\nTime: \;13:30-16:00 GMT (both days) | 14 :30-17:00 CET (both days)
\nLocation: \;Online - please be advised that this is a two-part webinar and delegates will be r equired to attend Part 1 in order to attend Part 2.
\nSpeaker s: \;Kelly Van Lancker \;(Ghent University)\, Il ya Lipkovich \;(Eli Lilly)\, Martin Ho \;(Pfizer)\, Alex Ocampo \;(Novartis)\, Stephen Ruberg \;(Anal ytix Thinking\, LLC)\, Yongming Qu \;(Eli Lilly)\, Sean Yiu \;(Roche)\, and Martin Linder \;(Novo Nordisk).
\n
\n
Who is this event intended for?&nbs
p\;Statisticians with an interest in understanding causal inference method
s or in applying these to practical situations in drug development
\n
What is the benefit of attending? \;To understand the
potential of the practical application of causal inference methods in dru
g development and be able to apply these to real world problems or clinica
l trials.
Cost
\nThis webinar is free of charge to both Me mbers and Non-Members of PSI.
\nRegistration
\nTo register f or this event\, please click here.
\nOverview
\nThe event wi ll be structured as two webinars in consecutive weeks\, each of 2.5 hours.
\nThe first webinar will provide an introduction to causal inferenc e ideas and methods and how these relate to the estimand framework in both the setting of RCTs or real world data. Graphical methods for communicati ng causal networks will also be outlined.
\nThe second webinar is a imed at illustrating real practical applications in drug development using case studies of how such ideas can provide valuable understanding of the effects of treatments in the presence of intercurrent events or where effe cts may be mediated by intermediate factors.
\n- \n
- Da
y 1\, 6th December 2023: Introduction to the Use of Causal Inference in Dr
ug Development\n
- \n
- Kelly van Lancker (Ghent Un iversity) - The Role of Causal Inference in Clinical Trials: An Introducti on \n
- Ilya Lipkovich (Eli Lilly) - Causal Inference and Est imands in Clinical Trials \n
- Martin Ho (Pfizer) - A Causal Inference Roadmap for Generating RWE in Regulatory Context: An Introductio n and Illustration \n
- Alex Ocampo (Novartis) - Single-World
Intervention Graphs for Defining\, Identifying\, and Communicating Estima
nds in Clinical Trials\n
\;
\n \n
\n - Day 2\, 14th December 2023: Case studies\n
- \n
- Stephen Ruberg (Analytix thinking) / Yongming Qu (Eli Lilly) - Estimating Treatment Effects in Patients Who Adhere to Trea tment \n
- Sean Yiu (Roche) - Comparative safety analysis of time-varying exposures in post marketing observational studies \n
- Martin Linder (Novo Nordisk) - Mediation analysis for a cardiovascu lar outcome trial \n
- Panel Discussion with all speakers fro m both days \n
\n
Speaker details
\n< table border="1" cellspacing="0" cellpadding="0">\n\n| \n Speak er \n | \n \n Biography \n | \n \n
Abstract \n | \n
| \n
| \n \n
Dr. Kelly Van Lancker is a postdoctoral researcher in biostat istics at Ghent University\, Belgium\, where she also obtained her PhD. Pr eviously\, Kelly was a postdoctoral researcher at the Johns Hopkins Bloomb erg School of Public Health. Her goal is to develop innovative designs and analytical techniques for drawing causal inferences in health sciences. A big part of her research focuses on more accurate and faster decision-mak ing in randomized clinical trials by making optimal use of the available d ata. She thereby mainly focuses on covariate adjustment\, data-adaptive me thods\, complex designs\, estimands and especially a combination of these topics. Her recent research is primarily aimed at learning about the oppor tunities and challenges in running pragmatic trials within clinical practi ce\, and developing better prediction tools for personalized medicine. \n | \n \
n The role of causal inference in clinical trials: a n introduction \nIn light of the recently publi shed ICH E9(R1) guideline on estimands and sensitivity analysis (2019) and the FDA draft guideline on covariate adjustment (2023)\, causal inference is progressively taking a more prominent role in the landscape of global drug development. In this talk we will try to bridge the gap between commu nities by elaborating on how this field provides a convenient\, unifying f ramework\, language and relevant tools to formally establish causal relati onships. We will hereby illustrate how causal thinking\, combined with imp ortant tools such as potential outcomes\, can facilitate defining\, identi fying and estimating treatment effects. Building on this\, we discuss the role of causal inference in different trial settings\, including targeting intention-to-treat effects with covariate adjustment\, handling intercurr ent events and the incorporation of external control data. \n | \n
