臨床試驗的Meta分析課件

542-11-#1Statistics542

IntroductiontoClinicalTrials

MetaAnalysis542-11-#2Meta-Analysis

Alternatives? Occasionally Complementary? YesMeta-AnalysisCombinationofsimilarstudiesusingsimilarsubjectsandsimilartreatmentsandsimilaroutcomes542-11-#3Figure2

OddsRatiosand95%ConfidenceLimits

forVariousStudiesandaPooledEstimate542-11-#5Reference:NIHProceedingsMethodologicIssuesinOverviewsofRandomizedClinicalTrialsNIHConferenceMay1986StatisticsinMedicineVol6,No.3,1987542-11-#6WhatisthePurpose?a. Testingforatreatmenteffect(rejectingthenullhypothesis)b. Evaluatingasafetyissue(rareevents)c. Estimatingsizeoftreatmenteffectinsubgroupsd. Designofnewstudiese. Developpracticeguidelines542-11-#7IdealMetaAnalysisisRandomizedMulti-centerControlTrialSameprotocolSametreatmentSametypeofsubjectsSameoutcomemeasure542-11-#9WhatStudiesShouldBeIncluded?AllexistingstudiesAllpublishedstudies"Non-flawed"trialsOtherselectioncriteria542-11-#10Meta-Analysis:When?(1)RetrospectiveAnalysesTestTreatmentEffectWhen:DefinitiveanswernotyetavailableNomorestudieslikelyNeedtosalvageavailableresultsDevelopPracticeGuidelinesDesignNewStudies542-11-#11Meta-Analysis:When?(2)ProspectiveAnalysesNotrecommendedBettertodesigninadvancepropermulti-centertrial(s)542-11-#13OddsRatiomoreexplicitly

OR=ad/bcTCSaba+bFcdc+da+cb+d542-11-#14MethodsofMeta-AnalysisCollapsingcanbemisleadingifthereisqualitativeinteraction.1.0CollapseDataRCT-1TCS155F8595OR=3.35RCT-2TCS515F9585OR=0.30CollapsedTC2020180180OR=1.0542-11-#152. GraphicalSeeFigure95%CIforeachstudy

(ad/bc)exp{±1.96(1/a+1/b+1/c+1/d)}MethodsofMetaAnalysis542-11-#17Comparisonofmeta-analysisof12RCTsofi.v.mixeddrugs(double-blind)withi.v.metoprolol(double-blind)andi.v.atenlol(openstudy).StatinMed6(3):320,1987.542-11-#18Comparisonofmeta-analysisofmortalityin11RCTsandreinfarctionratesin10RCTsofi.v.streptokinasewithlargeco-operativestudy(GISSI).StatinMed6(3):320,1987.542-11-#19Comparisonofmeta-analysisof7smallRCTsofphenobarbitalinthetreatmentofneonatalintra-cranialhaemmorrhagewithonelargeco-operativestudy(3institutions).Endpointsaretotalinfantswithhaemmorrhageandtotalswithseverehaemorrhage(GradesIII-IV)only.StatinMed6(3):321,1987.542-11-#213. Blocking(Peto-MH)OverallEstimate LetO=ai E=Ei Ei=(ai+ci)(ai+bi) ni V=Vi Vi=(ai+ci))(bi+di)(ci+di)(ai+bi ni2(ni-1) Z=O-E

C

PooledOR OR=exp{(O-E)/V}

95%CI=exp{(O-E)/V±1.96/}MethodsofMetaAnalysis542-11-#224. AveragingP-values Fisher(1948) Pi=P-valueforithtrial Z=-2

log(Pi)~2

with2Ndf5. AveragingTestStatistics e.g.wi=niMethodsofMetaAnalysis542-11-#23Meta-AnalysisExamplesCardiologyPostMITreatments (e.g.,beta-blockers,aspirin)ThrombolyticTherapy (e.g.,streptokinase)Anticoagulants542-11-#25Registries/DatabasesUseClinicalObservationalSeriesto:DescribeClinicalPracticeIdentifyRiskFactors"Evaluate"TreatmentHistoricalConcurrent542-11-#26DatabasesTreatmentEvaluationComparisonRequiresRiskFactorComparabilityMeasuredNotMeasuredorUnknownStatisticalModelsUsuallyNotAdequateAssociationvs.EstimationModelOnlyanApproximationSmallPortionofOutcomeExplained542-11-#29RegistriesBiasinTreatmentEffect(Peto,Biomedicine,1978)TrialsofAnticoagulantTherapy

Design Studies Patients Effect Historical 18 900 50%Reduction Concurrent 8 3000 50%Reduction RCT 6 3000 20%Reduction

542-11-#30PTCAPTCARegistryTrackedandcomparedusageLeadtofurthertrialsNoPTCAvs.placeboTIMI-IIComparedimmediatevs.dela