\n

\n

\n

\n

\n

\n

\n

\n

\n

\n

\n

\n

\n

\n

Incomplete datasets due to missing data is an issue that h as been\, and will be\, around for a long time. At this meeting we will pr esent the evolution of missing data approaches\, looking at how they have been handled in the past\, the current established missing data approaches and the impact of the new ICH E9 R1 addendum on the handling of missing d ata\, focussing in particular on the treatment policy estimand.

\nYou can now register for this event. Registration fee
s are as follows:

\n- Members of PSI = £\;20+VAT

\n- Non-Me
mbers of PSI = £\;115+VAT*

\n**Please note: Non-Member rate i
ncludes membership for the rest of the 2021 calendar year.*

\nTo
register for the \;session\, please \;**click here**.

**DAY 1 &ndash\; Tuesday 4 ^{th} May 2021**\n \n \n \n \n

**Speaker**

**Biography**

**Abs
tract**

\n Khadija Rantell

\n (MHRA)\n \n \n

Khadija Rantell (nee Rerhou) is a Senior Statistical Ass essor at the Medicines and Healthcare Products Regulatory Agency (MHRA) wh ere she has worked since 2013.

\nKhadija is also a membe r of the EFSPI (European Federation for Statisticians in the Pharmaceutica l Industry) Scientific Committee and a member of the EFPIA/EFSPI Estimands Implementation and Pharmaceutical Industry Biostatistics Working Groups.< /p>\n \n \n

**History of missing data in regulatory settings.
**

The problem of handling missing data has evo lved greatly over the last decade along with statistical methodologies for dealing with missing data. Several recent documents have been developed t hat lay out a set of general principles and techniques for addressing the problems raised by missing data in clinical trials. However\, prospective prevention of missing data occurrence\, through carefully designing and im plementing of a research study\, remains the single best approach. This se ssion will focus on the evolution of regulatory framework for handling mis sing data in confirmatory trials and the impact of the ICH E9 (R1) addendu m on the handling of missing data.

\n \n \n \n \n

\n Jiawei Wei

\n
(Novartis)

Dr. Jiawei Wei joined Novartis in 2011\, where she is currently a Director Biostatistician in the Advanced Methodo logy and Data Science group. She is interested in supporting the methodolo gical development in various areas of pharmaceutical statistics\, includin g estimand\, recurrent event data\, multiple testing\, etc. Before joining Novartis\, Jiawei got her PhD in statistics from Texas A&\;M Universit y in 2010\, and then one year assistant professor. Jiawei is awarded leadi ng scientist at Novartis\, she is associate editor of Statistics in Biopha rmaceutical Research\, and also a part time advisor at Fudan University in China.

\n \n \n**On the role of hypothetical estimand in
clinical trials and its estimation.**

The ICH E9(R1) Addendum on 'Estimands and Sensitivity Analysis in Clinical Trials' introduced various strategies for addressing intercurrent events when def ining the clinical question of interest. For hypothetical estimand strateg ies\, a scenario is envisaged in which the intercurrent event would not oc cur. The value of the variable that reflects the clinical question of inte rest is the value which the variable would have taken in the hypothetical scenario. If a hypothetical strategy is proposed\, it should be made clear what hypothetical scenario is envisaged. The ICH E9(R1) Addendum acknowle dges that a wide variety of hypothetical scenarios can be envisaged\, but it also clarifies that some scenarios are likely to be of more clinical or regulatory interest than others.

\nIn this talk we wil l not only discuss the role of hypothetical estimand in clinical trials\, but also the estimation of hypothetical estimand. One basic consideration is that the estimation of hypothetical estimand requires the prediction of hypothetical trajectories for all patient who have the intercurrent event . Importantly\, the assumptions for the predictions need to be aligned wit h the hypothetical strategy\, which begs the questions: From where or from whom do we borrow information to predict the hypothetical measurements of interest? Do we have sufficient data or information to borrow from? Moreo ver\, the prediction uncertainty needs to be adequately accounted for\, e. g. through multiple predictions. And finally\, sensitivity analyses need t o be performed to investigate the robustness of our conclusions. All the a bove considerations will be discussed and illustrated by a case study.

