[Historical issues in case-control studies].

This paper presents the main issues in the evolution of case-control studies (CCS) as of the late 1980s. The comparison of two groups regarding exposure to a risk factor has been known since the 18th century. The latter half of the 19th century witnessed a decline in the "Epidemiology of Populations", and the first CCS were only done in the 1920s. Improvement of the method occurred in the latter half of the 20th century, related to increased mortality from chronic diseases, especially in research on lung cancer and smoking. The main scientific contributions to the method were: use of the odds ratio as an estimate of relative risk; definition of statistical data analysis for retrospective studies; calculation of attributed risk and etiologic fraction; and discussion of the essence of CCS. Critics pointed to the method's possible weakness and susceptibility to bias. Application of CCS increased in the final decades of the 20th century in various areas of Epidemiology and has been considered an important tool to improve Public Health.