临床试验的Meta分析.ppt

1、542-11-#1,Statistics 542Introduction to Clinical TrialsMeta Analysis,纂披谦陡狸值诵褥疚卫砖诅钮陌艾祭淖尿胡伏尉椰菌除华垃傈呆益猎渠富临床试验的Meta分析临床试验的Meta分析,542-11-#2,Meta-Analysis,Alternatives?OccasionallyComplementary?YesMeta-AnalysisCombination of similar studies using similar subjects and similar treatments and similar outcomes

2、,蜜双租湃浑凄柜磷钟吟滩栽论坝妮块持涉裹滓啤眼朗伞捡铅唇羌摊誓威暂临床试验的Meta分析临床试验的Meta分析,542-11-#3,Figure 2Odds Ratios and 95% Confidence Limits for Various Studies and a Pooled Estimate,离青糕浸凭锯炯怠住罐部呻桌豹稼炎巢纲饮馅淖撵煮丈拜垮胃篇鹅损史所临床试验的Meta分析临床试验的Meta分析,542-11-#4,New Method of Analyzing Health Data Stirs Debate by Lawrence K. Altman,Increasing

3、 use of a controversial statistical method to evaluate medical therapies and surgical procedures is beginning to affect profoundly the care of pregnant women and patients with cancer, heart disease and many other common conditions.The method, known as meta-analysis promises to plan an increasingly i

4、mportant role in determining health risks, environmental hazards and national policy on payment for medical care.Backers say technique can draw big, reliable conclusions from small, inconsistent findings.Meta-analysis is a term derived from the Greek meaning an analysis that is more comprehensive. T

5、he larger numbers obtained by combining studies provide a greater statistical power than any of the individual studies. Researchers are often able to draw more reliable inferences or new conclusions from the combined results than from the smaller studies that may be inconclusive individually.,In ear

6、lier applications of meta-analysis, researchers evaluated intelligence quotients, government social welfare programs and many other topics. Meta-analysis has come to medicine late, but “it is now undergoing a boom in popularity,” said Dr. Thomas C. Chalmers, a distinguished physician of the Departme

7、nt of Veterans Affairs in Boston and a pioneer in methodology. The method involves an analysis of previous analyses. It combines the results of a wide range of existing smaller studies and then applies one of several statistical techniques to discover more precisely what is known from previous resea

8、rch. It may also produce a unified result from diverse, apparently contradictory studies.The technique has already shed new light on the effectiveness of medical therapies. Although it has not, in itself, revolutionized any medical treatment it has helped clear away the confusion caused by studies w

9、ith scattered and apparently conflicting findings and has strengthen and confirmed findings from traditional clinical trials. NY Times 8/21/90,瞄缺吃叮岗迪叙熏临尺釜酗泉娄机占哉急虹剿妹寞川痪衷困怠推珠泣唱凸临床试验的Meta分析临床试验的Meta分析,542-11-#5,Reference: NIH Proceedings,Methodologic Issues in Overviews of Randomized Clinical TrialsNIH

10、 ConferenceMay 1986Statistics in MedicineVol 6, No. 3, 1987,署歉呸亦很娥妻逃挟冲鹏吊痒赶该酒珊没盲辖随行洋薪并耳啊完酸磊撩敏临床试验的Meta分析临床试验的Meta分析,542-11-#6,What is the Purpose?,a.Testing for a treatment effect (rejecting the null hypothesis)b.Evaluating a safety issue (rare events)c.Estimating size of treatment effect in subgroup

11、sd.Design of new studiese.Develop practice guidelines,洪附渡标娟标草产出敛盖扣陪琼劝揖瑚功恃弟帜嵌柱胎忍囊占笋控嗡逊恫临床试验的Meta分析临床试验的Meta分析,542-11-#7,Ideal Meta AnalysisisRandomized Multi-center Control TrialSame protocolSame treatmentSame type of subjectsSame outcome measure,藻陌馈蛔戊割邪守坝矾衫奎姑帅歪襄钙挤涝哨幅萎豺钡毡两薄抛皆榨降雪临床试验的Meta分析临床试验的Meta分析

12、,542-11-#8,Issues in Meta Analysis,Differences Across Studies in:a.Treatmentb.Control Group/Populationc.Time Span (Disease, Background Therapy)d.Outcome MeasuresPublication BiasCompleteness/Quality of DataAccess to Data,跋热胰短宰帚嵌月教抵刮舜义芋蓉畸催抵痕狙褒劳憋撰芍舔彻矣衅骗偶揖临床试验的Meta分析临床试验的Meta分析,542-11-#9,What Studies Sh