\n \n \n \n \n

\n
Bohdana Ratitch

\n (Bayer)

Bohdana is a Principal Statistician at Bayer. She has over 15 years of ex perience in biopharmaceutical industry including statistical methodology r esearch and consulting\, with numerous publications in missing data\, esti mands\, subgroup identification\, and machine learning. She is a co-author of two books\, &ldquo\;Estimands\, Estimators and Sensitivity Analysis in Clinical Trials&rdquo\; (2020) and &ldquo\;Clinical Trials with Missing D ata: a Guide for Practitioners&rdquo\; (2014). Bohdana is a member of the DIA SWG on Missing data and EFSPI Subgroup Special Interest Group.

\n \n \n**Statistical Issues and Recommendations for Clinical Tr
ials Conducted During the COVID-19 Pandemic.**

The COVID-19 pandemic continues to impact planned and ongoing clinical tri als. Any study that is conducted in part or in whole during the pandemic m ust anticipate\, assess\, and mitigate these impacts to assure safety of p articipants and address operational issues. From a statistical perspective \, the study teams need to ensure the ability to conduct the trial and col lect data in alignment with the study objectives. Statistical analysis pla ns should incorporate strategies to deal with potential increases or disti nct patterns of treatment discontinuations\, interruptions\, protocol devi ations\, and missing data. In this presentation\, we will discuss potentia l impacts of COVID-19 pandemic disruptions on clinical trials with a focus on statistical aspects and mitigation strategies. It is beneficial to do so in a structured and systematic way through the estimand framework\, reg ardless of whether the estimand is formally defined in the trial protocol. We will also discuss issues of missing data handling and supplemental ana lyses that may be needed for the trial.

\n \n \n \n \n**Day 2 &ndash\; Wednesday 5 ^{th}
May 2021**

\n David Wright (AstraZeneca)

Da vid became the Head of Statistical Innovation at AstraZeneca in September 2016. David leads a team of expert statistical methodologists who advise c olleagues within AstraZeneca on novel trial design and analysis issues. Be tween 1999 and 2016 David worked for the Medicines and Healthcare products Regulatory Agency (MHRA) as a Statistical Assessor and was Chair of the B iostatistics Working Party from 2011-2016. David was heavily involved in t he revision to the CHMP missing data guideline. He is currently involved i n how the ICH E9 Addendum on Estimands impacts the design\, analysis and r eporting of clinical trials within AstraZeneca and is also a member of the EFPIA/EFSPI Estimand Implementation Working group.

\n \n \nICH E9 R1 explains the distinction between treatment di scontinuation and study withdrawal. The former is an intercurrent event wh ilst the latter gives rise to missing data to be addressed in the statisti cal analysis. However\, E9 R1 also states that &ldquo\;methods to address the problem presented by missing data can be selected to align with the es timand&rdquo\;. In this presentation I will stress that in fact the chosen methods should be selected to align with the estimand and failure to do t his would lead to an incoherent analysis strategy. The treatment policy st rategy will be considered and it will be highlighted that there are a numb er of methods of estimation available to address missing data. Which metho ds are fully aligned with the treatment policy estimand will be discussed.

\n \n \n \n \n

\n
James Bell

\n (Elderbrook solutions GmbH)

James originally trained as a chemist\, receiving his PhD fr om the University of Cambridge in 2009. Following a short spell in industr y in computational drug design\, he completed his MSc in statistics at UCL in 2013. Starting at Boehringer Ingelheim\, he spent three years as trial statistician before joining its newly-formed statistical methodology grou p. James now works as a consultant methodology statistician for the CRO El derbrook Solutions GmbH\, providing services to a major pharmaceutical com pany. James is an active member of cross-industry WGs in his two main area s of research\; estimands and missing data handling. Other topics of parti cular interest include event prediction and the process of how clinical tr ials are designed.

\n \n \n**The Practicalities of Treatm
ent Policy Estimation.**

Treatment policy estim ands were introduced by ICH E9(R1) as an approach to include the effects o f intercurrent events within the treatment effect of interest. They have b een commonly thought of as both equivalent to ITT analysis and robust to e stimate. However\, it has become increasingly clear that these properties start to break down in the presence of missing data &ndash\; almost an ine vitability in real clinical trials. Indeed\, due to missing data typically being associated with discontinuation of randomised treatment\, treatment policy estimation will usually deviate from traditional ITT approaches an d in doing so\, situations can easily arise where no reliable estimation i s possible.

\nThis talk will describe the practical diff iculties of treatment policy estimation that arise due to missing data and discuss potential solutions. Topics covered will include trial conduct\, approaches to estimation\, assumptions\, how much data is needed and sampl e size calculations.

