The case-control study: a primer for the obstetrician-gynecologist.

Case-control studies begin at the end. Two groups of patients, those with disease (cases) and those without (controls), are compared to determine the degree of exposure to a presumed risk factor. This research method is commonly used to study rare diseases or diseases that take years to develop. If a higher proportion of cases than controls has the exposure of interest, the exposure may be associated with illness. The strength of this association is measured by an "odds ratio," which is a good proxy for a relative risk when the illness in question is infrequent. Although some case-control studies are easy to do, all are easy to do poorly, especially because of selection bias in the choice of controls. A greater familiarity with the case-control study should enable obstetrician-gynecologists to evaluate critically published studies using this research method.