Case ControlStudies[1]

8/14/2019 Case ControlStudies[1]

1/53

Case-control

studies


2/53

This version is made for bilingual

teaching .Case-control study is an essential

research design of Epidemiology, which

involves identifying patients who have the

outcome of interest (cases) and control

patients who do not have that same outcome,and looking back to see if they had the

exposure of interest. The exposure could be

some environmental factor, a behaviouralfactor, or exposure to a drug or other

therapeutic intervention.


3/53

Select Study Design toMatch the Research Goals

Objective Design

Description of disease or spectrum Case series or reportCross-sectional study

Determine operating characteristics

of a new diagnostic test

Cross-sectional

Describe prognosis Cohort study

Determine cause-effect Cohort studyCase-control study

Compare new interventions Randomized clinical trial

Summarize literature Meta-analysis


4/53

Case-Control Studies

Introduction

Matching

Investigate Example Design of Case-Control Studies

Data collection and analysis

Bias Strengths and Weaknesses

Several important features

E P I D E M I O L O G Y A N D

H E A L T H S T A T I S T I C S

1 9 5 7


5/53

Introduction

Historical Perspective

Definition Types of Design



1 9 5 7


6/53

Unique contribution of epidemiology to the repertoire

of clinical research designs

First case-control study performed in late 1950s Doll and Hills study of lung cancer and smoking behavior

among physicians

Jerome Cornfields classic description of

Retrospective Studies

New statistical tools were developed to analyze the

study design - logistic regression

Historical Perspective

n


7/53

Definition A case-control study is a design in whichindividuals with an event or condition of

interest, CASES, are identified and thencompared with regard to one or more exposuresto individuals without the event or condition ofinterest, CONTROLS. Case-control

investigations typically are designed to assessthe association between occurrence of diseaseand an exposure suspected of causing (or

preventing) that disease.

n


8/53

a

b

c

d

Cases

Controls

Direction of inquiry

Exposed

Exposed

Unexposed

Unexposed

a/(a+c)

b/(b+d)

n


9/53

Types

Family of epidemiological study designs

Traditional case-control design Case-control studies within cohorts

Nested case-control study design Case-cohort study design

Case-parent study design Case-only study design



1 9 5 7

n


10/53

Matching

Summarize

Types

Problems with Matching



1 9 5 7


11/53

Matching is defined as the process of selecting

controls so that they resemble the cases with

regard to certain characteristics

The goal of matching is to create similar

distributions between cases and controls with

regard to certain characteristics

Matching can be used to Adjust for potential confounding factors

Increase precision of estimate

g

Summarize


12/53

Individual level matching For each case in the study, one or more controls

are selected with identical (similar)characteristics as the case

Frequency, or group, matching

Select controls so that the proportion with acertain characteristic is identical to theproportion of cases with that characteristic

g

TypesTypes


13/53

Difficult and expensive

Cannot evaluate the effect of controlled

variables May limit the ability to control for other

variables

Overmatching Controls resemble cases in terms of known and

unknown characteristics, some of which may be

associated with the disease

Problems with Matching

g


14/53


15/53

Example

BackgroundEMS was first recognized in October 1989, it

occurs predominantly in women and is relatively

rare. when astute physicians determined thatthree people with unexplained myalgias and

eosinophilia had consumed L-tryptophan. Prompt

response by health departments quickly led tocase-control studies,the results of which

suggested that ingestion of L-tryptophan was the

cause of EMS.


16/53

The Centers for Disease Control and Prevention(CDC)conducted a series of case-control studies in 1989 and1990.

One of the studies conducted in Minnesota, Researchersselected 63 case subjects of EMS in the metropolitanarea of Minneapolis-St.Paul.

Researchers randomly selected 5188 control subjects inthe same area.

Researchers interviewed subjects and asked abortpotential risk factors and about their use of L-tryptophan.

Example

Conduct


17/53

L-tryptophan was taken significantly more

frequently by cases than by controls 61 of

63 case subjects (97%),but only 101 of5188 control subjects (2%).

L-Tryptophan-containing products were

taken off the market in November1989,In1990,after the recall of L-tryptophan,the

number of reported cases fell to near zero.

Example

Results


18/53

Selection of Cases

Develop a case definition then identify new cases

within a specified time period Selection of Controls

The sample of controls should have the sameprevalence of exposure as the source population of

unaffected persons. Determination of Exposure

Design



1 9 5 7


19/53

Selection of Cases

n

Sources of cases Species of cases

Something important


20/53


21/53

Selection of Cases

Species of Cases

Newly diagnosed orincident cases

Previously existing orprevalent cases Incident cases preferred over prevalent cases in

most settings If prevalent cases chosen, then risk factors identified for

disease may be those related more to survival with

disease than disease occurrence. Survivorship bias also true for incident cases, but

minimized

n

n e ect on o ases


22/53

Specify the definition of a case The criteria should minimize the likelihood that

an affected person (true case) is missed (i.e,thecriteria must be sensitive).

