1. Dr Luis E Cuevas – LSTM Julia Critchley
Case-control studies
Dr Luis E Cuevas – LSTM
Julia Critchley

2. Analytical (Observational) Epidemiology
Cohort Studies
Case-control studies
aim to identify potential associations between ‘risk’ factors and a particular disease or outcome

3. Case-control studies
Cases
Controls

4. Cases
With the disease
studied
Controls
Without the disease
studied

5. Differences between cohort studies and case-control
Cohorts – start with exposure
Case-controls – start with disease
EXPOSURE
DISEASE
DISEASE
EXPOSURE

6. Start by defining a CASE
clinical definition may be insufficient
list of criteria
reproducibility
certainty of diagnosis
Proven, very likely, possible
severity
Mild, Moderate, Severe
USUALLY INCIDENT CASES (newly diagnosed)

7. How many?
How many controls?

8. How many cases and controls?
based on:
Availability of cases and controls
List the main risk factors
Review the prevalence of the risk factor in the controls
What would be the expected prevalence of the risk factor in cases
Epi-Info - ask a statistician

9. Expected difference Prevalence in controls: Literature Other studies
National statistics
Other countries
Prevalence in cases
Previous studies
Key informers
Common sense
Use epi-info

10. Exposure to risk factor/s?
Cases
Exposure to risk factor/s?
Controls

11. Is exposure higher/lower in cases?
Controls

12. When are these studies most useful?
Limited information on risk factors (some times carried out before cohort studies)
Incidence of the disease is low (rare diseases)
Study many risk factors simultaneously

13. Major problem with case-control studies is bias
Selection bias
– differences in people who select themselves for studies compared with those who do not
Measurement bias
– individual measurements of disease or exposure are more likely to be incorrect
Recall bias in case-control studies

14. How might you reduce these biases in practice?
Suggestions?

15. Example Physical activity and risk of coronary heart disease
What are the factors that put a person at a
higher risk of suffering from CHD?

16. Individuals without CHD
Individuals with CHD
Cases
Individuals without CHD
Controls

17. Case definition Source/s of cases Location Hospital Time Single point
health centre
population
Time
Single point
period
Diagnosis
New
old

18. Controls difficult and critical issue
individuals who would have been selected as cases if they had the disease
same population
comparability to cases essential

19. Sources of controls Hospital General population Special groups
friends, neighbors, relatives
No ideal control group
Selectio factors that get you to attend one hospital

20. Sources of controls Hospital controls
The limitations of the control group should be taken into account when interpreting findings

21. Limitations of controls
Hospital
Ill by definition
> smokers
> alcohol
Relatives
Genetic similarity
Socio-economic conditions
Geographical situation
Willing to collaborate
Anxiety
Not always available
Neighbours
waiting to return from work
similarity
share environment
General population
generally unavailable
Unreliable (recall bias?)
uncooperative

22. List potential risk factors

23. Recap – confounding confounding mortality Physical activity smoking
A variable is a confounder if it is associated with the outcome of interest (death) and independently with the risk factor of interest.
We are interested in the relationship between physical activity and CHD.
Infant death. Smoking is also associated with CHD, and smoking and physical activity are associated with each other. Smoking is therefore a confounder
of the relationship between physical activity and CHD.
smoking
Physical
activity
mortality
confounding

24. Confounding
factors
Restriction
Matching
Stratified analysis
Multiple regression

25. Matching?
Cases
Controls

26. To avoid confounding
Age and sex
More difficult to analyse
Possible to ‘overmatch’

27. Assessing Causality
Statistically significant Odds Ratios show that there are associations between the risk factor (physical activity) and the disease (CHD)
They don’t prove this relationship is causal

28. Criteria for assessing causality (Bradford Hill)
Exposure before onset of disease
Strength of association
Independence from confounding
Consistent in different populations with different levels of exposure
Consistent with different studies in different settings
Dose-response relationship
Biologically plausible
Evidence from animal studies
Removal of exposure reduces risk

29. Strengths Good for study of rare diseases Long latent periods
Can look at multiple risk factors for a single disease
Quicker and cheaper than cohort studies

30. Limitations - summary Inefficient for the evaluation of rare exposures
Selection bias
Measurement bias
Recall bias
Difficult to interpret
Does not provide incidence rates
Does not provide ‘causation’, only associations