Assessing Scientific Data: The Case-Control Study As It Applies to Dermatology
Part 2: Interpreting the Results


Helen J. Heacock* and Jason K. Rivers†

Critical Appraisal Review covers various topics in epidemiology and related fields that are useful to the practicing physician in understanding and using published studies on skin disease topics. Readers may suggest future topics for this series by writing to the Editorial Office.

In this issue, Helen Heacock and Jason Rivers elucidate the threats to the validity of case-control studies, and provide a checklist to assist in assessing their quality.

Martin A. Weinstock

Abstract

Background: In order to interpret the results of case-control studies correctly and to assign causality to an exposure-disease association, one must be able to assess elements in the design and/or analysis that may lead to inaccurate conclusions.

Objective: The purpose of this article is to describe factors that may invalidate the results of a case-control study. Topics discussed include bias, confounding, and chance. Criteria used to judge causality between exposure and disease are highlighted. A brief checklist that can be used as a tool in the design and interpretation of case-control studies is provided.

Conclusion: Before one concludes that an exposure causes a disease, alternative explanations for the observations must be considered. Assuming that these threats to the validity of the study have been minimized, criteria for judging causality can be examined. In this way, it becomes possible to link a specific exposure with a specific outcome.

Sommaire

Antécédents: Pour interpréter correctement les résultats d’une étude cas-témoins et établir un lien de causalité entre exposition et maladie, il faut pouvoir évaluer les éléments de méthode ou d’analyse qui peuvent induire en erreur.

Objectifs: Décrire les facteurs pouvant invalider les résultats d’une étude cas-témoins, dont l’erreur systématique, les biais, la confusion et le hasard. Les critères permettant de juger du lien de cause à effet entre exposition et maladie sont mis en relief. Le document contient en outre une brève liste de vérification pouvant aider à la conception et à l’interprétation des études cas-témoins.

Conclusion: Avant de conclure au lien de cause à effet entre exposition et maladie, mieux vaut envisager diverses façons d’expliquer les symptômes. Une fois réduite au minimum l’incidence des facteurs pouvant compromettre la validité de l’étude, il est possible d’examiner les critères permettant d’évaluer la causalité. Alors seulement peut-on lier telle exposition spécifique à tel résultat spécifique.


Received 1/14/97. Accepted for publication 3/13/97.

*The Department of Health Care and Epidemiology, University of British Columbia; †Division of Dermatology, Vancouver Hospital and Health Sciences Centre, University of British Columbia, and British Columbia Cancer Agency, Vancouver, British Columbia

Reprint requests: Jason K. Rivers, MD, FRCPC, Division of Dermatology, The Skin Care Centre, 835 West 10th Avenue, Vancouver, BC V5Z 4E8 Canada

Full text available in the print edition / Pour le texte intégral veuillez consulter la version imprimée.


JCMS 2(1) Contents