BEGIN:VCALENDAR VERSION:2.0 METHOD:PUBLISH PRODID:-//Telerik Inc.//Sitefinity CMS 13.3//EN BEGIN:VTIMEZONE TZID:UTC BEGIN:STANDARD DTSTART;VALUE=DATE:20230101 TZNAME:UTC TZOFFSETFROM:+0000 TZOFFSETTO:+0000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT DESCRIPTION:Defining the estimand of interest in a clinical trial is crucia l to align its planning\, design\, conduct\, analysis\, and interpretation . The need for more precise specifications of estimands is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in ICH E9(R1)\, the adde ndum  \;brings causal reasoning &ndash\; besides randomization and ITT &ndash\; into our world of pharmaceutical statistics. In this webinar\, w e will discuss the link between the ICH E9(R1) and causal inference. Furth ermore\, per protocol analyses will be discussed from a causal inference p erspective and a case study where a principal strata estimand was investig ated will be presented.\nFor more information please click here.\n\nBaldur Magnusson\nNovartis Pharma AG\nUsing principal stratification to address post-randomization events: A case study\nIn a randomized controlled trial\ , occurrence of post-randomization events associated with treatment and th e primary endpoint may complicate the interpretation of the overall treatm ent effect. In this presentation\, we discuss how these events may be acco unted for at the estimand and the estimator level in the context of a rece nt case study. We define a principal stratification estimand derived from the scientific question of interest. Consideration is given to identifying assumptions\, model-based derivation of an estimator\, handling of covari ates and missing data. We also discuss the role of sensitivity analyses.\n \nPlease \;click here \;to view the slides.\n\n\nDaniel Scharfstei n\nProfessor of Biostatistics\, Johns Hopkins Bloomberg School of Public H ealth\nEstimands and Causal Inference \nRecently\, the ICH proposed an add endum to the E9 Guidance: Statistical Principles for Clinical Trials. Thi s addendum is focused on estimands and sensitivity analysis for randomized trials with intercurrent events. In this webinar\, I will discuss the po tential outcomes framework for causal inference and use it to formally def ine estimands that address different types of intercurrent events. I will then discuss the assumptions required to identify these estimands from the observable data and discuss the important role of sensitivity analysis. \n\nPlease click here \;to view the slides. \nWanjie Sun\nFDA/CDER/OB/ DBVIII\nEstimating Causal Effects in Clinical Endpoint Bioequivalence Stud ies in the Presence of Treatment Noncompliance and Missing Data \nIn clini cal endpoint bioequivalence (BE) studies\, the primary analysis for assess ing equivalence between a generic and an innovator product is usually base d on the observed per-protocol (PP) population (i.e.\, completers and comp liers in general). The FDA Missing Data Working Group and the ICH E9 Revis ion 1 Working Group recommended using &ldquo\;causal estimands of primary interest.&rdquo\; The analysis based on the PP population\, however\, is n ot generally causal because PP is determined post-treatment\, hence condit ioning on it may introduce selection bias. To date\, no causal inference h as been proposed to assess to equivalence. In this paper\, we propose a ca usal framework and co-primary causal estimands to test equivalence by appl ying Frangakis and Rubin (2002)&rsquo\;s principal stratification in causa l inference. We identify three conditions when the current PP estimator is unbiased for one of the proposed co-primary causal estimands &ndash\; the &ldquo\;Survivor Average Causal Effect&rdquo\; (SACE) estimand. Simulation was used to demonstrate the bias\, type 1 error\, and power associated wi th the PP estimator when these three conditions are not met. We also propo se a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the un derlying sensitivity parameters vary across a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensitivity analysis method. Our work sta rts causal evaluation of equivalence assessment in clinical endpoint BE st udies with non-compliance and missing data\, and can be applied to clinica l biosimilar and non-inferiority studies. \n*The views expressed in this a rticle represent the opinions of the authors\, and do not represent the vi ews and/or policies of the U.S. Food and Drug Administration.\n\n\nTo acce ss the recording\, please visit the Video-on-Demand Library. DTEND:20171102T150000Z DTSTAMP:20240329T104832Z DTSTART:20171102T130000Z LOCATION: SEQUENCE:0 SUMMARY:PSI Webinar: Causal Inference UID:RFCALITEM638473061126840066 X-ALT-DESC;FMTTYPE=text/html:
Defining the estimand of interest in a clin ical trial is crucial to align its planning\, design\, conduct\, analysis\ , and interpretation. The need for more precise specifications of estimand s is highlighted in the draft addendum ICH E9(R1) which was published for public consultation in August 2017. Although not explicitly mentioned in I CH E9(R1)\, the addendum  \;brings causal reasoning &ndash\; besides r andomization and ITT &ndash\; into our world of pharmaceutical statistics. In this webinar\, we will discuss the link between the ICH E9(R1) and cau sal inference. Furthermore\, per protocol analyses will be discussed from a causal inference perspective and a case study where a principal strata e stimand was investigated will be presented.