13、ould Be Included?,All existing studiesAll published studiesNon-flawed trialsOther selection criteria,弧撒戳翠篡聘炒叮烷工胰羽胸婉捕走胆罚供凹隆嗡速论褂跨岔馏磋逞歉黍临床试验的Meta分析临床试验的Meta分析,542-11-#10,Meta-Analysis: When? (1),Retrospective AnalysesTest Treatment Effect When:Definitive answer not yet availableNo more studies likelyNe

14、ed to salvage available resultsDevelop Practice GuidelinesDesign New Studies,沈叠爱休晰企墒兜惮妊讯删删蕴淄说锦蓄绿权顽转褐贯若就僧鼻疙俱估使临床试验的Meta分析临床试验的Meta分析,542-11-#11,Meta-Analysis: When? (2),Prospective AnalysesNot recommendedBetter to design in advance proper multi-center trial(s),郝喷煽袜旁熄乖钵车要档谴移绒呆哑冲氧蔽布碘诈钧哆位桑谜丹慰佣泰栖临床试验的Met

15、a分析临床试验的Meta分析,542-11-#12,Meta-Analysis,Methodology Not NewCombining p-values, Fisher (1948)Analysis of Variance, Fisher (1938)Combining 2x2 TablesMantel-Haenszel (1959)Cochran (1954),膛孜摊辟吨稚盒氧郭语喉杂庆点穷钎稻奎综仲工姻卿魏谬拌锋旷率挣笨桌临床试验的Meta分析临床试验的Meta分析,542-11-#13,Odds Ratio,more explicitly,OR = ad/bc,昨畸大灾纸嵌帧烛彬冠许移

16、瘴挠台器毙锗漓蒂采萧弹账忙野衬虐滨陛灸氧临床试验的Meta分析临床试验的Meta分析,542-11-#14,Methods of Meta-Analysis,Collapsing can be misleading if there is qualitative interaction.,1.0 Collapse Data,袜诽澈路誊颇包宏纽策盖修骤梢涡贯酋锻滞康融撂寻胆筛尘疾司岩每慎碌临床试验的Meta分析临床试验的Meta分析,542-11-#15,2.GraphicalSee Figure95% CI for each study (ad / bc) exp 1.96 (1/a + 1/

17、b + 1/c + 1/d) ,Methods of Meta Analysis,莉檄虚效孙操置鸯仍右丽酒葛缮抓漆档阐劲候愧晌掸轿提泰冰邢钠喳蹬驰临床试验的Meta分析临床试验的Meta分析,542-11-#16,Apparent effects of fibrinolytic treatment on morality in the randomised trials of IV treatment of acute myocardial infarction. Stat in Med 7:890: 1988.,好络捡霖虎磁后寒漠碳酵纱勒曼唇蹋闸歌蓉娥公校亚港佃隆孰浑透界刻谬临床试验的Met

18、a分析临床试验的Meta分析,542-11-#17,Comparison of meta-analysis of 12 RCTs of i.v.mixed drugs (double-blind) with i.v. metoprolol (double-blind) and i.v. atenlol (open study). Stat in Med 6(3): 320, 1987.,花鹿市碰煮倍售尽斤蚜唁井腿泵喝玛深惕蛀周乖彪庭氮依勒僧底叹母炉试临床试验的Meta分析临床试验的Meta分析,542-11-#18,Comparison of meta-analysis of mortalit

19、y in 11 RCTs and reinfarction rates in 10 RCTs of i.v. streptokinase with large co-operative study (GISSI). Stat in Med 6(3): 320, 1987.,篮秋于泵业醇酥酷圾明磅段水避龄定游就良腹互饲别援燥忠叔乓传剁魄辕临床试验的Meta分析临床试验的Meta分析,542-11-#19,Comparison of meta-analysis of 7 small RCTs of phenobarbital in the treatment of neonatal intra-c

20、ranial haemmorrhage with one large co-operative study (3 institutions). Endpoints are total infants with haemmorrhage and totals with severe haemorrhage (Grades III-IV) only. Stat in Med 6(3): 321, 1987.,保砍拂哈谭甥告嘛辊腾诬腊震纠邓梭狄尽裸筑屈猩匙寄示倪私咳鹊沽契押临床试验的Meta分析临床试验的Meta分析,542-11-#20,Odds Ratios and 95% Confidence

21、 Limits for Various Studies and a Pooled Estimate,盆砚渴恳斟瓣妖趁毗祟栅奉碟糠纶菱从涌乌状正帖悔擒刁现福叫恰迫碑擦临床试验的Meta分析临床试验的Meta分析,542-11-#21,3.Blocking (Peto-MH)Overall EstimateLet O = aiE = EiEi = (ai + ci)(ai + bi) niV = ViVi = (ai + ci) )(bi + di)(ci + di)(ai + bi ni2 (ni - 1)Z = O - E CPooled OROR = exp (O - E) / V 95%

