Case Control Study

Presenter: Dr Swapna.M
Guide: Dr Lalitha
1
Contents

 Introduction

 Definition of case control study

 Characters & Steps involved of case control study

 Selection of cases and controls

 Matching

 Bias in case control studies

 Measurement of exposure

 Analysis

 Merits and Demerits of case control study

 Case-Control studies based in a defined Cohort

 Conclusions

 References

2
Introduction:
Case control study is an epidemiological study design called analytical observational study. Analytical
studies are the second most major type of epidemiological studies.

It includes

1) Case- Control studies &

2) Cohort studies

In contrast to descriptive study which provides clues to the etiology & look at the entire population in
analytical studies the subject of interest is the individual within the population & the objective is to test
the hypothesis.

Purpose of Case Control Studies

1. To determine whether or not an association exists between a disease and a particular risk factor.
2. To start with a group of people with disease and work back to see whether a possible risk factor may
be the cause.
3. It may be the first step in testing a hypothesis. If positive, it can then be tested in a cohort study.

Definition:
A case control study is an inquiry in which groups of individuals are selected in terms of whether they
do (Cases) or do not (Controls) have the disease of which etiology is to be studied , and the groups are
then compared with respect to existing or past characteristics judged to be of possible relevance to the
etiology of the disease.

Character of a case control study:

1. Both exposure & outcome have occurred before the start of the study.
2. The study proceeds backwards from effect to the cause
3. It uses a control or comparison group to support or refute an inference
4. They yield estimates of relative effect measure

3
Steps in conducting a case-control study
1. Define a study population (source of cases and controls)

2. Define and select cases

3. Define and select controls

4. Measure exposure.

5. Estimate disease risk associated with exposure

Selection of cases & controls

The first step is to identify a suitable group of cases & a group of comparable controls from the source
population

Selection of cases:
Some of the pertinent aspects in this process is to clearly elucidate the diagnostic criteria for definition
of the cases, the sources from which the cases are selected & the inclusion & exclusion criteria for
selection.

Defining the case:

This is one of the important steps in the case control studies. Before the start of the study the criteria
should be well laid out & no subsequent modifications should be made to this. The criteria for diagnosis
of a case should be defined as well as the eligibility criteria used for selection. The diagnostic criteria
should be sensitive and specific (i.e. strict!)

Criteria which provide clear & reproducible values must be considered.

Sources of cases

1) Hospital Based
2) Population Based

4
Hospital Based: All persons with the disease seen at a particular medical care facility or group of
facilities in a specified period of time.

Advantage: Relatively easy & inexpensive to carry out.

Population Based: All persons with the disease found in a more general population such as that of a
city or country, at a point or in a period of time. Information on diseases can be got from death
certificates, disease registers, medical records or population survey.

Advantage: it avoids the bias arising from the selective factors that guide affected individual to a
particular medical care facility or physician.

Incident prevalent cases:

It is preferable to include only incident cases, as inclusion of cases at variety of stages in the disease
process & patients undergoing recurrences will complicate the interpretation of the findings. In patients
in advanced stages of the disease it may be difficult to differentiate past events causally related to the
disease from those consequent to it. Example: in a study of the x-ray exposure of the patients with
chronic leukemic it may be unclear whether x-ray exposures reported by the patient were given for
diagnosis of early symptoms of the disease, or even for therapeutic purposes, when the patient himself
may have been unaware that he already had the disease. In addition, in studies of prevalent cases, even if
the exposures clearly antedated the onset of present disease, it may not be possible to determine to what
extent a particular characteristic noted in excess in the case has relevance to the duration & course rather
than to the etiology of the disease.

Selection of Controls:
Controls are needed to allow evaluation of whether the frequency of a characteristics or past exposure
among the cases is different among comparable persons in the source population who do not have the
disease under investigation.

Sources of controls:
Before selecting individual controls, it is necessary to decide on the general source from which they will
be selected. An important consideration is whether or not the cases represent all the affected individuals
in the defined population. If they do, then the control group should also be drawn from that population.

5
General Population (Community Controls)
This is an appropriate source only when the cases represent all, controls can be taken from the
community the cases are from. The controls may be healthy or may have other diseases. It is worth
bearing in mind a couple of weaknesses with community controls. Healthy controls have less reliable
recall of exposure. They may also be less motivated to take part and so may have lower response rates. It
is generally more expensive & time consuming than use of other potential source of control groups.