\nFor more information p
lease click here.
\n
\nBaldur Magnusson
Novartis Pharma AG
\nUsing principal stratification to address post-randomization events: A ca se study
\nIn a randomized controlled trial\, occurren
ce of post-randomization events associated with treatment and the primary
endpoint may complicate the interpretation of the overall treatment effect
. In this presentation\, we discuss how these events may be accounted for
at the estimand and the estimator level in the context of a recent case st
udy. We define a principal stratification estimand derived from the scient
ific question of interest. Consideration is given to identifying assumptio
ns\, model-based derivation of an estimator\, handling of covariates and m
issing data. We also discuss the role of sensitivity analyses.
\n
\nPlease \;click here \;to view the slides.
\n
\
n
Daniel Scharfstein
\nProfessor of Biostati
stics\, Johns Hopkins Bloomberg School of Public Health
R
ecently\, the ICH proposed an addendum to the E9 Guidance: Statistical Pri
nciples for Clinical Trials. This addendum is focused on estimands and se
nsitivity analysis for randomized trials with intercurrent events. In thi
s webinar\, I will discuss the potential outcomes framework for causal inf
erence and use it to formally define estimands that address different type
s of intercurrent events. I will then discuss the assumptions required to
identify these estimands from the observable data and discuss the importan
t role of sensitivity analysis.
\n
\nPlease click here \;to view
the slides.
Wanjie Sun
\nFDA/CDER/OB/DBVII
I
Estimating Causal Effects in Clinical Endpoint Bioeq uivalence Studies in the Presence of Treatment Noncompliance and Missing D ata
\nIn clinical endpoint bioequivalence (BE) studie s\, the primary analysis for assessing equivalence between a generic and a n innovator product is usually based on the observed per-protocol (PP) pop ulation (i.e.\, completers and compliers in general). The FDA Missing Data Working Group and the ICH E9 Revision 1 Working Group recommended using & ldquo\;causal estimands of primary interest.&rdquo\; The analysis based on the PP population\, however\, is not generally causal because PP is deter mined post-treatment\, hence conditioning on it may introduce selection bi as. To date\, no causal inference has been proposed to assess to equivalen ce. In this paper\, we propose a causal framework and co-primary causal es timands to test equivalence by applying Frangakis and Rubin (2002)&rsquo\; s principal stratification in causal inference. We identify three conditio ns when the current PP estimator is unbiased for one of the proposed co-pr imary causal estimands &ndash\; the&ldquo\;Survivor Average Causal Effect& rdquo\; (SACE) estimand. Simulation was used to demonstrate the bias\, typ e 1 error\, and power associated with the PP estimator when these three co nditions are not met. We also propose a tipping point sensitivity analysis to evaluate the robustness of the current PP estimator (primary analysis) in testing equivalence when the underlying sensitivity parameters vary ac ross a clinically meaningful range. Data from a clinical endpoint BE study is used to illustrate the proposed co-primary causal estimands and sensit ivity analysis method. Our work starts causal evaluation of equivalence as sessment in clinical endpoint BE studies with non-compliance and missing d ata\, and can be applied to clinical biosimilar and non-inferiority studie s.
\n*The views expressed in this article represent the opinions of
the authors\, and do not represent the views and/or policies of the U.S.
Food and Drug Administration.
\n
\n
To access th e recording\, please visit the Video- on-Demand Library.
END:VEVENT END:VCALENDAR