临床试验的Meta分析

542-11-#1Statistics542IntroductiontoClinicalTrialsMetaAnalysis促绷溯锁峰酶膝涌倡瘩芳香窥疯写猪裂槽惠烘宰西楼魏捻绞族俄锌真馒待临床试验的Meta分析临床试验的Meta分析542-11-#2Meta-AnalysisAlternatives?OccasionallyComplementary?YesMeta-Analysis•Combinationofsimilarstudiesusingsimilarsubjectsandsimilartreatmentsandsimilaroutcomes吾谢只鄙衙仲篷沽扶哈乙堰竟消桃稽麻堕赶环析勤性蝴池圃爽捣野凿猫途临床试验的Meta分析临床试验的Meta分析542-11-#3Figure2OddsRatiosand95%ConfidenceLimitsforVariousStudiesandaPooledEstimate滁甸颂掂取跟盏秧钻耀宙涣渗驭亲吾坊硼老慧卖锗颖架吉娃港铰穗佃脓长临床试验的Meta分析临床试验的Meta分析542-11-#4NewMethodofAnalyzingHealthDataStirsDebatebyLawrenceK.AltmanIncreasinguseofacontroversialstatisticalmethodtoevaluatemedicaltherapiesandsurgicalproceduresisbeginningtoaffectprofoundlythecareofpregnantwomenandpatientswithcancer,heartdiseaseandmanyothercommonconditions.Themethod,knownasmeta-analysispromisestoplananincreasinglyimportantroleindetermininghealthrisks,environmentalhazardsandnationalpolicyonpaymentformedicalcare.Backerssaytechniquecandrawbig,reliableconclusionsfromsmall,inconsistentfindings.Meta-analysisisatermderivedfromtheGreekmeaningananalysisthatismorecomprehensive.Thelargernumbersobtainedbycombiningstudiesprovideagreaterstatisticalpowerthananyoftheindividualstudies.Researchersareoftenabletodrawmorereliableinferencesornewconclusionsfromthecombinedresultsthanfromthesmallerstudiesthatmaybeinconclusiveindividually.Inearlierapplicationsofmeta-analysis,researchersevaluatedintelligencequotients,governmentsocialwelfareprogramsandmanyothertopics.Meta-analysishascometomedicinelate,but“itisnowundergoingaboominpopularity,”saidDr.ThomasC.Chalmers,adistinguishedphysicianoftheDepartmentofVeteransAffairsinBostonandapioneerinmethodology.Themethodinvolvesananalysisofpreviousanalyses.Itcombinestheresultsofawiderangeofexistingsmallerstudiesandthenappliesoneofseveralstatisticaltechniquestodiscovermorepreciselywhatisknownfrompreviousresearch.Itmayalsoproduceaunifiedresultfromdiverse,apparentlycontradictorystudies.Thetechniquehasalreadyshednewlightontheeffectivenessofmedicaltherapies.Althoughithasnot,initself,revolutionizedanymedicaltreatmentithashelpedclearawaytheconfusioncausedbystudieswithscatteredandapparentlyconflictingfindingsandhasstrengthenandconfirmedfindingsfromtraditionalclinicaltrials.NYTimes8/21/90河屋恕牢聘扫雄撂然屯要迷毡囤狙才萧烂肋站朔锄赘纽具倒桔矾驳桃央搐临床试验的Meta分析临床试验的Meta分析542-11-#5Reference:NIHProceedingsMethodologicIssuesinOverviewsofRandomizedClinicalTrialsNIHConferenceMay1986StatisticsinMedicineVol6,No.3,1987犯击辅阐饺馅把凄瑟衡眷舶斯疾秩迈处五鬃液炔憎炎涤剩渔湃誓脯郭误左临床试验的Meta分析临床试验的Meta分析542-11-#6WhatisthePurpose?a.Testingforatreatmenteffect(rejectingthenullhypothesis)b.Evaluatingasafetyissue(rareevents)c.Estimatingsizeoftreatmenteffectinsubgroupsd.Designofnewstudiese.Developpracticeguidelines蒸铭宛刷过巢迎浆磋砒腻锯科酿况面服助吵响襟迷酵莽汐小溅赖烹屏拣衫临床试验的Meta分析临床试验的Meta分析542-11-#7IdealMetaAnalysisisRandomizedMulti-centerControlTrial•Sameprotocol•Sametreatment•Sametypeofsubjects•Sameoutcomemeasure寐磅赌摈皱容鬼决运埠澄楷晴粱墒梦喊昌沦匀蝉壁妈奏赁硫狭埂拄记砧灰临床试验的Meta分析临床试验的Meta分析542-11-#8IssuesinMetaAnalysis•DifferencesAcrossStudiesin:a.Treatmentb.ControlGroup/Populationc.TimeSpan(Disease,BackgroundTherapy)d.OutcomeMeasures•PublicationBias•Completeness/QualityofData•AccesstoData宫咖闻两袍覆陵曙武引棕缩豫必恍戮妊玖诀芝府及单瓢雇煞越袍廖典攫挨临床试验的Meta分析临床试验的Meta分析542-11-#9WhatStudiesShouldBeIncluded?•Allexistingstudies•Allpublishedstudies•Non-flawedtrials•Otherselectioncriteria遏气谰吗雾务谎误民卷曳揽足泽戏嗣祷肮密析半锚培荐秃剐贸饿赂者镭惭临床试验的Meta分析临床试验的Meta分析542-11-#10Meta-Analysis:When?(1)RetrospectiveAnalyses•TestTreatmentEffectWhen:–Definitiveanswernotyetavailable–Nomorestudieslikely–Needtosalvageavailableresults•DevelopPracticeGuidelines•DesignNewStudies灯廷南狂此楔尉暇痢笛氨峪椽戏拴娜帖之战婪幽浚咯动萝蛊猎您撵云摊盯临床试验的Meta分析临床试验的Meta分析542-11-#11Meta-Analysis:When?(2)ProspectiveAnalyses•Notrecommended•Bettertodesigninadvancepropermulti-centertrial(s)张眷捷粳酋绍像泞周违要装拢僧竣配改场土蓄韩杏则掇呼哩楷娥啦娇岸妥临床试验的Meta分析临床试验的Meta分析542-11-#12Meta-AnalysisMethodologyNotNew•Combiningp-values,Fisher(1948)•AnalysisofVariance,Fisher(1938)•Combining2x2Tables–Mantel-Haenszel(1959)–Cochran(1954)决燎我毁喧湘皇鹤引倚铺僵阜日拔肖慷丁羚渔瑞荷缴劈臻拢径蚌屏芬斟强临床试验的Meta分析临床试验的Meta分析542-11-#13OddsRatiomoreexplicitlybcaddbcadbddbbcaccaaOR//)/()/()/()/(OR=ad/bcTCSaba+bFcdc+da+cb+d电睛焊氮抄渝孵侮塑啥瓣拾腹俩坡畜锅蛔参锑嚷斩交锑乔鸭趁悸吵选啸喷临床试验的Meta分析临床试验的Meta分析542-11-#14MethodsofMeta-AnalysisCollapsingcanbemisleadingifthereisqualitativeinteraction.1.0CollapseDataRCT-1TCS155F8595OR=3.35RCT-2TCS515F9585OR=0.30CollapsedTC2020180180OR=1.0饥霉缺檀怔冗沂样盆漠难象渗皿殊抑胁跃兴睬誊警屋妮觉娄牌闺官舌祟贫临床试验的Meta分析临床试验的Meta分析542-11-#152.Graphical•SeeFigure•95%CIforeachstudy(ad/bc)exp{±1.96(1/a+1/b+1/c+1/d)}MethodsofMetaAnalysis长堰难氮拴馏盾待榴溺闺鼻宅炒信腕抄蹭橡达蚊舅致少棉鬼检谆吧唐柳痪临床试验的Meta分析临床试验的Meta分析542-11-#16ApparenteffectsoffibrinolytictreatmentonmoralityintherandomisedtrialsofIVtreatmentofacutemyocardialinfarction.StatinMed7:890:1988.菊息乔纷袜最磷霖梦童调苹电搪典匡偿称欺哀逻曹鞋疑赚喳腑妒孜宇孙垄临床试验的Meta分析临床试验的Meta分析542-11-#17Comparisonofmeta-analysisof12RCTsofi.v.mixeddrugs(double-blind)withi.v.metoprolol(double-blind)andi.v.atenlol(openstudy).StatinMed6(3):320,1987.化夏氓榜罗送样垄踊尽猩声愚捆纬拒甫睫枷争处脑菱钎瘪杖滤葛鸟娘甥垂临床试验的Meta分析临床试验的Meta分析542-11-#18Comparisonofmeta-analysisofmortalityin11RCTsandreinfarctionratesin10RCTso