Hospital
Other patients attending the same hospital as the case may be used as a source of control.
One rationale behind this choice is that patients with other diseases are subject to the same selective
factors that influenced the cases to come to this particular hospital.

The advantages of using hospital controls are:

(1) They are comparable to cases in regards to recall of exposure
(2) They are easy to access and information is gathered in a similar way to the cases
(3) They may be more willing to take part than healthy controls from the general population.

Disadvantages:
(1) They are not typical of healthy controls in regard to a variety of exposures
(2) You need to exclude diseases known to be associated with exposure of interest

Relatives of the cases

Two types of relatives are commonly used as sources of controls –spouses & siblings. Both these groups
are generally similar in ethnic & social background to cases. This will usually be an advantage since it
will eliminate certain spurious associations. However, if the study factor itself is one in which close
relatives are likely to be similar. Example diet, smoking or genetic background-they will not constitute a
suitable control group.

Associates of the cases

Members of the population must be selected on the basis of having shared with the case attendance at
the same school, similar place of employment, or residence in the same neighborhood.
Advantage: A large pool of healthy controls is available for comparison

Disadvantage similar to that of population controls.

6
Selection of individual controls

Having selected the source from which controls will be drawn, it is necessary to decide whether the data
for the cases will be compared with the data all the individual who might be available from the chosen
source or whether a sample will be selected. If a sample is decided on, a choice must be made between
the various sampling procedures available- the most common of them are random, systematic & paired
sampling.

Total population- No sampling

When the population from which the cases are drawn can be defined & is chosen as source of a control
group, it may be possible to use data on the total population. This is practical only when the data on the
frequency of the factors under examination are routinely recorded for the total population.
Random or systematic sampling is often used in the selection of controls when a listing of all the
potential control is available. Eg: population of birth in maternity hospital, a listing of all birth in the
hospital may be available. Similarly, population registers may facilitate the drawing of random sample
of the population of a geographic area. However, information on patients in or attending a general
hospital is rarely adequate for random or systematic sampling & paired samples are usually preferred if
hospitals are source of controls.

Paired sampling
This involves the selection from the sampling frame of one or more controls for each case. Individuals
are selected by virtue of some defined temporal or geographical relationship to the case. E.g.: the next pt
admitted after the case, the person living in the nearest residence to that of the case, the student next to
the case in an alphabetical class listing & so on.

USE OF MULTIPLE CONTROLS

Multiple controls for each case are frequently used.

Such controls may be either

(1) Controls of the same type, or

(2) Controls of different types, such as hospital and neighborhood controls, or controls with different
diseases.

Controls of the Same Type

Multiple controls of the same type, such as two controls or three controls for each case, are used to
increase the power of the study. Practically speaking, a noticeable increase in power is gained only up to
a ratio of about 1 case to 4 controls. These controls are of the same type; only the ratio of controls to
cases has changed.

7
Multiple Controls of Different Types

For example, we may be concerned that the exposure of the hospital controls used in our study may not
represent the rate of exposure that is “expected” in a population of non diseased persons. Hospitalized
patients smoke more than people living in the community, and we are concerned because we do not
know what the prevalence level of smoking in hospitalized controls represents or how to interpret a
comparison of these rates with those of the cases. To address this problem, we may choose to use an
additional control group, such as neighborhood controls. The hope is that the results obtained when
cases are compared with hospital controls will be similar to the results obtained when cases are
compared with neighborhood controls. If the findings differ, the reason for the discrepancy should be
sought. In using multiple controls of different types, the investigator should ideally decide which
comparison will be considered the “gold standard of truth” before embarking on the actual study.

In 1979, Gold and coworkers published a case-control study of brain tumors in children. They used two
types of controls: children with no cancer (called normal controls) and children with cancers other than
brain tumors (called cancer controls)

Children with brain tumor Children with cancer but Children without cancer
without brain tumor

What was the rationale for using these two control groups?

Let us consider the question, “Did mothers of children with brain tumors have more prenatal radiation
exposure than control mothers?” Some possible results are seen in fig below.

