Study designs introduction, Slides of Research Methodology

Download Study designs introduction and more Slides Research Methodology in PDF only on Docsity!

Research Methodology 1 Intro to study designs Case control and Cohort Studies

Guest Lecture- T Devanathan

Background

• (^) Study designs are structured approaches to address specific research questions- looks at the relationship between exposure and outcome to answer a research question.
• (^) Outcomes - Health outcome of interest in the study- Disease, death, side effect, complication (stats: “dependent variables” Y axis )
• (^) Exposures - Measures that may be associated with the outcome - Possible “risk factors”, “causes”, “determinants” (stats: “independent variables” X axis )

Case-control study design

• (^) You have the outcome , you are investigating

exposure

• (^) In order to do this: Compares a group of

participants possessing a condition of interest

(cases) to a similar group who do not possess

that condition of interest (controls)-

• (^) Draw a conclusion by assessing those who have

the outcome compared to those who don’t.

Example: To investigate if smoking is associated with an increased risk of lung cancer.

• (^) Cases: Patients who have been diagnosed with lung cancer (the outcome of interest).
• (^) Controls: Patients who do not have lung cancer but are otherwise similar in age, gender, and other relevant factors.
• (^) Exposure Assessment: Gather information on the smoking history of both the cases and controls, such as whether they have smoked, for how long, and how much.
• (^) Analysis: Compare the frequency of smoking between the cases and controls. If smoking is more common among the cases than the controls, it may suggest an association between smoking and lung cancer.
• (^) Draw a conclusion based on your results- is the exposure related to the outcome?

Disadvantages of case-control studies:

• (^) Multiple outcomes cannot be studied
• (^) Recall bias
• (^) Sampling bias
• (^) Cannot calculate prevalence, incidence, population relative risk
• (^) Beware of reverse causation

When should you use a case-control study design?

• (^) The disease or outcome is rare: It's easier to find a group of people who already have the condition (cases) and compare them to those who don't (controls).
• (^) Time or resources are limited: Case-control studies are quicker and less expensive because they focus on people who already have the outcome rather than following a large group over time.
• (^) You want to study multiple risk factors: You can explore various factors that might be linked to the outcome by looking at differences between the cases and controls

For example, if the OR is 2, it means that the odds of having the exposure are twice as high among the cases compared to the controls, suggesting that the exposure may be a risk factor for the outcome. Conversely, an OR of less than 1 suggests that the exposure might be protective against the outcome.

Cohort study design

• (^) In a cohort study you start with a group of people who are exposed to something (like smoking) and another group who are not exposed. You follow both groups over time to see who develops the outcome (like lung cancer).
• (^) Example: Tracking smokers and non-smokers over several years to see who gets lung cancer- note how this is different to a case-control study.
• (^) Key differences:
• (^) Cohort Study: Follows people forward in time from exposure to outcome.
• (^) Case-Control Study: Looks backward in time from outcome to exposure.

2. Retrospective - researchers look back at data from a

group of people (a cohort) who were exposed to

something in the past and compare their outcomes to

those who were not exposed. The key here is that the

events (exposures and outcomes) have already

happened, and the researchers are analysing existing

records or data (looking back)

How is a retrospective cohort study different from a

case-control study?

• (^) Retrospective Cohort Study: Starts with people

based on their past exposure and follows up on

what outcomes they developed. The focus is on

a timeline where exposure happened first, and

then you check the outcomes.

• (^) Case-Control Study: Starts with people who

already have the outcome (cases) and those

who don't (controls), then looks back to see if

they were exposed to something in the past.