Lea Vaas

The replacement of concurrent control animals by so-called Virtual Control Groups (VCGs) may reduce the use of animals in systemic toxicity studies and contributes to the 3R's principle of animal experimentation. However, the idea of replacing living beings with virtual data from historical data sets has so far not been introduced into the design of regulatory animal studies. Major steps facilitating review of methodology for derivation of ViCoGs from historical control data and performance testing in statistical analysis, are the collection, curation and sharing of suitable sets of historical control data from preclinical toxicity studies. This talk will summarize accomplished and ongoing efforts for cross-industry provision of data resources, standardization and curation activities and line out both general ideas and specific methodology for derivation of ViCoGs. Moreover, a discussion of advantages, pitfalls, real-world examples, potential solutions is given and ideas for transferring these insights into regulations and guidelines are presented.

Professor Nick Andrews

With an increasing number of vaccines recommended in pregnancy it is important to consider how best to evaluate safety. There are particular challenges in assessing safety in pregnancy such as healthy vaccinee effects, immortal time bias and biases introduced in the days close to birth. In this talk I will discuss these challenges and consider different designs with pros and cons, this will include presenting a study I have done using a nested case -control study within a cohort for Covid-19 vaccine safety and plans for a target trial emulation approach for assessing RSV vaccine in pregnancy.

Sanne Roels, Tim Morris, Kelly van Lancker (hosts) Kaspar Rufibach (Merck), Susan Gruber (TL revolution) and Florian Lasch (EMA)

First, Kaspar Rufibach (Merck) shared his perspectives on opportunities to apply causal methods. Next, Susan Gruber (TL revolution) discussed targeted learning as a framework to address causal questions and the importance of sensitivity analyses. Finally, Florian Lasch (EMA) discussed both the importance of the causal inference angle in determining estimands, and will discuss a case study.  The webinar ended with a panel discussion. 

Several design choices must be made while creating a visualisation. Bar chart or line plot? Faceted plots or overplotting? Should there be used multiple colours? And if yes, what colour scheme is best? How to optimize axes, legend, background and title? See the step-by-step improvement. The next challenge will be about intra- and interrater reliability. See the Wonderful Wednesday homepage for more detail.

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Zachary Skrivanek, Lorenz Uhlmann, Steve Mallett, Rhys Warham, Mark Baillie, Paolo Eusebi, Martin Brown, Benjamin Lang

Margaret Gamalo, Cordula Zeller, Patrick Schlömer, Dali Zhou

This webinar discusses the complexities and opportunities of clinical trials with hierarchical composite endpoints, covering topics such as win odds, win ratio, net benefit as well as regulatory considerations when defining hierarchical composite endpoints. This webinar starts with a general introduction to hierarchical composite endpoints and an overview of common analysis methods including win ratio, win odds, and net benefit. Then, the practical considerations are illustrated through case studies from clinical trials in heart failure and chronic kidney disease. The webinar concludes with a discussion and a Q&A.

In this webinar we will review the range of statistical methodologies used to harness the potential of Real-World Data (RWD) in clinical development, particularly in the context of rare diseases and small populations like paediatrics. The session will include theoretical understanding and practical case studies, with a special focus on Bayesian methods and causal inference.    

The interactive Shiny application DoRiS was specifically designed to explore the dose-response in subgroups. It combines the display of summary level data, individual data, and statistical probability. Other proposals were to use augmented box plots, combined box and violin plots, or matrix plots across the subgroup factors.

The next challenge is about improving a plot of longitudinal data. See the Wonderful Wednesday homepage for more detail.

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Zachary Skrivanek, Lorenz Uhlmann, Steve Mallett, Rhys Warham, Mark Baillie, Paolo Eusebi, Martin Brown, Benjamin Lang

Phil Kay and Chandramouli Ramnarayanan, JMP

Advances in AI, lab automation and closed-loop optimization promise big productivity gains for pharma R&D. But experimenting with maximum efficiency - that is, the least number of runs - will always be important. This is especially true where there is an ethical imperative, such as in pre-clinical animal experiments.  Recent advances in statistical Design Of Experiments (DOE) including Definitive Screening Designs (DSDs) and the broader class of Orthogonal Minimally Aliasing Response Surface (OMARS) designs have given us new options for understanding complex systems with small experiments. Self-Validated Ensemble Modelling (SVEM) is an innovative analysis approach that applies ideas from Machine Learning to small data from designed experiments. In this presentation we will show how SVEM works and how it can overcome common challenges when you are building useful models of complex systems from small experiments.

