Case-Control Studies in Neurosurgery: The Issue of Effect Estimates

Abstract

Clinical research questions are commonly answered using a case-control design. The decision to use this design is usually justified due to low cost, feasibility, and ease of execution. However, the case-control design presents challenges in execution, selection of cases/controls, and interpretation of effect measures (odds ratios, among others). In this paper, we clarify for a neurosurgical audience the design and appropriate effect size measures obtained from case-control studies. A narrative review was conducted of published literature on the topic. The future implementation of such studies was discussed and highlighted with several examples from neurosurgical practice. In a case-control design, participants are selected for a study based on their outcome status. Some participants have the outcome of interest (cases), whereas others do not (controls). Controls can be selected from a variety of sources, such as the general population, relatives/friends, or hospital patients without the disease under investigation. The most important criterion is that these controls come from the same study base as cases. Furthermore, it is essential to realize that measures of association obtained from a case-control study depend on the sampling strategy of the controls and, as such, have equivalent counterparts available from cohort studies. We delineate traditional case-control, case-cohort, and incidence density-sampled case-control studies and their applicability to common conditions encountered in daily neurosurgical practice (e.g., glioblastoma, aneurysms, and epilepsy). Neurosurgeons must understand the types of case-control studies and their associated effect measures to properly conduct research and incorporate research findings into clinical practice.