Clinical Research Methodology 2: Observational Clinical Research

• Published in: Anesthesia and analgesia Vol. 121; no. 4; pp. 1043 - 1051
• Main Authors: Sessler, Daniel I., Imrey, Peter B.
• Format: Journal Article
• Language: English
• Published: United States International Anesthesia Research Society 01.10.2015
• Subjects: Biomedical Research - methods; Biomedical Research - standards; Case-Control Studies; Cohort Studies; Humans; Observational Studies as Topic - methods; Observational Studies as Topic - standards; Research Design - standards; Retrospective Studies
• ISSN: 0003-2999; 1526-7598; 1526-7598
• DOI: 10.1213/ANE.0000000000000861

Case-control and cohort studies are invaluable research tools and provide the strongest feasible research designs for addressing some questions. Case-control studies usually involve retrospective data collection. Cohort studies can involve retrospective, ambidirectional, or prospective data collection. Observational studies are subject to errors attributable to selection bias, confounding, measurement bias, and reverse causation—in addition to errors of chance. Confounding can be statistically controlled to the extent that potential factors are known and accurately measured, but, in practice, bias and unknown confounders usually remain additional potential sources of error, often of unknown magnitude and clinical impact. Causality—the most clinically useful relation between exposure and outcome—can rarely be definitively determined from observational studies because intentional, controlled manipulations of exposures are not involved. In this article, we review several types of observational clinical researchcase series, comparative case-control and cohort studies, and hybrid designs in which case-control analyses are performed on selected members of cohorts. We also discuss the analytic issues that arise when groups to be compared in an observational study, such as patients receiving different therapies, are not comparable in other respects.