《casecontrolstudy》由会员分享，可在线阅读，更多相关《casecontrolstudy（46页珍藏版）》请在金锄头文库上搜索。
1、Case-Control Study（病例对照研究）病例对照研究）A study starts with the identification of persons with the disease of interest and a control group of persons without the disease, to measure the association between the exposure and the disease by comparing the diseased and non-diseased with regarded to how frequent
2、ly the exposure present.1. Basic ConceptsExposureStudy subjects contact with or possession of acharacteristic or factor that is suspected to influence the risk of developing a particular disease.Direction of Investigate casescontrols compare number exposure disease Onset of study acbda/(a+c) b/(b+d)
3、 Figure. Schematic diagram of case-control study basic principle 2.Type of Design Unmatched Matchedfrequency matchingindividual matchingUnmatched The number of controls should be equal cases or more than case. In addition, have no other any restricts.MatchedMatching is the process of selecting the c
4、ontrols so that they are similar to the cases in certain characteristics, such as age, sex, race, occupation, etc. Matching may be two types: frequency matching individual matching Frequency Matching (group matching) Frequency matching consists of selecting the controls in such a manner that the pro
5、portion controls with a certain characteristics is identical to the proportion of cases with the same characteristics. Such as, if 50% of the case are female, the controls will be selected so that 50% of that group is also female. Individual Matching The first is to identify a case. Then select from
6、 the source population one or more controls who have the same values that the case has for each matching factor. To match on a binary variable such as sex can match directly. To match on a continuous variable such as age, it is typical1y necessary to form categories, such as 5-year intervals. If a c
7、ontrol be matched one case called the ratio of one to one matching, 1:1matching (matching pair ). If a case matched more than one controls called the ratio of one to R matching, 1:R (1:M) matching. The ratio of controls to cases rarely exceeds 4:1 by Pitman Formula ,because additional controls beyon
8、d this ratio add relatively little to the statistical power of the study. Why match? To reduce likelihood of confoundingIncrease the study efficiency Once you match on a characteristic, you can not study its effect.Over-matching.Match what? Possibly confounding factorsMatch variable Age, gender, etc
9、.Disadvantage3.ExampleA case-control study on mothers use of diethylstilbesterol during gestation and adenocarcinoma of the vagina in daughters.Dr.Herbst was a gynecologist of the Vincent Memorial Hospital ,in Boston, USA. He found seven patient with vaginas adenocarcinoma of the hospitalization tre
10、atment from 1966 to 1969. The patients were all 15-22 year old young girls. Usually the vagina cancer was 2% that the female reproductive system, but the vagina adenocarcinoma was 5-10% of the vagina cancer, very rare. In the past, the patients age was usually older than 25 years old, but that 7 cas
11、es were 15 to 22 years old. BackgroundStepThe Herbst explored on risk factors of the vagina adenocarcinoma.Seven cases plus the one patient of another hospital made up of case group.4 controls be matched to each case, total 32 controls.Investigators used the standard questionnaire investigated the c
12、ases and controls and their mothers. The comparison of the main exposure factor of mother of cases and controlsCaseMothers ageWhether mother smokingThis time pregnancy bleedabortionhistoryUsed estrogen during pregnantThe mothers breast feedpregnant whether exposure to X radial No.case controlcase co
13、ntrolcase controlcase controlcase controlcase controlcase control12345678total25 3230 3022 3133 3022 2721 2930 2725 28yes 2/4yes 3/4yes 1/4yes 3/4yes 3/4yes 3/4no 3/4yes 3/47/8 21/32 no 0/4 no 0/4 yes 0/4 yes 0/4 no 1/4 ye 0/4 no 0/4 no 0/4 3/8 1/32 yes 1/4 yes 1/4 no 1/4 yes 0/4 no 1/4 yes 0/4 yes
14、1/4 yes 0/4 6/8 5/32 yes 0/4 yes 0/4 yes 0/4 yes 0/4 no 0/4 yes 0/4 yes 0/4 yes 0/4 7/8 0/32 no 0/4 no 1/4 yes 0/4 yes 2/4 no 0/4 no 0/4 yes 0/4 no 0/4 3/8 3/32 no 1/4 no 0/4 no 0/4 no 0/4 no 0/4 no 1/4 no 1/4 yes 1/4 1/8 4/32averge 2 P OR26.1 29.30.530.505.74.520.058.07.160.0110. 523.220.0000128.02
