Case-Control Study Design
Case-Control Study Design
STUDY DESIGN
1
2
DEFINTION
• Case control studies, often called "retrospective studies“
• Are a common first approach to test causal hypothesis.
• Emerged as a permanent method of epidemiological investigation.
Three distinct features :
a) both exposure and outcome (disease) have occurred before the start of the study.
b) the study proceeds backwards from effect to cause.
c) it uses a control or comparison group to support or refute an inference.
3
Case Control Design
Time
Direction of Inquiry
8
BASIC STEPS
1. Selection of cases and controls
2. Matching
3. Measurement of exposure, and
4. Analysis and interpretation
9
1. Selection of cases and controls
(1) SELECTION OF CASES
(a) Definition of a case
DIAGNOSTIC CRITERIA - diagnostic criteria & stage of disease
ELIGIBILITY CRITERIA – only newly diagnosed cases
(b) Sources of cases
i) HOSPITALS (ii) GENERAL POPULATION
10
(2) SELECTION OF CONTROLS –
controls must be free from the disease under study
Sources of controls
i) HOSPITAL
ii) RELATIVES
iii)NEIGHBOURHOOD
14
3. Measurement of exposure
• Information about exposure should be obtained in precisely the
same manner both for cases and controls.
• Interviews,
• By questionnaires
• By studying past records of cases such as hospital records,
employment records, etc
15
4. Analysis
(a) Exposure rates among cases and controls to suspected factor.
16
(a) EXPOSURE RATES
A case control study provides a direct estimation of the exposure
rates (frequency of exposure) to a suspected factor in disease
and non-disease groups
Exposure rates
a. Cases = a/(a+c)
b. Controls = b/(b +d)
17
18
b) ESTIMATION OF RISK
• It is the estimation of disease risk associated with exposure.
• The ratio between the incidence of disease among exposed persons and
incidence among non-exposed.
22
Example 1: Adenocarcinoma of vagina
• An excellent example
• It is not only a rare disease, but also the usual victim is over 50 years of
age.
• There was an unusual occurrence of this tumour in 7 young women (15 to
22 years) born in one Boston hospital between 1966 and 1969.
• An eighth case occurred in 1969 in a 20 year old patient who was treated
at another Boston hospital in USA.
23
• The cause of this tumor was investigated by a case control study in 1971.
• The controls were identified from the birth records of the hospital in which each
case was born.
• Information was collected by personal interviews regarding (a) maternal age (b)
maternal smoking (c) antenatal radiology, and (d) diethyl-stilbesterol (DES)
exposure in foetal life.
24
25
Example 2: Oral contraceptives and
thromboembolic disease
• By August 1965, the British Committee on Safety of Drugs had received 249
reports of adverse reactions and 16 reports of death in women taking oral
contraceptives.
• In 1968 and 1969, Vassey and Doll reported the findings of their case control
studies
• Women with venous thrombosis or pulmonary embolism without medical cause
• Other women who had been admitted with other diseases
• Matched for age, marital status and parity.
26
The investigators found that users of oral contraceptives were about 6
times as likely as non-users to develop thromboembolic disease.
27
BIASES IN CASE-CONTROL STUDY
Bias is any systematic error in the determination of the association between the
exposure and disease
Many varieties may arise in epidemiological studies
b)Memory or Recall bias : Cases who are suffering from a disease are likely to
recall much more as regards their exposure.
c)Selection bias : The cases and controls may not be representative of cases and
controls in the general population.
e)Observer bias : If observer is aware of the case - control status, she may
subconsciously tend to ask much more from cases.
29
ADVANTAGES
30
• Relatively easy to carry out.
• Inexpensive, requires only a few subjects gives quick results.
• Well suited for diseases which have a long latent period (e.g. cancers,
AIDS, MI, CVA etc.)
• Well suited for an outcome which is ‘rare’.
• No risk to subjects
• Helps in examining multiple etiologic factors.
• Reasonably good for diseases that have a “relatively rapid onset” and are
usually hospitalised (e.g. most of the acute infections; injuries etc.)
31
• Risk factors can be identified. Rational prevention and control programmes
can be established.
32
DISADVANTAGES
33
• Selection of an appropriate control group may be difficult
34
• Not suited to the evaluation of therapy or prophylaxis of disease.
35
THANK YOU
36