Case-non-case studies: Principle, methods, bias and interpretation

Abstract

Case-non-case studies are among the methods used to assess drug safety by analyzing the disproportionality of adverse drug reaction reports in pharmacovigilance databases. First used in the 1980s, the last few decades have seen a significant increase in the use of this study design. The principle of case-non-case studies is to compare the drug exposure of cases of an adverse reaction of interest with that of cases with other reported reactions and called "non-cases". Their results are presented in the form of reporting odds ratio (ROR), the interpretation of which makes it possible to highlight pharmacovigilance signals. This article describes the principle of case-non-case studies, the calculation method of the ROR and its confidence interval, the different analytical modalities and how to interpret its results with regard to the advantages and limitations of this type of study.

Keywords: Bias; Case–non-case studies; Disproportionality analysis; Pharmacoepidemiology; Pharmacovigilance; Reporting odds ratio.