Observational studies in orthodontics

Randomized controlled trials (RCTs) are generally considered the highest level of evidence and the preferred approach to comparing the effectiveness of different treatments. However, the cost of an RCT can be very high, and it may be considered unethical to randomly assign patients to treatments that have no real benefits or even may cause harm. For rare events, it may take a long time and require a large number of patients to observe a sufficient number of outcomes. RCTs may have low external validity or generalizability. Observational studies provide valuable alternatives, particularly for developing predictive models and assessing the effectiveness of interventions. This article aims to provide a general introduction to the advantages and disadvantages of two major observational study designs, namely cohort and case-control studies. Cohort studies compare the outcomes of exposed and unexposed groups over time. However, the nonrandom allocation may lead to confounding bias. Propensity score matching and statistical adjustment are often used to address this problem, but they cannot deal with unmeasured confounders. Case-control studies select participants based on their outcomes and retrospectively collect information on the exposure levels of the case and control groups. We will discuss methods to minimize or adjust for confounding bias, such as propensity score matching and statistical adjustment.