CASE CONTROL STUDY - PowerPoint PPT Presentation

Loading...

PPT – CASE CONTROL STUDY PowerPoint presentation | free to download - id: 3d3ec1-MzBmN



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

CASE CONTROL STUDY

Description:

CASE CONTROL STUDY * * * * Differences: Prospective retrospective Randomized not randomized Baseline defined no baseline defined Examining the outcome ... – PowerPoint PPT presentation

Number of Views:18
Avg rating:3.0/5.0
Slides: 41
Provided by: etdcTums
Learn more at: http://etdc.tums.ac.ir
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: CASE CONTROL STUDY


1
CASE CONTROL STUDY
2
Case-control study
Exposure Disease () ? -------------------
-------------------------
Exposure Disease (-) ? -------------------
-------------------------
Investigator
3
Case control study
4
Type of studies
5
Source population
Exposed
Unexposed
6
Source population
Exposed
Cases
Unexposed
7
Source population
Exposed
Sample
Cases
Unexposed
Controls
8
Source population
Cases
Exposed
Sample
Unexposed
Controls Sample of the denominator Representat
ive with regard to exposure
Controls
9
Cases Controls Exposed a b Not
exposed c d Total a c b d
exposed a/(ac) b/(bd)
10
(No Transcript)
11
CASE-CONTROL STUDIES
  • Basic Idea
  • Cases Should represent all cases in the
    population
  • Controls Should represent all persons without
    disease in the population

12
CASE-CONTROL STUDIES
Sample
Population
13
Case control study
Exposure
? ?
Disease Controls
Retrospective nature
14
Two types of case control studies
  • Exploratory New disease New risk
    factors Several exposures "Fishing
    expedition
  • Analytical Precise a single
    hypothesis Dose response

15
REVIEW
  • A design used to assess the relationship between
    the exposure to a risk factor and the development
    of a disease
  • It compares the exposure distributions between
    the groups of patients with and without the
    disease.
  • It typically uses only a fraction of the subjects
    in the non-disease group.

16
Randomized Clinical Trials vs. Case-Control
Studies
Randomization
Exposure
Patients in Baseline State
Outcome Event
No Exposure
Patients with Disease
Exposure History
Patients without Disease
17
Characteristics of the Design
  • Retrospective
  • No randomization
  • Population at risk is often undefined
  • Ascertainment of exposure history

18
Implementation a Case-Control Study Practical
Issues
  • Selecting a study base representative of the
    intended population
  • Defining the disease
  • Choosing the cases and controls
  • Exclusion criteria
  • Ascertainment of exposure

19
Selection of the Study Base
  • Hospital based case-control studies The study
    base is the collection of clinical records of the
    participating hospitals.
  • Berksons Bias Cases and controls experience
    different hospital admission rates.
  • Population based case control studies The Study
    base is the collection of subjects who would
    become cases if they develop diseases.
  • Neymans Bias Case group not representative of
    the intended population.

20
Diagnostic Criteria and Case Selection
  • Diagnostic criteria unambiguous definition under
    equal diagnostic surveillance.
  • Sources of cases
  • Persons with the disease seen at a care facility
    in a specified period of time.
  • Persons with the disease in a more general
    population in a period of time.

21
Selection of Controls Basic Principles
  • True Representation of the Study Base The
    controls should be selected so that they truly
    represent the distribution of exposure in the
    study base from which the cases are selected.
  • Comparable Accuracy There should be no
    differential misclassification between the two
    groups.

22
CASE-CONTROL STUDIES
  • Sources of Cases and Controls
  • Population-Based
  • Cases from Registry (fed by population)
  • Controls from General Population
  • Hospital-Based
  • Cases - selected group that made it to hospital
  • Controls as above

23
Selection of ControlsSources
  • The controls should be drawn from the population
    of which the cases represent the affected
    individuals.
  • Sampling Frames
  • Population of an administrative area (eg. HMOs)
  • Hospital patients
  • Difference with target population
  • Cost effective
  • Relatives of the cases (spouses and siblings)
  • Associates of the cases (neighbors, co-workers,
    etc)

24
Matching
  • Frequency matching
  • Individual matching

25
Matching
  • Advantages
  • Sometimes the only way of control of some
    confounding in certain situations
  • Increasing power
  • Straightforward way to obtain a comparable group

26
Matching
  • Disadvantages
  • Some time impossible
  • Association between matching variable and the
    outcome cant be assessed
  • Not possible to assess theadditive interaction
    between matching variable and exposure
  • Increased int validity may result in reduced ext.
    validity
  • Considering OVERSTIMATION not highcorrelation
    between the variable of interest and matching
    variable
  • eg matching ethnic background
  • No statistical power is gained if the matched
    variable is a weak confounder

27
Selection of ControlsSampling Schemes
  • Total population no sampling
  • Random and systematic sampling
  • Matching deliberately select the controls in
    such a way as to make them similar to the cases
    with respect to certain confounding variables.
  • Multiple control groups.

28
Multiple controls
  • Similar
  • different

29
Exclusion Criteria
  • Exclusion criteria should not alter the exposure
    rate in one of the two groups.
  • Examples
  • Low-level lead exposure and mental
    retardation-children with lead related diseases
    were excluded from the control group
  • Reserpine and breast cancer-patients with
    thyrotoxicosis, renal disease, and cardiovascular
    diseases were excluded from the control group.

30
Information on Exposure
  • The most common sources of information on
    exposure are patients (or parents, in the case of
    children).
  • Other sources include relatives, hospital
    records, employment records, etc.
  • When information is obtained via interviews,
    recall bias is often a concern.

