How good is "evidence" from clinical studies of drug effects and why might such evidence fail in the prediction of the clinical utility of drugs?

Abstract

Promising evidence from clinical studies of drug effects does not always translate to improvements in patient outcomes. In this review, we discuss why early evidence is often ill suited to the task of predicting the clinical utility of drugs. The current gap between initially described drug effects and their subsequent clinical utility results from deficits in the design, conduct, analysis, reporting, and synthesis of clinical studies-often creating conditions that generate favorable, but ultimately incorrect, conclusions regarding drug effects. There are potential solutions that could improve the relevance of clinical evidence in predicting the real-world effectiveness of drugs. What is needed is a new emphasis on clinical utility, with nonconflicted entities playing a greater role in the generation, synthesis, and interpretation of clinical evidence. Clinical studies should adopt strong design features, reflect clinical practice, and evaluate outcomes and comparisons that are meaningful to patients. Transformative changes to the research agenda may generate more meaningful and accurate evidence on drug effects to guide clinical decision making.

Keywords: bias; clinical trials; drug therapy; precision medicine; prediction in pharmacology; treatment effectiveness.