\n \n \n \n \n

\n Michae
l O&rsquo\;Kelly &\; Sylvia Li

\n (IQVIA)

Michael O&rsquo\;Kelly has worked as a statistician in the pharmaceu tical industry for 27 years. He has been involved in many areas of biostat istics\, and has a special interest in statistical modelling and simulatio n. He co-authored a Best Practice proposal for projects involving Modellin g and Simulation\, which was adopted by the PSI board in 2017. With collea gues Michael O&rsquo\;Kelly has developed new methods for missing data tha t are now widely used in clinical trials. His book authored with Bohdana R atitch\, &ldquo\;Clinical trials with missing data: a guide for practition ers&rdquo\;\, was published in 2014 by Wiley. He has given courses on miss ing data for PSI and at many conferences and for many pharmaceutical compa nies. For his work in best practice and in missing data\, Michael received the RSS/PSI award for Excellence in Pharmaceutical Statistics in 2017\; h e is Senior Director with IQVIA&rsquo\;s Centre for Statistics in Drug Dev elopment.

\n \n \n**Even a &ldquo\;treatment policy&rdquo
\; estimand may have missing data: how can we take account of this?**

Under the &ldquo\;treatment policy&rdquo\; estimand \, outcomes contribute to the estimate of effect irrespective of treatment actually taken after randomisation\, and all subjects are to be followed up for the full scheduled follow-up period. It is hoped that under this es timand missing data would be limited. However\, in practice\, subjects may avail of their right to discontinue completely from a trial. Even under a &ldquo\;treatment policy&rdquo\; estimand\, this leaves the analyst with missing data. How is the analyst to take account of this residual missing data under the &ldquo\;treatment policy&rdquo\; estimand? The new ICH E9 R 1 Addendum suggests &ldquo\;for subjects who discontinue treatment without further data being collected\, a model may use data from other subjects w ho discontinued treatment but for whom data collection has continued&rdquo \;. However\, numbers of appropriate subjects with data available may be s mall\, and compromises or assumptions may be required to do the kind of mo delling suggested by ICH E9 R1. This presentation evaluates some of the op tions that use statistical modelling to take account of this residual miss ing data.

\n \n \n \n \n

\n Daniel Bratton

\n (GSK)

Dan worked as a statistician at GSK since 2016. During this time h e has worked on RCTs investigating the effect of various treatments in sev ere asthma\, COPD and nasal polyps\, and is now working in trials assessin g therapies for COVID-19. Dan started his career as a medical statistician at the Medical Research Council Clinical Trials Unit (MRC CTU) working on RCTs in respiratory diseases and dermatology. He then completed a PhD at the same unit through UCL investigating statistical issues in the design o f multi-arm multi-stage clinical trials which are increasingly being used in practice to accelerate the evaluation of new therapies. Prior to starti ng at GSK\, Dan worked as a statistician in the Department of Pulmonology at University Hospital Zurich for one year\, focusing mainly on network me ta-analyses of RCTs investigating treatments for sleep apnoea.

\n \n \n**Treatment policy estimands for recurrent event data using
data collected after cessation of randomised treatment.**

Trials now increasingly collect data from subjects following pr emature discontinuation of study treatment\, as this event is irrelevant f or the purposes of a treatment policy estimand. However\, despite efforts to keep subjects in a trial\, some will still choose to withdraw. Publicat ions for sensitivity analyses of recurrent event data have often focused o n reference‐based imputation methods\, more commonly applied to continuous outcomes\, where imputation for the missing data for one treatment arm is based on the observed outcomes in another arm. The existence of data foll owing premature discontinuation of treatment now raises the opportunity to impute missing data for subjects who withdraw from study using this obser ved &lsquo\;off-treatment&rsquo\; data\, potentially allowing more plausib le assumptions for the missing post‐study‐withdrawal data than other refer ence‐based approaches. In this poster\, we describe a recent imputation me thod (1) for recurrent event data in which the missing post‐study‐withdraw al event rate for a subject is assumed to reflect the rate observed from s ubjects during the off‐treatment period. The method is illustrated in a tr ial in chronic obstructive pulmonary disease (COPD\; GSK funded NCT0210596 1) where the primary endpoint was the rate of exacerbations\, analysed usi ng a negative binomial model.

\n \n \n < /tbody>\n\n\n

\n

\n

\n