The good, the bad, and the different: A primer on aspects of heterogeneity of treatment effects

摘要

The concept of heterogeneity is concerned with understanding differences within and across patients and studies. Heterogeneity of treatment effects is nonrandom variability in response to treatment and includes both benefits and harms. Because not all patients respond the same way, treatment decisions applied in a "one size fits all" fashion based on the average response observed in clinical trials may lead to suboptimal outcomes for some patients. Variation in outcomes among patients may be caused by observable and nonobservable factors. Changes in patients' health status over time can contribute to variability among patients. Assuming that the results from clinical trials are homogeneous across patients may fail to take into account clinically significant variability where some patients may receive benefit and others harm. Subgroup analyses and prediction models are 2 tools to explain variability observed within a study. Evidence synthesis with meta-analysis can provide useful information on the overall effectiveness and response among groups of patients undersampled in individual studies. Yet caution is warranted if the meta-analysis is missing studies or the individual studies comprising the meta-analysis are inherently different. For those making clinical, coverage, and reimbursement decisions at a population level, such as clinicians and pharmacy and therapeutics committee members, understanding the variation among patients, among subpopulations or populations of patients, among clinical studies, or within a meta-analysis is important to ensuring optimal patient outcomes. This article presents a variety of tools and resources to aid decision makers as they evaluate the literature to determine when clinically relevant differences exist.