Docstoc

7251 Introduction to Cancer Epidemiology. Part III

Document Sample
7251 Introduction to Cancer Epidemiology. Part III Powered By Docstoc
					      Case-Control Study Design

   Two groups are selected, one of people with
    the disease (cases), and the other of people
    with the same general characteristics but
    without the disease (controls)

   Compare the past exposures of both groups


                                                   1
             Case Control Study Design


                                         Exposed
                      Diseased
                       (Cases)
                                         Not Exposed
   Target
Population
                                         Exposed
                    Not Diseased
                      (Controls)
                                     Not Exposed


                                                       2
         Case-Control Study Design

Limitations:

   Cannot yield incidence rates because
    subjects are selected on outcome

   An estimate of the ratio of incidence rates or
    risks (RR) is obtained by calculating an
    odds ratio (OR)

                                                     3
               Odds Ratio Calculation

                      Outcome
    Exposure       Cases        Controls
    Exposed          A             B
   Not Exposed       C             D


Odds of exposure for cases       A/C
                                           = Odds Ratio
Odds of exposure for controls    B/D       (estimates the
                                            relative risk)
                                                             4
Comparing Odds Ratios and Relative Risks

                  Outcome
   Exposure    Cases   Controls
   Exposed      70       300      370
 Not Exposed    30       700      730
                100     1000      1100


 OR = AD/BC = 5.44     RR = Ie/In = 4.41


                                           5
            Stating your results

   OR = 5.44
    Those with the disease are 5.44 times as
    likely to have had the exposure compared to
    those without the disease


   RR = 4.41
    Those with the exposure are 4.41 times as
    likely to develop the disease compared to
    those without the exposure

                                                  6
    Summary of Strengths and Limitations of
  Prospective Cohort and Case-Control Studies
   Prospective Cohort                  Case-Control
Strengths:                              Strengths:
 Opportunity to measure risk factors    Useful for rare disease
  before disease occurs                  Relatively inexpensive
 Can study multiple disease             Relatively quick results
  outcomes
 Can yield incidence rates as well   Limitations:
  as relative risk estimates           Possible bias in measuring risk
                                        factors after disease has
 Limitations:                           occurred
  Useful for rare disease             Possible bias in selecting control

  Relatively inexpensive
                                        group
                                       Identified cases may not
  Relatively quick results
                                        represent exposure of all cases
                                                                        7
Randomized Clinical Trials
        (RCT)

      The Gold Standard
        Cohort Study




                             8
   Schematic diagram of a clinical trial
        Study
      Population                                Non-participants
                                Participants


                            Randomization
    Treatment arm                              Control arm
    Intervention or                               Control
    new treatment


                                            Improved   Not Improved
Improved              Not
                Improved
                                                                      9
              Crossover Design
   Subjects are randomized to a sequence of
    two or more treatments

   Each subject serves as his own control

      Group   Sequence   Period 1   Washout   Period 2

        I       A,B         A                    B

        II      B,A         B                    A



                                                         10
                    Factorial Design
   Two or more treatments are evaluated
    simultaneously in the same set of subjects using
    varying combinations of treatments
                               Randomization




            Treatment A                        Placebo


      Treatment B    Placebo           Treatment B       Placebo



                                                                   11
How do we evaluate whether
cancer studies are valid?

Understand bias and confounding
      Testing for a true association

   Examine the methodology for bias

   Examine the analysis for confounding

   Examine the results for statistical significance




                                                       13
Examine the study design for Bias

   Selection Bias
       Errors in the process of identifying the
        study population and selecting the subjects



   Information/Observation Bias
       Errors in measurements of exposure or
        disease status

                                                      14
                Confounding

   Confounding is an apparent association
    between disease and exposure caused by a
    third factor not taken into consideration




                                                15
       Examples of Confounders

   Study A found an association between
    gambling and lung cancer. The study may
    be confounded by smoking.

