultation Core, NC Diabetes Research Center (P30DK124723), National Institute of Diabetes and Digestive and Kidney Diseases; and from a generous contribution from Dr. Nancy A. Dreyer to the Department of Epidemiology, UNC at Chapel Hill. T.S. owns stock in Novartis, Roche, and Novo Nordisk. J.L.L.’s spouse was formerly employed by GSK and previously owned stock in the company. AbbVie, Astellas, Boehringer Ingelheim, GlaxoSmithKline (GSK), Takeda, Sarepta, and UCB Bioscience have collaborative agreements with the Center for Pharmacoepidemiology housed in the Department of Epidemiology, which provides salary support to T.S. and M.J.F. M.J.F. is a member of the Scientific Steering Committee (SSC) of a post-approval safety study of an unrelated drug class funded by GSK. All compensation for services provided on the SSC is invoiced by and paid to UNC at Chapel Hill. M.J.F. is a member of the Epidemiology and Clinical Advisory Board for Epividian. I.H.S. received funding from Bristol-Myers Squibbs (BMS) through UNC as UNC-BMS Global Health Economics and Outcomes Research predoctoral fellow. The other authors have no conflicts to report.

Figures

Figure 1
Figure 1
Articles from active comparator cohort studies in (A) medical and (B) epidemiology journals that conducted sensitivity analyses for confounding from unmeasured variables. JAMA, Journal of the American Medical Association.

Similar articles

Cited by

References

    1. US Food and Drug Administration . 21st Century Cures Act. 2020. Accessed May 3, 2022. https://www.fda.gov/regulatory-information/selected-amendments-fdc-act/2...
    1. 114th Congress . 21st Century Cures Act. H.R 34; 2016. Accessed May 3, 2022. https://www.congress.gov/114/plaws/publ255/PLAW-114publ255.pdf
    1. Concato J, ElZarrad MK. FDA issues draft guidances on real-world evidence, prepared to publish more in future. US Food and Drug Administration. 2022. Accessed May 3, 2022. https://www.fda.gov/drugs/news-events-human-drugs/fda-issues-draft-guida...
    1. Concato J, Corrigan-Curay J. Real-world evidence—where are we now? N Engl J Med. 2022;386(18):1680-1682. 10.1056/nejmp2200089 - DOI - PubMed
    1. Moore KL, Neugebauer R, van der Laan MJ, et al. Causal inference in epidemiological studies with strong confounding. Stat Med. 2012;31(13):1380-1404. 10.1002/sim.4469 - DOI - PMC - PubMed

Publication types

MeSH terms