《Optimising clinical trial programs to enable more robust 优化临床试验的方案使更强大文档资料.ppt》由会员分享，可在线阅读，更多相关《Optimising clinical trial programs to enable more robust 优化临床试验的方案使更强大文档资料.ppt（31页珍藏版）》请在三一办公上搜索。
1、Outline,File name/location,Company ConfidentialCopyright 2000 Eli Lilly and Company,The Observational Research Problem(or Challenge),Selection Bias,Confounders,The Observational Research Challenge,Selection Bias,Measured:Information is collected within the study and statistical adjustment is possibl
2、eUnmeasured:Information on the confounder is not available from the study,Selection Bias,Confounders,Can We Get Causal Inference From Observational(non-randomized)Data?,YES IF 3 key assumptions hold.“No Unmeasured Confounders”An ASSUMPTION!Can not be definitively verified.“No Perfect Confounding”Cor
3、rect Models are used,Hierarchy of EvidenceVandenbrouke(2008),Concato(2000),.,Increasing the Quality of Observational Research(Rubin 2007,2008),Keep core statistical(RCT)design principles in mind that are sometimes overlooked in observational research.Prospective SpecificationMultiplicityReplicationS
4、ensitivity Analyses,Current State of the Union Regarding Unmeasured Confounding,What should I do about unmeasured confounding?,Current State of the Union Regarding Unmeasured Confounding,What should I do about unmeasured confounding?,Just mention it as a limitation in the Discussion Section and move
5、 on!,EXPERT,There are new methods in the literature!“Best Practices”include sensitivity analyses,Figure 1:Unmeasured Confounding Options,Internal,Unmeasured Confounding,External,BayesianMultiple ImputationPropensity Calibration,None,InformationAvailableMethod,1)Rule Out2)IV,1)Bayesian2)Algebraic,Exa
6、mple for Today,Pawaskar M,Zagar A,Sugihara T,Shi L(2011).Healthcare resource utilization and costs assessment of type 2 diabetes.J Med Econ.2011;14(1):16-27.No direct measure of glycemic control was available in the original claims database.However,after linking with a laboratory file,A1C values wer
7、e obtained in a subset(about 20%)of the sample;A1C was a significant predictor of treatment selection(p.001)but only modestly related to outcome(costs)Our Work:Sensitivity Analysis using this Internal Information,Information Available:None,Rule Out CONCEPT:Quantify how strong and imbalanced a confou
8、nder would need to be in order to explain(rule out)the observed treatment difference,Instrumental Variables CONCEPT:Use of an Instrument(variable associated with treatment selection but not with outcome)allows one to mimic randomization,Concept:Quantify how strong and imbalanced a confounder would n
9、eed to be in order to explain(“rule out”)the observed result.,Rule-out Method,This approach attempts to find all combinations of 1)the confounder-outcome relationship and 2)the confounder-treatment relationship,-necessary to move the observed point estimate to zero.,Rule Out Simple Model,Basic(addit
10、ive)Model:AMD=TTD+BiasAMD is the apparent(observed)mean treatment difference TTD is the true(fully adjusted)mean treatment difference Bias is a function of:The imbalance of the unmeasured confounding factor between treatment groups The strength of the association between the unmeasured confounder an
11、d the outcome,Rule Out Simple Spreadsheet,Bias,Fixed Value 1,Fixed Value 2,File name/location,Company ConfidentialCopyright 2000 Eli Lilly and Company,Rule-out Method Example,Confounder Cohort Association,Confounder-Outcome Association,So,a confounder occurring in 20%more patients in Cohort A(compar
12、ed to Cohort B)which results in$15,000 higher cost per patient would eliminate the observed difference,Trt A is Not Less Costly,Trt A remains Less Costly,Rule Out Example,Information Available:External,Bayesian Models:Incorporate the external information through a prior distribution and account for
13、the uncertainty surrounding the external estimates,Concept:Use information external to the study(e.g.data from literature or other databases)to estimate parameters regarding unmeasured confounding(e.g.strength of association with outcome and treatment).,External Adjustment(ctd),Algebraic External Ad
14、justment Examples:-Schneeweiss et al JAGS 2005-Schneeweiss et al CNS Drugs 2009,Some Issues:1)Transportability 2)Correlation of Unmeasured Confounder with variables already accounted for in the analysis model,Information Available:Internal,With Internal data can avoid transportability assumption and
15、 can account for correlation between unmeasured confounder and measured confounders,Concept:Use information from the patients in the study(e.g.subsample of chart review data for a retrospective claims database study)to estimate parameters regarding unmeasured confounding,Information Available:Intern
16、al,MethodsPropensity Score CalibrationSturmer et al,Am J Epi 2005Bayesian ModelingMcCandless Stat Med 2007Multiple ImputationFaries(submitted),Propensity Score Calibration,Two propensity scores(PS)are calculated for the validation data,-“Error Prone”PS:utilizes only covariates available for the full