Children with brain tumor Children with cancer but

without brain tumor Children without cancer

8
If the radiation exposure of mothers of children with brain tumors is found to be greater than that of
mothers of normal controls, and the radiation exposure of mothers of children with other cancers is also
found to be greater than that of mothers of normal children, what are the possible explanations? One
conclusion might be that prenatal radiation is a risk factor both for brain tumors and for other cancers;
that is, its effect is that of a carcinogen that is not site specific. Another explanation to consider is that
the findings could have resulted from recall bias and that mothers of children with any type of cancer
recall prenatal radiation exposure better than mothers of normal children.

Consider another possible set of findings, shown in Figure

Children with brain tumor

Children with cancer but Children without cancer
without brain tumor

If mothers of children with brain tumors have a greater radiation exposure history than do both mothers
of normal controls and mothers of children with other cancers, the findings might suggest that prenatal
radiation is a specific carcinogen for the brain. These findings would also reduce the likelihood that
recall bias is playing a role, as it would seem implausible that mothers of children with brain tumors
would recall prenatal radiation better than mothers of children with other cancers. Thus, multiple
controls of different types can be valuable for exploring alternate hypotheses and for taking into account
possible potential biases, such as recall bias.

9
Matching:
It refers to the procedure whereby the controls are selected for each case on the basis of similarity with
respect to certain characteristics other than the exposure under investigation (since cases & controls are
similar on matching variables, their difference with respect to disease status may be attributable to
difference in some other factors). Common matching variables are age, sex, and ethnicity, place of
residence or S.E.S.

Group Matching

Group matching (or frequency matching) consists of selecting the controls in such a manner that the
proportion of controls with a certain characteristic is identical to the proportion of cases with the same
characteristic. Thus, if 25% of the cases are married, the controls will be selected so that 25% of that
group is also married. This type of selection generally requires that all of the cases be selected first.
After calculations are made of the proportions of certain characteristics in the group of cases, then a
control group, in which the same characteristics occur in the same proportions, is selected.

Individual Matching

A second type of matching is individual matching (or matched pairs). In this approach, for each case
selected for the study, a control is selected who is similar to the case in terms of the specific variable or
variables of concern. For example, if the first case enrolled in our study is a 45-year-old white woman,
we will seek a 45-year-old white female control. If the second case is a 24-year-old black man, we will
select a control who is also a 24-year-old black man. This type of control selection yields matched case-
control pairs; that is, each case is individually matched to a control.

Individual matching is often used in case-control studies that use hospital controls. The reason for this is
more practical than conceptual. Let us say that sex and age are considered important variables, and it is
thought to be important that the cases and the controls be comparable in terms of these two
characteristics. There is generally no practical way to dip into a pool of hospital patients to select a
group with certain sex and age characteristics. Rather, it is easier to identify a case and then to choose
the next hospital admission that matches the case for sex and age. Thus individual matching is most
expedient in studies using hospital controls.

Matching must be restricted to confounding variable

Concepts of confounding variable:

1) Variables that are known to be associated with both the disease & exposure

10
 2) Distributed unequally in the study & control group.
3) It is independently a risk factor for the disease.

Example: OCP OVARIAN CANCER

AGE (confounding factor)

Overmatching:

When controls are similar to the cases for a characteristic & when this similarity tends to mask the
disease association with the exposure of interest then cases & controls are said to be overmatched.

1) Variables intermediate in the causal pathway between the study factor & the disease should not
be matched
Example:
Hepatitis B Chronic liver disease Liver cancer
If cases & controls are matched for chronic liver disease then effect of virus on the occurrence of
liver cancer would be underestimated.

2) Factors should not be matched that are related to the suspected cause but not to the disease.
Example:
Smoking Lung cancer

Alcohol

If matching is done with respect to alcohol intake (usually smoking levels are positively correlated with
alcohol intake) hence matching for alcohol in this e.g., though alcohol is correlated to smoking & is not
an independent risk factor, will result in overmatching, because controls would be made similar to cases
not only their relation to alcohol but even to smoking also which is the exposure of interest.

11
Hence caution should be exercised while determining the number of variables selected for matching,
when the role of variable is in doubt , the preferable strategy is not to match but to adjust for it in
statistical analysis.

Comparability:

If the data are incomplete or inaccurate, spurious differences may be introduced between cases &
controls only if the inaccuracy or incompleteness affects the two groups to a different degree.
Example: Intake of a drug during 1st trimester of pregnancy
If the proportion of cases & controls recall to the same extent is acceptable but if the recall is higher
among cases compare to controls will lead to erroneous result among cases.