   Study B found a larger crude death rate in
    Florida than in Alaska. The rate may be
    confounded by differences in the
    population age structure.
                                                 16
        Testing for Confounding
1. Calculate the crude rate

2. Calculate a rate adjusted for the confounding
  variable

3. Compare the two measures

    The two measures will be different if the variable
      is a confounder (in practice, when the crude and
      adjusted measures differ by at least 10%)
                                                          17
                                                   1980 U.S.    Expected
          Cancer     Population                    Standard     Number of
Age       Deaths       at risk       ASR
                                                                 Deaths
                                                  Population
            (1)        (2)      (1) / (2) = (3)      (4)        (3) x (4) = (5)
0-18         5        5,000     1.00 per 1000     60,500,000      60,500
19-64        10       25,000     0.40 per 1000 140,300,000        56,120
65+         100       15,000    6.67 per 1000     25,700,000     171,419
Total       115      45,000          xxx          226,500,000    288,039


            Crude Rate                          Age-Adjusted Rate
        (115 / 45,000) x 1000    Not equal (288,039 / 226,500,000) x 1000
           2.56 per 1,000                          1.27 per 1,000


 AGE IS A CONFOUNDER FOR DEATH FROM CANCER
                                                                              18
    Evaluating Statistical Significance

   The probability that you would get your results
    by chance alone is the p-value
   A low p-value ( < 0.05 ) says that chance is not
    likely to explain your results
   A 95% confidence interval (CI) is the range of
    values in which the true value will be found 95%
    of the time
   Large samples yield small confidence intervals
   Small samples yield large confidence intervals

                                                       19
                   Evaluating Results
        RR = 1: No difference in disease between
         exposed and unexposed groups
        OR = 1: No difference in exposure between
         cases and controls

       Examples:
           RR = 1.8 (1.6, 2.0) is statistically significant
           RR = 1.8 (0.8, 2.9) is not statistically significant
           OR = 0.7 (0.6, 0.8) is statistically significant
           OR = 0.7 (0.4, 1.2) is not statistically significant

                                                                   20
How do we assess whether
associations between cancer and
risk factors are causal?

Understand criteria for causality
                 To Show Cause

    Chronic disease and complex conditions
     require the use of Hill’s Postulates
1.   Strength of association      5.   Plausibility
2.   Consistency of               6.   Coherence
     association                  7.   Experiment
3.   Specificity of association   8.   Analogy
4.   Temporality
5.   Biologic gradient

                                                      22
How much of the morbidity and
mortality from cancer might be
prevented by interventions?

Understand the impacts of education
and screening programs
   Validity
                  Principles of Screening
       Sensitivity: correctly identify those with disease

       Specificity: correctly identify those without disease

       + Predictive Value: proportion of correct positive
        tests

       - Predictive Value: proportion of correct negative
        tests

   Reliability: ability of test to give consistent results

   Yield: amount of unrecognized disease brought to
    treatment due to screening
                                                                24
    Calculating Measures of Validity
                        True Diagnosis

 Test Result       Disease        No Disease     Total
      Positive           a            b          a+b
      Negative          c             d          c+d
      Total             a+c          b+d       a+b+c+d


Sensitivity = a/(a+c)        Positive Predictive Value = a/(a+b)
Specificity = d/(b+d)        Negative Predictive Value = d/(c+d)

                                                               25
Example: Breast Cancer Screening
Mammogram
  Results      Disease      No Disease            Total

  Positive            132           983           1,115
  Negative             45         63,650      63,695
   Total              177         64,633      64,810

  Sensitivity = 132/177 = 74.6%
  Specificity = 63,650/64,633 = 98.5%
  Positive Predictive Value = 132/1,115 = 11.8%
  Negative Predictive Value = 63,650/63,695 = 99.9%
                                                          26
            Keys to Screening
   Sensitivity: detect a sufficient number of
    preclinical cases to be useful
   Prevalence: screen high-risk populations
   Frequency: one-time screening does not allow
    for differences in individual risk or differences
    in onset
   Participation: tests unacceptable to the target
    population will not be utilized
   Follow-up: those with positive tests need to be
    provided with a plan of action
                                                        27
Advice for Reading the Literature
   Identify the study design
   Understand how subjects are selected
   Understand how exposure is defined
   Evaluate potential bias and confounding
   Determine if the statistical evaluation is
    appropriate
   Make decisions about whether the outcome
    measures are statistically significant and/or
    clinically important
   Use good judgment
                                                    28
End

				
DOCUMENT INFO
Shared By:
Categories:
Stats:
views:39
posted:4/10/2008
language:English
pages:29