| \n
| \n
\n Ilya Lipkovich is a Sr. Research Advisor at Eli Lilly and Company. Ilya receive d his Ph.D. in Statistics from Virginia Tech in 2002 and has >\; 20 year s of statistical consulting experience in pharmaceutical industry. He is a n ASA Fellow and published on subgroup identification in clinical data\, a nalysis with missing data\, and causal inference. \n | \n
\n This presentation revisits recent ICH E9 (R1) Addendum on Estimand s and Sensitivity Analysis in Clinical Trials and discusses various strate gies for handling intercurrent events (ICEs) using the causal inference fr amework. The language of potential outcomes (PO) is widely accepted in the causal inference literature but is not yet recognized in the clinical tri al community and was not used in defining causal estimands in ICH E9(R1). I will try to bridge the gap between the causal inference community and cl inical trialists by advancing the use of causal estimands in clinical tria l settings and illustrate how concepts from causal literature\, such as PO s and dynamic treatment regimens\, can facilitate defining and implementin g causal estimands for different types of outcomes providing a unifying la nguage for both observational and randomized clinical trials. I emphasize the need for a mix of strategies in handling different types of ICEs\, rat her than taking one-strategy-fit-all approach and suggest that hypothetica l strategies should be used more broadly and provide examples of different hypothetical strategies for different types of ICEs. \n \n |
| \n
| \n \n Martin Ho is an ASA Fellow\, and a Senior Director of RWE Rare Disease\, Evidence Generation Platform at Pfiz er\, leading all RWE activities for Sickle Cell Disease assets. Prior\, he was the head of biostatistics at Google\, LLC for 2 years and served the public at the U.S. FDA for 13 years\, with the last 3 years as Associate D irector of the Office of Biostatistics and Epidemiology at the Center for Biologics Evaluation and Research. Before joining the U.S. FDA\, he worked as senior biostatisticians in contract research organizations for clinica l studies. He co-led the RWE Scientific Working Group of the ASA Biopharma ceutical Section and the Working Group published 5 papers in landscape ass essments as well as state of the science prospects of RWE for regulatory c onsiderations. One of the papers introduces a casual inference roadmap for RWE design and analysis in regulatory context. \n | \n
\n A Causal Inference Roadmap for Generating RWE in Regulatory Context: An I ntroduction and Illustration \nAs real-world da ta (RWD) become more readily available\, the regulatory agencies\, medical product developers\, and other key stakeholders has increasing interests in exploring the use of real-world evidence (RWE) to support regulatory de cisions alternative to traditional clinical trials. To facilitate and prom ote statistical research in design\, analysis\, and interpretation of RWE studies for regulatory decision making\, the ASA Biopharmaceutical Section established the RWE Scientific Working Group to address challenges and id entify opportunities in the statistical research of this area. In a Workin g Group publication in 2022\, Ho and colleagues (DOI 10.1080/19466315.2021 .1883475) have proposed a causal inference roadmap for study design and an alysis that generates RWE for regulatory considerations. In this talk\, Ma rtin will briefly review the steps of the roadmap before using an example to illustrate how to apply the roadmap to generate RWE for regulatory cons ideration. \n | \n
| \n