Bias in case control study

A bias is a systematic error in the design conduct or analysis of a study that results in an erroneous
conclusion
There are 3 broad categories of biases

Selection bias:

1) If women with OCP use are more likely than non users to examine their breast by a physician or
undergo mammography diagnostic bias may be introduced. If a positive association is found in
the study between OCP use & breast cancer, it may be just due to the fact that OPC user are
more investigated & therefore more likely to be diagnosed with breast cancer than non users.
.
2) A study measuring protective effect of BCG against leprosy, all newly diagnosed cases were
included, for each case an age & sex matched control was obtained from the same community.
School children are surveyed annually for leprosy: thus if school child developed leprosy , he or
she is more likely to be diagnosed than a non school going child. Furthermore a school child is
more likely to have had BCG vaccination, for these reason the study may underestimate the
protective effect of BCG. When cases are obtained from clinic & controls from community often
encounter this type of bias called surveillance bias.

3) If the exposure factor affects the duration of the disease, choosing prevalent casers results in a
biased study. e.g. Smoking increases the risk of MI. suppose smokers who develop MI are more
likely to die quickly , then the case control study using surviving cases of MI(prevalent cases)
alone would result in a lower estimate of relative risk this type of bias is referred to as incidence-
prevalence bias also called as Neymans fallacy

12
Information bias

1) If one were studying the use of certain drugs & congenital abnormalities , one must be aware that
the mother of the affected child is more likely to remember the details of her antenatal period
than the mother of an unaffected child .The former has been going through a recapitulative
process since the birth of her child . This is often called a Recall Bias.
2) When one use surrogates information for the dead cases, one may encounter Reporting Bias.
3) When interviewer is pervasive in questioning case as compared to controls this is called
Interviewer Bias

4) Misclassification bias

i) Nondifferential misclassification: exposure or disease status classification is independent of

each other. This leads to diluting the odds ratio, value nears to 1, even when true difference
exists
ii) Differential classification: exposure or disease classification is dependent on the other. odds
ratio may either inflate or deflate

Confounding bias:

In epidemiological study if one finds an association between two variable one needs to bear in mind the
possibilty of being confounded by third variable . a case control study on the asssociation between
alcohol intake & lung cancer can thus be confounded by smoking .
confounding can be avoided by matching for confounder or its effect can be removed during analysis
with appropriate adjustment.

Analysis in case control study :

THE ODDS RATIO (RELATIVE ODDS)

To calculate a relative risk, we must have values for the incidence of the disease in the exposed and the
incidence in the nonexposed, as can be obtained from a cohort study. In a case-control study, however,
we do not know the incidence in the exposed population or the incidence in the nonexposed population
because we start with diseased people (cases) and nondiseased people (controls). Hence, in a case-
control study we cannot calculate the relative risk directly. In this section we shall see how another
measure of association, the odds ratio, can be obtained from either a cohort or a case-control study and
can be used instead of the relative risk. We will also see that even though we cannot calculate a relative
risk from a case-control study, under many conditions, we can obtain a very good estimate of the
relative risk from a case-control study using the odds ratio.

The concept of odds.

13
Suppose we are betting on a horse named Epi Beauty, which has a 60% probability of winning the race
(P). Epi Beauty therefore has a 40% probability of losing (1 - P). If these are the probabilities, what are
the odds that the horse will win the race? To answer this we must keep in mind that the odds of an event
can be defined as the ratio of the number of ways the event can occur to the number of ways the event
cannot occur.

Consequently, the odds of Epi Beauty winning, as defined above, are as follows:

Odds= P of Epi beauty will win the race/ P of Epi beauty will lose the race

Recall that, if P is the probability that Epi Beauty will win the race, 1 - P equals the probability that

Epi Beauty will lose the race. Consequently, the odds of Epi Beauty winning are:

Odds= P/1-P or 60%/40% = 1.5

It is important to keep in mind the distinction between probability and odds. In the above example: P of
winning is 60% & an odds of winning is 1.5

The Odds Ratio in Cohort Studies

Disease devloped Do not devlop disease

Exposed A B
Not exposed C D

OR= odds that a exposed person will develop the disease / odds that the unexposed person will develop
the disease

OR= A/B/C/D =AD/BC

Just as the ratio of the incidence in the exposed to the incidence in the nonexposed can be used to
measure an association of exposure and disease, we can also look at the ratio of the odds that the disease
will develop in an exposed person to the odds that it will develop in a nonexposed person. Either
measure of association is valid in a cohort study.