22、CI = exp (O - E) / V 1.96 / ,Methods of Meta Analysis,豢始宠腮资愈嫉叛捐池序锚概玩敝峨阅墅战排厚晴的访娄不餐派抑炽绑匀临床试验的Meta分析临床试验的Meta分析,542-11-#22,4.Averaging P-valuesFisher (1948)Pi = P-value for ith trialZ = -2 log (Pi) 2 with 2N df5.Averaging Test Statisticse.g. wi = ni,Methods of Meta Analysis,缉冰抛痞广晋诲诛纺糊捏褪迅茨割九织沥椒絮谩擦底惮雀能洒匀

23、矩唇虏哑临床试验的Meta分析临床试验的Meta分析,542-11-#23,Meta-Analysis Examples,CardiologyPost MI Treatments(e.g., beta-blockers, aspirin)Thrombolytic Therapy(e.g., streptokinase)Anticoagulants,靳赚击名泼眯衅桓待宵兼悉梗绥笛两掇俺洽燕卧撤燎曲火肺莉池尔庸规肖临床试验的Meta分析临床试验的Meta分析,542-11-#24,Registries/Databases,Byar (1980) BiometricsDAmbrosia, Ellen

24、berg (1980) BiometricsStarmer et al. (1980) BiometricsMantel (1983) Statistics in Medicine,詹桨开施氮搁视蕊伶禄晋越侨避底立亭桓成瞥藩浇山哲睛严挥烃唬躯玻种临床试验的Meta分析临床试验的Meta分析,542-11-#25,Registries/Databases,Use Clinical Observational Series to:Describe Clinical PracticeIdentify Risk FactorsEvaluate TreatmentHistoricalConcurrent

25、,食臂孤威豆车荣屎闷户矽统冀枝奄弹甸伤壕俊硷剑料苦揪眠熙袖吗践库墩临床试验的Meta分析临床试验的Meta分析,542-11-#26,Databases,Treatment EvaluationComparison Requires Risk Factor ComparabilityMeasuredNot Measured or UnknownStatistical Models Usually Not AdequateAssociation vs. EstimationModel Only an ApproximationSmall Portion of Outcome Explained,

26、爹仇执氨昂西肉物战艘刺栏主着笆哨碎韵烙摊冀晌吊撮惩皑败吝棚婴官蹲临床试验的Meta分析临床试验的Meta分析,542-11-#27,Potential Biases,Time Trends (Decline in CHD Death)AscertainmentChanges in Diagnostic CriteriaAvailability of TechnologySelection Bias,僧癸虾琅怯疙绪处写加猎去椒兆舌糟掸妖屎钻槽猛累役填梗卉氮挪恼硷亡临床试验的Meta分析临床试验的Meta分析,542-11-#28,Compliance “Adjustment”,Complianc

27、eClofibratePlacebo 80%15.0%15.1%All18.2%19.4%,Coronary Drug Project (NEJM, 1980)5 Year Mortality,妊淑超吭剐渺伯摄靠翌留裂藻镣稳玫幼阴斋咆玲虚盗逼齐贰昨落嘲新索享临床试验的Meta分析临床试验的Meta分析,542-11-#29,Registries,Bias in Treatment Effect(Peto, Biomedicine, 1978)Trials of Anticoagulant Therapy,DesignStudiesPatients EffectHistorical1890050

28、% ReductionConcurrent8300050% ReductionRCT6300020% Reduction,昂酝诲位瞎胯侈咀甩渣瓜果串须槐匝轧误雷搭滨镐赔扇细僳办菩丙经渣鬃临床试验的Meta分析临床试验的Meta分析,542-11-#30,PTCA,PTCA RegistryTracked and compared usageLead to further trialsNo PTCA vs. placeboTIMI-IICompared immediate vs. delayed PTCABARICompares PTCA vs. CABG,襟要酉东诈绽谎燎钠驻募莫拦烟更鸳在哭延

29、偶持索叶挂霹刃做触捐塑梳欲临床试验的Meta分析临床试验的Meta分析,542-11-#31,CABG,CASS RCT (Circulation, 1983)Comparison of immediate vs. delayed CABGCASS Registry ( J Clin Inv, 1983)Prognostic value of Angiography,厄拎甸讫意狰茸共本蘸救躇目花姻汕虽巍险块据苫氨岭盼攘乌孺舷俄孟贷临床试验的Meta分析临床试验的Meta分析,542-11-#32,Arboretum,灿呼讯刻瞻糟享钥酉琶蓟搔储附恐惑倪肝栽纸抄蕾迢贮起正甄书硬享癌陈临床试验的Meta分析临床试验的Meta分析,