PSI Journal Club presents “Subgroup and Covariate Analysis”. Chaired by Chris Harbron with presentations from: Thomas Jemielita: - Investigating Stability in Subgroup Identification for Stratified Medicine and Björn Holzhauer: - “Super-covariates”: Using predicted control group outcome as a covariate in randomized clinical trials.

Many cancer trials use the progression free survival as primary outcome measure, i.e. the length of time that a patient lives on without worsening of the disease. Various reasons can lead to censoring of the data. And differential censoring could influence the interpretation of the results. Paolo Eusebi presents visualisations that help to explore the pattern of events and reasons for censoring. Visualisations are available on the Wonderful Wednesday blog.

The basic plot for progression free survival is the survival plot using Kaplan-Meier estimates. Augmented with information on censoring this gives a great overview. An innovative way of displaying events and censoring is by stacked lollipop plot. See the panel discussing pros and cons. The next challenge is about visualising dose response in subgroups for personalized dosing. See the Wonderful Wednesday homepage for more detail.

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Zachary Skrivanek, Lorenz Uhlmann, Steve Mallett, Rhys Warham, Mark Baillie, Paolo Eusebi, Martin Brown, Benjamin Lang

The development of a new patient reported outcome (PRO) needs to include the interpretation of the results. It should be possible to define a minimal clinically important difference and a meaningful between-group difference. Rhys Warham is presenting ways how visualisations can support that process. They are available on the Wonderful Wednesday blog.

For comparing the new PRO with the gold standard eCDF plots and PDF plots can be shown overlapping or stacked. There are also many different ways to show the distribution of within the standard ratings to easily spot differences or possible inconsistencies. The next challenge is on the event pattern in a study aiming for improvement on progression free survival. See the Wonderful Wednesday homepage for more detail.

Wonderful Wednesdays are brought to you by the Visualisation SIG. The Wonderful Wednesday team includes: Bodo Kirsch, Zachary Skrivanek, Lorenz Uhlmann, Steve Mallett, Rhys Warham, Mark Baillie, Paolo Eusebi, Martin Brown, Benjamin Lang

Avery McIntosh (Pfizer) and Oleksandr Sverdlov (Novartis)

This webinar will help listeners gain a broader understanding of a recent and rapidly advancing core area of pharmaceutical drug development. The content will be broad, but will focus on clinical design and analysis strategies for advanced therapeutics such as cell/gene therapies, and strategic options to advance candidate drugs in this space.

One of the recent advances in 21st century medicine is the emergence of gene therapies, drugs that affect the basic biology of genetic disease. The field has seen some notable setbacks in the past, but in recent years has exploded as decades of basic science have been successfully translated into the most complex biologics ever constructed, leading to regulatory approval of several gene therapy products in oncology, hematology, neurology, and ophthalmology indications. These drugs are at the apex of biological manufacturing complexity, and have the potential to be disease modifying or even curative. Evidence-based and innovative quantitative clinical development and lifecycle management strategies will be required as fixtures in the development for these unique drugs in order to reach patients in need. In this webinar we provide an overview of the history and future of gene therapies, and discuss the crucial role of the statistician in the drug development process of these drugs, with a focus on innovative trial design and analysis techniques.

A list of useful references from the presentation can be found below:
- McIntosh, Avery, and Oleksandr Sverdlov, eds. Development of Gene Therapies: Strategic, Scientific, Regulatory, and Access Considerations. CRC Press, 2024.
- Rohde, Maximilian, et al. "Practical and Statistical Considerations for the Long Term Follow‐Up of Gene Therapy Trial Participants." Clinical Pharmacology & Therapeutics 115.1 (2024): 139-146.
- McIntosh, Avery, et al. "Clinical design and analysis strategies for the development of gene therapies: considerations for quantitative drug development in the age of genetic medicine." Clinical Pharmacology & Therapeutics 110.5 (2021): 1207-1215.
- Mueller, Arne, et al. "Digital endpoints for self‐administered home‐based functional assessment in pediatric Friedreich’s ataxia." Annals of Clinical and Translational Neurology 8.9 (2021): 1845-1856.
- Hudry, Eloise, and Luk H. Vandenberghe. "Therapeutic AAV gene transfer to the nervous system: a clinical reality." Neuron 101.5 (2019): 839-862.
- Cox, Gerald F. "The art and science of choosing efficacy endpoints for rare disease clinical trials." American Journal of Medical Genetics Part A 176.4 (2018): 759-772