14
In a cohort study, to answer the question of whether there is an association between the exposure and the
disease, we can either use the relative risk discussed in the previous section or we can use the odds ratio
(also called the relative odds). In a cohort study, the odds ratio is defined as the ratio of the odds of
development of disease in exposed persons to the odds of development of disease in nonexposed persons,
and it can be calculated as follows: OR= A/B/C/D =AD/BC

The Odds Ratio in a Case-Control Study

In a case-control study, we cannot calculate the relative risk directly to determine whether there is an
association between the exposure and the disease. This is because, having started with cases and controls
rather than with exposed and nonexposed persons, we do not have information about the incidence of
disease in exposed versus nonexposed persons. However, we can use the odds ratio as a measure of the
association between exposure and disease in a case-control study, but we ask different questions: “What
are the odds that a case was exposed?”

cases controls
History of A B
exposure
No history of C D
exposure

Looking at the left-hand column in Figure, we see that the odds of a case having been exposed are A:C
orA/C . Next, we ask, “What are the odds that a control was exposed?” Looking at the right-hand
column, we see that the odds of a control having been exposed are B:D or B/D.

We can then calculate the odds ratio, which in a case-control study, is defined as the ratio of the odds
that the cases were exposed to the odds that the controls were exposed. This is calculated as
follows:A/C/B/D = AD/BC

Thus, interestingly, AD/BC represents the odds ratio (or relative odds) in both cohort and case-control
studies. In both types of studies, the odds ratio is an excellent measure of whether a certain exposure is
associated with a specific disease. The odds ratio is also known as the cross-products ratio, because it
can be obtained by multiplying both diagonal cells in a 2 × 2 table and then dividing AD/BC

When Is the Odds Ratio a Good Estimate of the Relative Risk?

In a case-control study, only the odds ratio can be calculated as a measure of association, whereas in a
cohort study, either the relative risk or the odds ratio is a valid measure of association. However, many
people are more comfortable using the relative risk, and this is the most frequently used measure of
association reported in the literature when results of cohort studies are published. Even when the odds

15
ratio is used, people are often interested in knowing how well it approximates the relative risk. Even
prestigious clinical journals have been known to publish reports of case-control studies and to label a
column of results as relative risks. Having read the discussion in this chapter, you are aghast to see such
a presentation, because you now know that relative risks cannot be calculated directly from a case-
control study! Clearly, what is meant is an estimate of relative risks based on the odds ratios that are
obtained in the case-control studies.

When the odds ratio (relative odds) is obtained in a case-control study a good approximation of
the relative risk in the population?

When the following three conditions are met:

1. When the cases studied are representative, with regard to history of exposure, of all people with the
disease in the population from which the cases were drawn.

2. When the controls studied are representative, with regard to history of exposure, of all people
without the disease in the population from which the cases were drawn.
3. When the disease being studied does not occur frequently

Example : When Disease is Rare

Disease devloped Do not devlop disease

Exposed 200 9800
Not exposed 100 9900

RR=200/10000/100/10000 =2

OR=200*9900/9800*100 = 2.02
The odds ratio is a good estimate of the relative risk when a disease is infrequent

Example : When Disease in not Rare

Disease devloped Do not devlop disease

Exposed 50 50
Not exposed 25 75

16
RR= 50/100/25/100 =2

OR=50*75/50*25 = 3

The odds ratio is not a good estimate of the relative risk when a disease is not infrequent

Remember

• The relative odds (odds ratio) is a useful measure of association, in and of itself, in both
case-control and cohort studies.
• In a cohort study, the relative risk can be calculated directly.
• In a case-control study, the relative risk cannot be calculated directly, so that the relative
odds or odds ratio (cross-products ratio) is used as an estimate of the relative risk when the
risk of the disease is low.

Calculating the Odds Ratio in a Matched-Pairs Case-Control Study

As discussed earlier, in selecting the study population in case-control studies, controls are often
selected by matching each one to a case according to variables that are known to be related to
disease risk, such as sex, age, or race (individual matching or matched pairs). The results are then
analyzed in terms of case-control pairs rather than for individual subjects.

