Newsletter for Statistical Programmers and Biostatisticians #58

STATISTICAL PROGRAMMING

Jalender Musku and Srinivas Tiyyagura - Blinded studies and challenges. Presented last year in SESUG and will be presented this year on PharmaSUG! Please, check here - Link

Mazi ?? Ntintelo has published recently a few posts:

• If you've recently transitioned from #SAS 9 to #SAS Viya, you'll soon realize that the datastep doesn't behave in the same way when executing on the #CAS server. Learn more about differences here - Link
• A problem to solve.The question read as follows: “Suppose we have 100 SAS datasets in a library, out of which 30 datasets have a common variable and we would like to apply format on that variable for all 30 datasets. What are the possible way to do it.” Link
• Creating a simple AE summary table. Link
• Alo check his advice for juniors - One of the top questions I still receive from connections is how to learn #SAS programming from scratch. Link

Mantsoe Justice Ramatsa wrote about hash objects - It is a dynamic data structure controlled during execution time from the DATA step (or the DS2 procedure) environment. The hash object provides an efficient method for quick data storage and data retrieval. Using a common set of lookup keys, hash objects can be used to retrieve data, store data, merge or join tables of data, and split a single table into multiple tables. Learn more here - Link

Roman Gryzodub - Great news for Statistical Programmers and Clinical Trial Analysts! Customized ChatGPT, the Clinical Trials Analyst, is now available in the GPT Store. Designed for SAS, R, Python programming and in line with CDISC standards, it provides efficient, code-centric support for clinical trials analysis. Link

Imam Jaffer - has shared a PHUSE 2020 paper from Vipin Kumpawat (PhD) , Clinical Data Analysis- Creating a CDISC - ADaM standard: Subject Level Data (ADSL) dataset using R. Link

Learnings from the First R-Based Submission to FDA by Novo Nordisk. Novo Nordisk set a standard in regulatory submissions to the hashtag#FDA. The company achieved a milestone by completing the first-ever submission using R, a statistical programming language. Link

Sam Hume - This post explains the rationale for creating a dataset exchange format using JSON instead of alternative file formats. The PHUSE/CDISC/FDA Dataset-JSON as Alternative Transport Format for Regulatory Submissions pilot project is the motivation for the post. Responses from pilot participants have been very positive, but we have received a few comments about alternative file formats. This post answers the question: Why JSON? Link

Pharmaverse blog - Testing Containers and WebAssembly in Submissions to the FDA

In this post, we dig into the ongoing efforts undertaken to evaluate new technologies for submissions to the Food and Drug Administration (FDA). These transformative approaches, including WebAssembly and containers, hold immense potential to transform the regulatory landscape and streamline the submission process. Link

BIOSTATISTICS

Robert Rachford and his advice for Biostatisticians - Learn as much as possible about the Investigational Product (IP) your clinical trial(s) are studying. The clinical trial is being run specifically for the IP. It is important to understand how it works, why it is needed, etc. so the clinical trial can be set up for success (at least, as much as it can - some products just don't work and that is not dependent upon the clinical trial team). Learn more directly from his posts - Link

Thanks to Ryan Batten, PhD(c) for sharing a few articles:

• Propensity score matching is often used with real-world data. Choosing what caliper width to use is crucial. Why?The caliper width decides how "close" matched pairs are. So why not pick a narrow caliper? The participants will be more similar but will have increased variance of the treatment effect. So what's the answer to balance between wide vs narrow? (aka the variance-bias tradeoff in this situation). An article that helped me with this for differences in means & proportions is Austin (2011). It gave a good introduction into why this is important and I was able to try simulating examples for myself. It also gives a case study using real data. Link
• Correctly specifying the confounder-exposure and?confounder-outcome relationship is important for valid inferences. Why?If they aren't properly specified it could introduce bias.A confounder is a variable that affects both the exposure and outcome. So it's important to look at both of those relationships!An article that helped me understand this better was Schuster et al. (2023). It goes over four scenarios and measures model performance. Link
• Hazard ratios can be problematic for causal inference. An alternative is the restricted mean survival time. Why? Three advantages: RMST is valid under any of the time-to-event distributions. - Doesn't require the proportional hazards assumption to be met. - It's a measure of survival time (easier to interpret). An article that helped me learn about RMST was Royston & Parmar (2013). Recommend reading if interested about an alternative to HRs! Link