| \n \n I am currently a statistician with Novartis based in Ba sel\, Switzerland. I obtained my Bachelor&rsquo\;s degree in Statistics fr om the University of Michigan in my hometown of Ann Arbor and then a Ph.D. in Biostatistics from Harvard University in 2020. My doctoral dissertatio n focused on statistical methods for dealing with missing data when the &l dquo\;Missing at Random&rdquo\; assumption does not hold. My current work at Novartis focuses on leveraging causal reasoning in the pharmaceutical i ndustry. \n | \n \n Single-World Intervention Graphs for D efining\, Identifying\, and Communicating Estimands in Clinical Trials \nConfusion often arises when attempting to articu late target estimand(s) of a clinical trial in plain language. We aim to r ectify this confusion by using a type of causal graph called the Single-Wo rld Intervention Graph (SWIG) to provide a visual representation of the es timand that can be effectively communicated to interdisciplinary stakehold ers. These graphs not only display estimands\, but also illustrate the ass umptions under which a causal estimand is identifiable by presenting the g raphical relationships between the treatment\, intercurrent events\, and c linical outcomes. To demonstrate its usefulness in pharmaceutical research \, we present examples of SWIGs for various intercurrent event strategies specified in the ICH E9(R1) addendum\, as well as an example from a real-w orld clinical trial for chronic pain. LaTeX code to generate all the SWIGs shown is this paper is made available. We advocate clinical trialists ado pt the use of SWIGs in their estimand discussions during the planning stag es of their studies. \n | \n
| \n <
img src="https://www.psiweb.org/images/default-source/default-album/stevee
dit5a02c9ff3ad665b3a176ff00001f6b97.png?sfvrsn=9fd4acdb_0&\;sf_site_tem
p=true&\;sf_site=00000000-0000-0000-0000-000000000000&\;MaxWidth=160
&\;MaxHeight=&\;ScaleUp=false&\;Quality=High&\;Method=ResizeFi
tToAreaArguments&\;Signature=3873898235BCBD7842DC89D4936F24AE" data-met
hod="ResizeFitToAreaArguments" data-customsizemethodproperties="{'MaxWidth
':'160'\,'MaxHeight':''\,'ScaleUp':false\,'Quality':'High'}" data-displaym
ode="Custom" alt="Steveedit" title="Steveedit" /> | \n \n Stephen Ruberg\, PhD spent 38 years in t he pharmaceutical industry and is currently the founder and President of A nalytix Thinking\, a consulting company dedicated to advancing the use of statistics in the design of clinical trials\, the conduct of analysis\, an d the interpretation of scientific data. His present interests are in esti mands\, subgroup identification\, Bayesian statistics and digital medicine . He is a Fellow of the American Statistical Association\, the Internation al Statistics Institute and was a member of an advisory committee to the S ecretary of Health and Human Services in the US federal government. \n | \n \n
Estimating Treatment Effects in Patients Who Adhere t o Treatment (Part 1) \nThe estimation of treatm ent effects has traditionally been based on the value of randomization and the causal inference it confers. However\, causal inference from randomiz ed controlled trials requires that all patients be analyzed as randomized AND\, importantly\, that all patients be followed for the duration of the trial and the primary outcome measured. Since many large or long-term tria ls involve patients who discontinue the study or discontinue their study t reatment\, this approach &ndash\; often called intent-to-treat (ITT) &ndas h\; actually becomes an estimate of the effect of initiating (or being ass igned) a treatment and NOT the effect of actually taking the treatment\, w hich we call the direct treatment effect. An alternative approach is to ce nsor the data from the time of treatment deviation and impute the resultin g missing values (e.g.\, a hypothetical strategy). This approach uses all randomized patients but requires strong assumption on the potential outcom e after the deviation away from the randomized treatment. While ICH-E9 rec ommended the ITT approach in general (or at least the use of all randomize d patients in the analysis)\, ICH-E9(R1) has opened the door to other poss ible estimands and strategies for estimating a treatment effect. One such alternative is the direct treatment effect in patients (principal stratum) who actually would take/adhere to a treatment (Adherers Average Causal Ef fect &ndash\; AdACE). This lecture will be divided into two parts: the fir st will motivate why such an estimand is of major importance\, and the sec ond will provide technical details on its estimation using causal inferenc e methods. Examples will be given to highlight the methods\, the code need ed\, and the interpretation of such the AdACE estimate. \n < /td>\n |
| \n
| \n \n Yongming Qu is currently a Vice President at Eli Lilly and Company. He received his PhD in Statistics fro m Iowa State University in 2002. He has made significant contributions in all phases of clinical development at Lilly and has been active in researc h for using novel analytics and statistical methods in drug development. H e is a Fellow of American Statistical Association. \n | \