17、 sample of patients-“Gold Standard”PS:calculated using both the covariates in the main study along with the additional confounding covariates.Regression calibration(measurement error modeling)is then applied to adjust the regression coefficients and thus compensate for the unmeasured confounding.,Co
18、ncept:Utilize additional data-variables not in full sample but available for a subset of patients-to modify the propensity score adjustment,File name/location,Company ConfidentialCopyright 2000 Eli Lilly and Company,Propensity Score Calibration(ctd),Error Prone Propensity Score Model(PSEP)Gold Stand
19、ard Propensity Score Model(PSGS)Calibration Model:,Propensity Score Calibration,Validity relies on surrogacy of the error prone propensity for the gold standard propensity.“error prone PS”must be independent of the outcome given“gold standard PS”and treatment.For our example surrogacy assumption not
20、 clearly satisfiedCorrelations of A1C&Outcome was negativeCorrelations of Other Covariates&Outcome was positive,Bayesian Twin Regression Models,Concept:Bayesian models naturally incorporate additional sources of information such as internal subset data or external information from other studies-thro
21、ugh prior distributions,Implementation:WinBUGS(SAS 9.3 code upcoming),Internal data serves in essence as informative prior information for parameters relating to unmeasured confounder,Bayesian Twin Regression Models,Priors:Uninformative:Informative:,Keys to Bayesian Approach,Incorporation of best av
22、ailable information through Informative PriorsBest available data whether internal(via subset data)or External data(e.g.literature)Informative Priors not just a way to add uncertainty(McCandless 2007)Yields a posterior distribution(point and interval estimates)for the treatment effect adjusted for t
23、he unmeasured confounder U.Fixed Modeling(Schneeweiss 2006)failed to incorporate variability Flexible data driven modelNo restrictions on relationships on associations between variables as in measurement error approaches(Sturmer 2007).,Missing Data Multiple Imputation(for internal data),Imputation M
24、odel:Treatment,Measured Covariates,and Outcome(in order to account for he association between confounder/outcome and confounder/treatment)Used 5 replications due to amount of missing data Implementation:PROC MI in SAS,Concept:This is a missing data problem use a well accepted method-Multiple Imputat
25、ion!,Example:Summary of Sensitivity Analyses with Internal A1C Data,Conclusions,Other References,Goodman M,Barraj LM,Mink PJ,Britton NL,Yager JW,Flanders D,Kelsh MA(2007).Estimating uncertainty in observational studies of associations between continuous variables:example of methylmercury and neurops
26、ychological testing in children Epi Perspec Innovat 4:9.Gustafson P,McCandless LC(2010).Probabilistic Approaches to Better Quantifying the Results of Epidemiologic Studies.Int.J Environ Res Pub Hlth 7:1520-1539.McCandless,L.C.Gustafson,P.Levy,A.R.Bayesian sensitivity analysis for unmeasured confound
27、ing in observational studies.Statist.Med.2007,26,2331-2347.McCandless,L.C.Gustafson,P.Levy,A.R.A sensitivity analysis using information about measured confounders yielded improved assessments of uncertainty from unmeasured confounding.J.Clin.Epidemiol.2008,61,247255.Pawaskar M,Zagar A,Sugihara T,Shi
28、 L(2011).Healthcare resource utilization and costs assessment of type 2 diabetes patients initiating exenatide BID or glargine:a retrospective database analysis.J Med Econ.2011;14(1):16-27.Epub 2010 Dec 15.Schneeweiss S,Setoguchi S,Brookhard MA,Kaci L,Wang PS(2009).Assessing Residual Confouding of t
29、he Association between Antipsychotic Medications and Risk of Death Using Survey Data.CNS Drugs,23(2):171-180.Schneeweiss S,Wang PS(2005).Claims Data Studies of Sedative-Hypnotics and Hip Fractures in Older People:Exploring Residual Confounding Using Survey Information.JAGS 53:948-955.Schneeweiss S,W
30、ang PS(2005).Claims Data Studies of Sedative-Hypnotics and Hip Fractures in Older People:Exploring Residual Confounding Using Survey Information.JAGS 53:948-955.Sturmer T,Schneeweiss S,Rothman KJ,Avorn J,Glynn RJ(2007).Performance of Propensity Score Calibation A Simulation Study.Am J Epi 165(10):11
31、10-1118.Sturmer T,Schneeweiss S,Avorn J,Glynn RJ(2005).Adjusting Effect Estimates for Unmeasured Confounding with Validation Data using Propensity Score Calibration.Am J Epi 162(3):279-289.Weiner MG,Xie D,Tannen RL(2008).Replication of the Scandinavian Simvastatin Survival Study using a primary care medical record database prompted exploration of a new method to address unmeasured confounding.Pharmacoepi Drug Safety DOI:10.1002/pdsXue F,Strombom I,Turnbull B,Zhu S,Seeger JD(2011).Duloxetine for Depression and the Incidence of Hepatic Events in Adults.J Clin Psych 31:517-522/,