Darko Medin writes about Frequentist framework advantages in Statistics (in areas where its applicable). Frequentist framework advantages, why its been here for decades and still one of the best standards in most research areas, from life science to econometrics. Tried to write the article using intuitive language without formulas and complex terminology. In the focus experiment, scientific defensibility, testability, reproducibility. Some examples such as why Bayesian priors could introduce bias in an RCT vs why its more objective to use Frequentist framework for phase III RCTs and avoid such bias, and why being falsifiable (empirically testable) is very important. Some discussion on fixed vs random variable parameters too. Link

Quantification of follow-up time in oncology clinical trials with a time-to-event endpoint: Asking the right questions. In this paper, inspired by the estimand framework, we formulate a comprehensive list of relevant scientific questions that trialists have when reporting time-to-event data. We illustrate how these questions should be answered, and that reference to an unclearly defined follow-up quantity is not needed at all. In drug development, key decisions are made based on randomized controlled trials, and we therefore also discuss relevant scientific questions not only when looking at a time-to-event endpoint in one group, but also for comparisons. We find that different thinking about some of the relevant scientific questions around follow-up is required depending on whether a proportional hazards assumption can be made or other patterns of survival functions are anticipated, for example, delayed separation, crossing survival functions, or the potential for cure. From Kaspar Rufibach , Lynda Grinsted , Jiang Li , Hans-Jochen Weber , Cheng Zheng , Jiangxiu Zhou - Link

Adaptive phase I–II clinical trial designs identifying optimal biological doses for targeted agents and immunotherapies. This review article examines several innovative phase I–II clinical trial designs that utilize accumulated efficacy and toxicity outcomes to adaptively determine doses for subsequent patients and identify the optimal biological dose, maximizing the overall therapeutic effect. Specifically, we highlight three categories of phase I–II designs: efficacy-driven, utility-based, and designs incorporating multiple efficacy endpoints. For each design, we review the dose–outcome model, the definition of the optimal biological dose, the dose-finding algorithm, and the software for trial implementation. To illustrate the concepts, we also present two real phase I–II trial examples utilizing the EffTox and ISO designs. From yong zang , Beibei Guo, Yingjie Qiu, Hao Liu, Mateusz Opyrchal , and Xiongbin Lu - LINK

Statistical and practical considerations in planning and conduct of dose-optimization trials. Dose optimization is a challenging task that involves a variety of factors and is considerably more complicated than identifying the maximum tolerated dose, both in terms of design and implementation. This article provides a comprehensive review of various design strategies for dose-optimization trials, including phase 1/2 and 2/3 designs, and highlights their respective advantages and disadvantages. In addition, practical considerations for selecting an appropriate design and planning and executing the trial are discussed. The article also presents freely available software tools that can be utilized for designing and implementing dose-optimization trials. The approaches and their implementation are illustrated through real-world examples. From Ying Yuan , Heng Zhou, and Suyu Liu - Link

Andrea Vele has recommended Defining Clinical Trial Estimands: A Practical Guide for Study Teams with Examples Based on a Psychiatric Disorder. This paper describes an interdisciplinary process for implementing the estimand framework, devised by the Estimands and Missing Data Working Group (a group with clinical, statistical, and regulatory representation) of the International Society for CNS Clinical Trials and Methodology. This process is illustrated by specific examples using various types of hypothetical trials evaluating a treatment for major depressive disorder. Each of the estimand examples follows the same template and features all steps of the proposed process, including identifying the trial stakeholder(s), the decisions they need to make about the investigated treatment in their specific role and the questions that would support their decision making. Link

REAL WORLD EVIDENCE

Gerd Rippin - External Comparator Cohort studies - clarification of terminology. There is diverse terminology about External Comparator studies, including the terms historical control study, synthetic control study, externally controlled trial and external comparator cohort / arm study. We discuss in this new publication differences in terminology and whether there is preferred nomenclature to avoid unintended implications or inaccurate perceptions. Link

Thomas Debray, PhD has published an article together with his team. Visualizing the target estimand in comparative effectiveness studies with multiple treatments. When using the propensity score to compare the effectiveness of multiple treatments, ambiguity may arise about the interpretation of estimated treatment effects. In this publication we illustrate how simple visualizations can be used to clarify to whom results about the benefit of different treatment options apply. The research was conducted by Gabrielle Simoneau, Marian Mitroiu, Wei Wei, Stan Wijn, Joana Caldas Magalhaes, Justin Bohn, Changyu Shen, Fabio Pellegrini and Carl de Moor. Link