n \n
| \n
| \n Sean is a Pr incipal Statistical Scientist at Roche\, UK. Prior to this\, he was a Rese arch Associate at the MRC Biostatistics Unit\, University of Cambridge\, w hich is also where he obtained his PhD in biostatistics. At Roche\, Sean w orks on establishing new endpoints in neuroscience\, understanding the ope rating characteristics of treatments on clinical outcomes through characte rizing drug concentration-response relationships and disentangling distinc t pathways from treatment to outcomes via potential mediators\, as well as on real world observational studies for making indirect treatment compari sons and estimating long-term treatment effects. He also supports the cond uct of ongoing Phase 3 and post marketing requirement studies in multiple sclerosis as a study statistician\, and collaborates with academics\, exte rnal companies and multiple sclerosis registries in his projects. His rese arch interests include longitudinal data\, causal inference\, missing data and composite endpoints. \n | \n \n Comparative safety an alysis of time-varying exposures in post marketing observational studies \nHealth authorities often mandate license holde rs of approved treatments to conduct post marketing observational studies to sufficiently assess long-term risk of important safety events\, e.g. ma lignancies\, since randomized clinical trials are typically too short and underpowered to detect treatment effects on such events. Furthermore\, com parative safety analysis of newly approved versus other already approved t reatments may be requested as part of the post marketing requirement. Howe ver\, performing comparative safety analysis of long-term observational st udies where treatment assignment is based on clinical practice is challeng ing and not well established in the regulatory setting\, particularly when treatment switching (from control to active and vice versa) is anticipate d to be frequent and often occurs prior to safety events of interest. Usin g a case study for OCREVUS\, which is an approved treatment for adult pati ents with relapsing or primary progressive forms of multiple sclerosis\, I will describe one specific post marketing requirement from the FDA on com parative safety analysis\, the challenges of performing such analyses in t he presence of multiple treatment switching\, and highlight severe limitat ions of conventional methods based on time fixed treatments. I will then d escribe how established methodology for drawing causal inferences for the effects of time-varying exposures in the presence of time-dependent confou nding\, e.g. marginal structural Cox models\, can address limitations of t he conventional methods\, and provide feedback from the FDA on the use of causal inference methodology in this observational setting. \n | \n |
| \n
| \n
\n Martin is a s tatistician with close to 15 years experience in the pharmaceutical indust ry and currently employed by Novo Nordisk A/S. He combines regular activit ies in clinical trials with an interest in statistical methodology\, inclu ding the use of causal inference. \n | \n \n Mediation ana lysis for a cardiovascular outcome trial \nTher e is a growing interest in statistical analyses that can answer questions concerning how a drug may affect an outcome via intermediate variables (me diators). The LEADER trial is an example. The trial showed a beneficial ef fect of the drug liraglutide on cardiovascular outcome in people with type 2 diabetes and high cardiovascular risk. Key opinion leaders as well as r egulatory agencies asked whether the effect on cardiovascular outcome coul d be explained by previously known effects of liraglutide on blood glucose levels or body weight. The question is best answered within the framework of causal inference which provides methods for statistical analysis but a lso clarifies the assumptions necessary for a meaningful interpretation of the results. \nIn this presentation\, we will consider some selected methods for causal mediation analysis that will be applied t o the LEADER data. The methods include an approach developed jointly with experts from academia which specifically handles the case where the outcom e is a time-to-event variable and the mediator is repeatedly measured. \n | \n
END:VEVENT END:VCALENDAR