A clinical study in which participants identified as belonging to study groups are assessed for biomedical or health outcomes. Participants may receive diagnostic, therapeutic, or other types of interventions, but the investigator does not assign participants to specific interventions (as in an interventional study).

observational_study

 

You can see the above figure, which show the small structure of study design. As per the requirement of study, we divide it into two parts, “Observational Study” and “Experimental Study”. We will discuss about Experimental Study in next part, so right now I will tell you something about “Observational Study”. In an Observational study, the investigator only observes the effect of the exposure on the study subjects; he/she not assigning exposure to the study subject from their side.

Exposure and Outcome are the two main or basic components in clinical epidemiology. Exposure covers all risk factor, a prognostic factor, diagnostic test, or a treatment. On the other hand outcome consist death and disease.  In an observational study, the frequency of an outcome—or an exposure, depending on the study design—is measured, estimated, or visualised. Risks, rates, prevalences, and odds are common measures of the frequency of an outcome, and comparing them between groups will yield relative frequency measures—that is, relative risks, rate ratios, prevalence ratios, and odds ratios. These describe the association between exposure and outcome and provide the basis for the study’s conclusions.

Observational Study Designs

If you see the above figure of study design then you see the Observational study is of three types:

Cohort Design

Cohort studies starts with the subject who are exposed or not to a factor and evaluate the subsequent development of an outcome. Cohort studies may be concurrent or retrospective, the distinction being when, relative to the current time, the subject are identified. See below figure

Importance of cohort studies:

  • Evidence to suggest a relation between an exposure and an outcome
  • Time interval between exposure and outcome is relatively short to minimize follow-up loss.
  • The outcome is not too rare

cohort

Here you can see, one group is exposed (smoker) and other one is not exposed (non-smoker). After long follow-up, investigator check the outcome or difference result between these two groups. Sometime outcome is not show the satisfied result, in that case a very large population must be followed for the better result and evaluation of association between the exposure and outcome.

Case–control design

In case-control studies, first find out the individual or subject who have the outcome or cases and then compare them to the individual who do not have any outcome or we can say controls, as per the past history to a factor.

A case-control study is suitable in two cases:

  • Outcome is rare
  • Reliable evidence of past exposure