15、.350.2010.003.0ResultConclusions:vAmong all research factors only 3 of them were significant in statistics: Their mothers had used estrogen during pregnancy. (P0.00001) Their mothers history of abortion. (P0.01) Their mothers vagina hemorrhage during this pregnancy. (P1, OR1Analysis of Unmatched Des
16、ign vCross-table 2 testvCompute OR vOR 95% Confidence Interval (OR 95% CI)Woolf methodMiettinen methodOCCase ControlTotal take NoTotal 39(a)114(c)153(m1)24(b)154(d)178(m2)63(n1)268(n2)331(N)A case-control study on oral contraceptive and myocardial infarction Example association of OC and MI by age w
17、as stratified 40 40 OC（+） OC（-） Total OC（+） OC（-） Total Case 21（a1） 26（b1） 47（m11） 18（a2） 88（b2） 106（m12） Control 17（c1） 59（d1） 76（m01） 7（c2） 95（d2） 102（m02） Total 38（n11） 85（n01） 123（t1） 25（n12） 183（n02） 208（t2） association of age and MI association of age and OC 40 40 40 40 MI 26 88 OC(+) 17 7 Con
18、trol 59 95 OC(-) 59 95 OR=0.48，2=7.27 OR=3.91，2=8.89OR=2.80 OR=2.78 By MantelHaenszel formula compute OR and 2 ORL=1.551.55， ORU=5.015.011:1 matched data analysisControl CaseTotal Exposed UnexposedExposed Unexposed a cbda+bc+dTotal a+cb+da+b+c+dSummary data format for a matched case-control study wi
19、th one control per caseMcNemarMcNemar test test =(b-c)=(b-c)=(b-c)=(b-c)2 2 2 2/b+c/b+c/b+c/b+cCompute OR Compute OR OR=c/bOR=c/bOR=c/bOR=c/b MiettinenMiettinen method compute OR95 compute OR95CICIAssociation infectivity mononucleosis (IM) and lymphocyte leukaemiaControl CaseTotal (MI+) (MI-)(MI+) (
20、MI-) a cbda+bc+dTotal a+cb+da+b+c+d2=（35-60）2/（35+60）=6.58，P0.01OR=60/35=1.71OR95%CI=1.71（11.96/ ） ORL =2.57， ORU= 1.14Exampleattributable fraction，AF （etiology fraction，EF） 8. BiasWhat does bias mean? Any systematic error in the design, conduct or analysis of a study that results in a mistaken esti
21、mate of an exposures effect on the risk of disease.Types of bias:nSelection biasnInformation bias (observation bias)nConfounding nSelection bias Selection bias is a is a systematic error in a study that arises from the manner in which the subjects are sampled. Prevalence-incidence biasAdmission rate
22、 (Berksons) biasDetection biasDetection biastime effect biastime effect biasCases should be limited to incident cases, and should be chosen as random samples of all cases.Definitions, ascertainments and exclusions must always be made explicit. At least two control groups should be chosen: a. a hospi
23、tal-based group b. a community-based control group.Control of selection biasnInformation bias (observation bias)Information bias is a systematic error in a study that arises from the manner in which data are collected from participants.Recall biasinvestigation biasinvestigation biasControl:Selecting
24、 objective indexTraining investigatorExamining condition consistentnConfounding Confounding is a systematic error in a study that arises from mixing of the effect of the exposure of interest with other associated correlates of the disease outcome. control of confounding:Restriction by study design M
25、atching Stratification in the analysisMathematical modelling in the analysis such as multiple linear regression, logistic regression , Cox model9. Advantages of case-control studyUseful for studying rare diseases and diseases of long latencyCost effective, quick and easy to completeCan be used to ge
26、nerate hypotheses in a defined populationCan do rapid evaluation of new disease10. Disadvantages of case-control studyNot useful for rare exposuresUncertainty of the exposure-disease relationshipInability to provide direct estimate of riskPotential biases: such as selection bias, recall bias11. Othe
27、r Types of Case Control StudyNested case control studyCase-cohort studyBlood drawn on 10 000 individual10 years10 yearsRA=200(serologic test)no RA=9800take sample of 400 with no RA (serologic test) 80 120 40 360 + - + -+ - + -A sample a nested case-control study RA denotes rheumatoid arthritisBlood
28、drawn on 10 000 individual RA=200 SLE=100 AS=150 (serologic test) (serologic test) (serologic test) sample 400 oforiginal 10 000(serologic test) 80 120 20 80 15 135 40 360 + - + - + - + -A example of case-cohort study RA denotes rheumatoid arthritis,SLE denotes systemic lupus erythematosus, AS denotes ankylosing spongylitis10years10years10years10years