What types of case-control combinations are possible in regard to exposure history? Clearly, if
exposure is dichotomous (a person is either exposed or not exposed), only the following four types
of case-control pairs are possible:

Concordant pairs 1. Pairs in which both the case and the control were exposed

2. Pairs in which Pairs in which both neither the case nor the control
was exposed

17
 Discordant pairs 3. Pairs in which the case was exposed but the control was not

4. Pairs in which the control was exposed and the case was not

Note that the case-control pairs that had the same exposure experience are termed concordant
pairs, and those with different exposure experience are termed discordant pairs. These possibilities
are shown schematically in the following 2 × 2 table. Note that unlike other 2 × 2 tables that we
have examined previously, the figure in each cell represents pairs of subjects (i.e., case-control
pairs), not individual subjects. Thus, the following table contains a pairs—in which both the case
and the control were exposed; b pairs—in which the case was exposed and the control was not; c
pairs—in which the case was not exposed and the control was exposed; and d pairs—in which
neither the case nor the control was exposed.

Control
Exposed Not Exposed
Case Exposed a b
Not Exposed c d
Calculation of the odds ratio in such a matched-pair study is based on the discordant pairs only (b
and c). The concordant pairs (a and d, in which cases and controls were either both exposed or both
not exposed) are ignored, because they do not contribute to our knowledge of how cases and
controls differ in regard to past history of exposure.

The odds ratio for matched pairs is therefore the ratio of the discordant pairs (i.e., the ratio of the
number of pairs in which the case was exposed and the control was not, to the number of pairs in
which the control was exposed and the case was not). The odds ratio for the preceding 2 × 2 table
is as follows:odds ratio for matched pair is as follows=b/c

Advantage & disadvantage of case control study

Advantages

1. Quicker, cheaper and require less time and effort than cohort studies
2. Case-control studies can study rare diseases
3. Case-control studies can study multiple risk factors/exposures
4. They are useful for studying outcomes (diseases) that take a long time to develop, e.g. cancer
5. No risk to subjects
6.No attrition problem
7.Ethical problems are minimal

18
 Subgroup
selected as
controls

Disadvantages

1. Case-control studies are prone to selection and recall bias (i.e. better recollection of exposure amongst
cases than among controls
2. They are inefficient for examining rare exposures
3. It may be difficult to establish temporality (when the person was actually exposed to the disease/risk
factor)
4. It can be difficult to choose an appropriate control group
5. Unlike cohort studies, case-control studies cannot calculate incidence rates, relative risks or
attributable risks. Instead odds ratio are the measure of association used (when outcome is uncommon,
e.g. most cancers, it can be a good proxy for the true relative risk)

CASE-CONTROL STUDIES BASED IN A DEFINED COHORT

The general design is shown schematically in Figure below.

Initial data & /or Serum,
Defined Cohort Urine or Other
specimens Obtained
Years

Have not
developed disease
Developed
disease

Cases

19
 Case- control study
Design of a case-control study initiated within a cohort.

In this type of study, a population is identified and followed over time. At the time the population is
identified, baseline data are obtained from records or interviews, from blood or urine tests, and in other
ways. The population is then followed for a period of years. For most of the diseases that are studied, a
small percentage of study participants manifest the disease, whereas most do not. As seen in the above
Figure a case-control study is then carried out using as cases persons in whom the disease developed and
using as controls a sample of those in whom the disease did not develop.

Such cohort-based case-control studies can be divided into two types largely on the basis of the
approach used for selecting the controls.

These two types of studies are called nested case-control studies and case-cohort studies.

Nested Case-Control Studies

In nested case-control studies the controls are a sample of individuals who are at risk for the disease at
the time each case of the disease develops. This is shown schematically in Figure below.

Defined Cohort

Developed Have not developed

disease disease

Time

1yr

2yr

3yr
20
4yr

5yr
 5 Cases

Design of a hypothetical nested case-control study: Steps in selecting cases and

controls

Above figure shows the starting point as a defined cohort of individuals. Some of them develop the
disease in question but most do not. In this hypothetical example, the cohort is observed over a 5-year
period. During this time, 5 cases develop—1 case after 1 year, 1 after 2 years, 2 after 4 years, and 1 after
5 years.