31
Information on ExposureComparability and
Validity
  • Comparability If the inaccuracy in exposure
    reporting affects the two groups to a different
    degree, the study may yields questionable
    conclusions.
  • Validity The information on exposure reflects
    the true level of exposure.

32
(No Transcript)
33
(No Transcript)
34
(No Transcript)
35
(No Transcript)
36
Bias?
37
  • Long latency period of disease
  • Controls should be selected independent of
    exposure
  • Controls neighbor
  • Other hospital wards
  • Phone book
  • Friends

38
Advantage and disadvantages
39
Case control studies
  • epidemiologists use them to study a huge variety
    of associations.
  • more frequently than other analytical studies

40
Case control studies
  • Advantages
  • Rare diseases
  • Several exposures
  • Long latency
  • Rapidity
  • Low cost
  • Small sample size
  • No ethical problem
  • Efficient, cost-effective for rare outcomes

41
Strengths of the Case-Control Study Design
  • It is less constrained by the natural frequency
    of the disease
  • It greatly shortens the waiting time required by
    cohort studies
  • It can be used when an RCT is not logistically or
    ethically feasible.
  • Efficiency, low cost, fewer practical restrictions

42
(No Transcript)
43
Case control studies
  • Disadvantages
  • Selection bias
  • Measurement of exposure information
  • Control of confounding factors
  • Not suitable for rare exposure
  • ? Sequence of events ?
  • Only one outcome
  • Does not yield incidence or relative risk
    (although in some cases these can be inferred
    using external information)
  • BIAS

44
Limitations of case-control studies
  • Cannot compute directly relative risk
  • Not suitable for rare exposure
  • Temporal relationship exposure-disease difficult
    to establish
  • Biases
  • control selection
  • recall biases when collecting data
  • Loss of precision due to sampling

45
Weaknesses of the Case-Control Study Design
  • Less well defined target population
  • Concerns of various types of selection biases
  • Lack of causal interpretation due to the
    existence of confounding factors
  • No absolute measure for the exposure effect on
    the disease

46
Effects
47
INCIDENCE or PREVALENCE DISEASE or
EXPOSURE Intuitively if the frequency of
exposure is higher among cases than
controls then the incidence rate will probably
be higher among exposed than non exposed.
48
Distribution of cases and controls according to
exposure in a case control study
Cases Controls Exposed a b Not
exposed c d Total a c b d
exposed a/(ac) b/(bd)
49
Distribution of myocardial infarction cases and
controls by amount of physical activity
Physical Myocardial activity Infarction Control
s gt 2500 Kcal 190 230 lt 2500
Kcal 176 136 Total 366 366
exposed 51.9 62.8
50
Volvo factory, Sweden, 3000 employees, Cohort
study 200 cases of gastroenteritis
Water Cases Controls Consumption YES
150 ? NO 50 ? Total
200 200
51
Probability that an event will
happen Odds Probability that the even will
not happen
Probability that an event will
happen Odds 1 - (Probability that the event
will happen)
52
Case control study
Odds of exposure among cases Probability to be
exposed among cases Probability to be unexposed
among cases a / (ac) Odds Ecases
------------ a / c c / (ac) Odds of
exposure among controls Probability to be
exposed among controls Probability to be
unexposed among controls b/ (bd) Odds
Econtrols ------------ b / d d/
(bd)
Cases Controls Exposed a b Not
exposed c d Total a c b d
a/c OR ---- ad / bc b/d
53
CASE-CONTROL STUDIES
  • BASIC IDEA
  • Is the risk factor more common among cases than
    controls?

100 100
RF PREVALENCE FOR CASES 50/10050 RF
PREVALENCE FOR CONTROLS 20/10020 PREVALENCE
RATIO 50 / 20 2.5
54
CASE-CONTROL STUDIES
  • BASIC IDEA
  • Is the risk factor more common among cases than
    controls?

ODDS FOR CASES 5050 1 ODDS FOR CONTROLS
2080 0.25 ODDS RATIO 5050/2080
1/0.25 4
55
  • RR isnt possible to calculate in case control
    study
  • OR is calculated
  • OR is representative of RR if
  • Cases are representative
  • Controls are representative
  • Disease prevalence is rare

56
CASE-CONTROL STUDIES
Disease () (-)
Relative Risk
()
For rare diseases, a is small compared to b, and
c is small compared to d. So. . . . .
Exp
(-)
Relative Risk
57
CASE-CONTROL STUDIES
  • Method Population-based
  • Prospective case-control
  • Cases All incident cases of
    childhood (lt15 yo) cancer in Denver
    registry, 1976-1983
  • Controls Random-digit dialing match on
    sex, age 3y

58
CASE-CONTROL STUDIES
Results
Brain Cancer
Case Odds 11/34 0.32 Control Odds 31/175
0.18 Odds Ratio 0.32/0.18 1.8
Case
Control
()
Electric Blanket
(-)
(95 CI 0.9 4.0)
59
Analytical Issues
  • Association vs Causal relationship.
  • Adjustment of confounders
  • Matching
  • Model based adjustment (regression, etc)
  • Propensity score method
  • A common limitation of the adjustment cannot
    account for the effects of the unobserved
    confounders.

60
Assessment of the Effect of the Exposure
61
Relative Risk and Odds Ratio
  • For a RCT, we report the relative risk
  • For a Case-Control study, we report the odds
    ratio
  • RR and OR

62
Final Thoughts
  • Thoughtful design and careful implementation.
  • Reducing biases of various kinds.
  • The workhorse of the case-control data analysis
    is logistic regression.
  • Reporting a case-control study.

63
Nested case control
About PowerShow.com