A nonaffected person is falsely classified as a

case (i.e, the criteria must be specific).

n e ect on o ases

Something Important

n


23/53

Selection of Controls

Sources of controls

Multiple controls

Something important

n

n e ect on o ontro s


24/53

Hospital control group Hospitalized patients, best if chosen from the

same hospital as cases in order to control forunknown reference population

Select from all patients admitted to the

hospital

Select from specific diagnosis

n e ect on o ontro s

Sources of Controls (1)

e ec on o on ro sn


25/53

e ec on o on ro s

Sources of Controls (2)

Community control group Probability sample best, but not often

practical Select from school rosters, insurance

companies, etc.

Neighbors of cases Random digit dialing

Best friend

n

n


26/53

Multiple Controls

Controls of the same type May improve precision of the measure of

association Precision rarely improved with more than 5

controls per case

Controls of different types Hospital controls and community controls

per case

n


27/53


28/53

n


29/53

Determination of Exposure Exposure

Exposure is determined in a retrospective

manner, that is one must look back in timeto assess exposure status before a person

became a case.

Each individuals prior exposure to the riskfactor of interest

Other exposures

n


30/53

n


31/53

Exposure must be measured in a blinded

manner Data collectors must be unaware of whether

subject is a case or control

Data collectors should be unaware of the study

hypothesis

n

Determination of Exposure

Something Important(2)


32/53

ata collection and analysis


33/53

Collection of Data

Interviews and questionnaires

Information concerning risk factors may also

be obtained from medical,occupational,orother records.




34/53

Analysis of Data


Unexposed - c

Exposed - a

Population

at Risk

Exposed - b

Cases

Controls

Unexposed - d



35/53

The power of the study design lies in the

symmetry of the OR.

OR is the odds of exposure given disease dividedby the odds of exposure given no disease.

Remember that the odds of exposure among cases

compared with controls is the same as the odds of

disease among exposed and unexposed.


Odds Ratio



36/53

a+b+c+db+da+cTotal

a+b

c+d

b

d

a

c

Cases

Controls

TotalUnexposedExposed

Unmatched analysis

d)c)(bd)(ab)(c(anbc)(ad

++++

=

22




37/53

Unmatched analysis

)1.96/(1 2

OROR95%CI.

bc

ad

d

cba

exposurecontrolofOdds

exposurecaseofOddsOR

=

==

=




38/53

a+b+c+db+da+cTotal

c+ddcCase unexposed

a+bbaCase exposed

TotalControl

Unexposed

Control

Exposed

Case-control pairs that share the same exposure

status do not contribute to the estimate of risk.


Matched analysis



39/53

Matched analysis

cb

cb

+

=

22 )(

)1.96/(12

OROR95%CI.

cbOR

=

=




40/53

Analytic Strategy

Assess relationship/association between

Exposure and independent variables Case/Control status and independent variables

Calculate crude, or unadjusted, OR forexposure - case association Matched analysis required for matched studies




41/53

Analytic Strategy

Stratified analysis Calculate stratum-specific ORs for exposure-case

relationship Determine presence of confounding and interaction

Logistic regression analysis Regression technique used to adjust for confounding

and interaction Special logistic model applied in matched studies



42/53

Bias Introduction

Selection bias Information bias

Confounding



1 9 5 7

Bias


43/53

Introduction

Case-control studies are subject to bias and

confounding, both will distort the results of the

study Bias is defined as the deviation of results, or

inferences, from the truth, or processes leading to

such deviation.

There are about 75 different types of bias now

identified in published case-control studies

Bias

Bias


44/53

Selection Bias

Features Types

Bias

Bias


45/53

Features (1)

Selection bias reflects systematic errors that arise

from the way in which subjects are selected.

If the prior exposure of the cases studied differsfrom that of all cases arising from the source

population or if prior exposure of controls

differs from that of persons in the source

population without the disease or interest

selection bias may be present.

Bias


46/53

Features(2)

Preferential diagnosis of exposed cases may

lead to selection bias.

Low participation may lead to selectionbias.

Errors in sampling controls from the source

population can also create selection bias.

Bias


47/53

Types

Admission rate bias

Prevalence-incidence bias Detection signal bias

Time effect bias

Bias


48/53

Information Bias A distortion in measuring exposure or

outcome data that results in different quality

(i.e., accuracy or reliability) or frequency ofinformation between comparison groups. Recall bias

Confoumding bias

Bias


49/53

Confounding Bias Confounding is a distortion of results that occurs when

the apparent effects of the exposure of interest are

attributable entirely or in part to the effects of anextraneous variable.

Criteria for confounding Factor is associated with exposure

Factor is associated with disease in the absence of exposure

Factor is not in the causal path between exposure and outcome


50/53

Strengths and Weaknesses

Strengths

Rare disease Long latency between exposure

and disease

Explore multiple hypotheses Inexpensive



1 9 5 7


51/53

Weaknesses

Prone to bias Temporal relationships cannot be

established

Inefficient for rare exposures, unlessexposure often lead to disease

Strengths and Weaknesses


52/53

Several important features

The study provides an efficient means to studyrare diseases.Case-control studies tend to be morefeasible than other studies.

Case-control studies allow researchers toinvestigate several risk factors.

A single case-control investigation does notprove causality, but it can provide suggestiveevidence of a causal relationship that warrantsintervention by public health officials to reduceexposure to the implicated risk factor.



1 9 5 7


53/53

Case ControlStudies[1]

Documents