. At the end of 5 years, 5 cases have appeared and at the times the cases appeared a total of 5 controls
were selected for study. In this way, the cases and controls are, in effect, matched on calendar time and
length of follow-up. Because a control is selected each time a case develops, a control who is selected
early in the study could later develop the disease and become a case in the same study.

Case-Cohort Studies

The second type of cohort-based case-control study is the case-cohort design seen in Figure below. In
the hypothetical case-cohort study seen here, cases develop at the same times that were seen in the
nested case-control design just discussed, but the controls are randomly chosen from the defined cohort
with which the study began. This subset of the full cohort is called the subcohort. An advantage of this
design is that because controls are not individually matched to each case, it is possible to study different
diseases (different sets of cases) in the same case-cohort study using the same cohort for controls. In this
design, in contrast to the nested case-control design, cases and controls are not matched on calendar time
and length of follow-up; instead, exposure is characterized for the subcohort. This difference in study
design needs to be taken into account in analyzing the study results.

Defined Cohort

Developed
disease

Time

1yr
5 Controls
2yr

3yr
21
4yr

5yr
 Design of a hypothetical case-cohort study: Steps in selecting cases and controls

Advantages of Embedding a Case-Control Study in a Defined Cohort

1) Interviews are completed or certain blood or urine specimens are obtained at the beginning of the
study (at baseline), the data are obtained before any disease has developed. Consequently, the
problem of possible recall bias discussed earlier in this chapter is eliminated.
2) If abnormalities in biologic characteristics such as laboratory values are found, because the
specimens were obtained years before the development of clinical disease, it is more likely that
these findings represent risk factors or other premorbid characteristics than a manifestation of early,
subclinical disease. When such abnormalities are found in the traditional case-control study, we do
not know whether they preceded the disease or were a result of the disease.
3) Study is often more economical to conduct. One might ask, why perform a nested case-control
study? Why not perform a regular prospective cohort study? The answer is that in a cohort study of,
say, 10,000 people, laboratory analyses of all the specimens obtained would have to be carried out,
often at great cost, to define exposed and nonexposed groups. In a nested case-control study,
however, the specimens obtained initially are frozen or otherwise stored. Only after the disease has
developed in some subjects is a case-control study begun and the specimens from the relatively
small number of people who are included in the case-control study are thawed and tested. But
laboratory tests would not need to be performed on all 10,000 people in the original cohort. Thus the
laboratory burden and costs are dramatically reduced.
4) In both nested case-control and case-cohort designs, cases and controls are derived from the same
original cohort, so there is likely to be greater comparability between the cases and the controls than
one might ordinarily find in a traditional case-control study. For all of these reasons, the cohort-
based case-control study is an extremely valuable type of study design.

Conclusion:
The Case Control study methodology has been subjected to scrutiny & criticism at various times since
1930. However form the discussions that have been ensured Case Control Studies are a reliable
methodology when executed with due care, hopefully the modern advances in medicine &
epidemiological methods would strengthen the use of this wonderful tool.

22
References:

1) Silvia .I, Cancer Epidemiology: Principles and Methods. International Agency for Research on
Cancer ,Lyon, France.1999
2) Park K. Park’s Textbook of Preventive and Social Medicine,20th edition. Jabalpur:Banarsidas
Bhanot;2009.
3) Raymond S, Greenberg, Ibrahim M. The case- control study .In: Walter.W, Detels.H, Knox.G.
editors.Oxford Textbook of Public Health. 2nd edition. New York: Oxford Medical Publications;
2nd vol, 1991.
4) Bhalwar R editor.Textbook of Public Health and Community Medicine.1st edition. Pune:
Department of community medicine AFMC; 2009.
5) Gordis L.Epidemiology, 4th edition. Philadelphia: Saunders Elsevier; 2008.
6) Sherry L editor. Epidemiology in medicine.1st edition. Boston: Little Brown and Company;1987.
7) Macmohan B. Epidemiology Pinciples and Methods,1st edition. Boston: : Little Brown and
Company;1970.
8) Hulka BS, Hogue OR, Greenberg BG. Methodologic issues in epidemiologic studies of
endometrial cancer and exogenous estrogen. Am J Epidemiol 1978;107;267-76
9) Prakash J,Notes on Case Control Study .CMC Vellore.

23