False-positive results in pharmacoepidemiology and pharmacovigilance

Abstract

False-positive constitute an important issue in scientific research. In the domain of drug evaluation, it affects all phases of drug development and assessment, from the very early preclinical studies to the late post-marketing evaluations. The core concern associated with this false-positive is the lack of replicability of the results. Aside from fraud or misconducts, false-positive is often envisioned from the statistical angle, which considers them as a price to pay for type I error in statistical testing, and its inflation in the context of multiple testing. If envisioning this problematic in the context of pharmacoepidemiology and pharmacovigilance however, that both evaluate drugs in an observational settings, information brought by statistical testing and the significance of such should only be considered as additional to the estimates provided and their confidence interval, in a context where differences have to be a clinically meaningful upon everything, and the results appear robust to the biases likely to have affected the studies. In the following article, we consequently illustrate these biases and their consequences in generating false-positive results, through studies and associations between drug use and health outcomes that have been widely disputed.

Keywords: Biais; Biases; Drug safety; False-positive; Faux positifs; Pharmacoepidemiology; Pharmacovigilance; Pharmacoépidémiologie; Sécurité du médicament.