Hengwei Liu has shared a very interesting article written by Benjamin D Bray and Sreeram V Ramagopalan. R WE ready for reimbursement? A round up of developments in real-world evidence relating to health technology assessment. In this latest update we highlight: a publication from the US FDA regarding the definitions of real-world data (RWD) and real-world evidence (RWE); a publication from academic researchers on a demonstration project for target trial emulation; a publication from the National Institute of Health and Care Excellence (NICE) on the 1?year anniversary of their RWE framework; and a publication from NICE and Flatiron Health on the utility of US RWD for initial?UK health technology assessment decision making. Link

Quantitative bias analysis for external control arms using real-world data in clinical trials: a primer for clinical researchers. Kristian Thorlund, Stephen J. Duffield, Sanjay Popat, Sreeram Ramagopalan, Alind Gupta, Grace Hsu, Paul Arora, Vivek Subbiah, MD Journal of Comparative Effectiveness Research. We illustrate how QBA is used to ascertain robustness of results despite a large proportion of missing data on baseline ECOG performance status and suspicion of unknown confounding. The robustness of findings is illustrated by showing that no meaningful change to the comparative effect was observed across several ‘tipping-point’ scenario analyses, and by showing that suspicion of unknown confounding was ruled out by use of E-values. Full R code is also provided. Link

Freshly published! Understand how to address bias from studies using real-world data, "Quantitative Bias Analysis for External Control Arms using Real World Data – A Must-Read Primer for Clinical Researchers." External control arms leveraging real-world data are a game-changer in comparative studies, however navigating the complexities from imperfect data is tough.??Quantitative Bias Analysis (QBA) can elevate real-world analytics research by improving scientists’ understanding of the robustness of study results.?Cytel authors: Kristian Thorlund, Alind Gupta, Grace Hsu. Link?

EVENTS/WEBINARS

Stefano Vezzoli - The Italian BIostatistics Group is glad to share the final agenda of the 2024 IBIG Journal Club. The six-webinar series will start in March and end in December and all webinars will be in English. This series presents an excellent opportunity to explore a diverse range of trending topics and engage with speakers from both academia and the industry.The fee is 60€ for SIMeF members and 120€ (+VAT) for non-SIMeF members. With our best regards, The IBIG Journal Club Scientific Committee: Stefano Vezzoli, Meike Adani, Giovanni Nattino, Marco Costantini, Veronica Sciannameo - Link

Register for The Effective Statistician Conference 2024 with Dr. Alexander Schacht ! It is for everyone who wants to know more about effective statistics and its extensive use in making a progressive and productive society.

The best thing about this conference is that it is completely FREE OF CHARGE!

With top speakers included in the program, you are surely going to get the best out of your time and improve your perception of progressive statistics.

With Guest Speakers Anja Schiel, Andy Grieve and many other respected statisticians in the industry. Link

Sunil Gupta - Webinar. Move over Data Science, R is ready for Clinical Trials!Understanding the potential of R programming for clinical research and its significance in the space that is dominated by SAS.

In this webinar, we intend to help life sciences stakeholders including SAS programmers to better understand how and why R is getting into Clinical Trials. This webinar is designed to answer your fundamental questions and to explain how R transforms the way we review and analyze clinical data. We will also discuss some of the challenges in R programming. Link

Katja Glass - Join?the#OpenStudyBuilder #community #meeting! ?? Date: 26.02. | ?? Time: 13:30-14:20 CEST | ?? Virtual Event Discover?the?power?of?OpenStudyBuilder?through: ?? Interactive Demo: Dive?into?aspects?you?are?interested?in. ?? Q&A Session:?Get?expert?insights?and?answers. ?? Lively?Discussions:?Engage?on?various?subjects. Link

Interview - Gen AI in Pharma and BioTech with Paul Agapow, Director at GSK. Here I have a conversation with Ilya Billig about the possibilities - and problems - for generative AI and large models in the pharmaceutical industry, including the casino nature of drug development, timescales & risk, the challenge of unstructured data, and more. Check it out! Link

BAYES2024, taking place in Rockville, MD, from October 23-25, 2024. Visit https://bayes-pharma.org/ for additional information. The call for abstracts will be announced soon.

EMA Accelerating Clinical Trials in the EU (ACT EU) initiative: slides presented at the ACT EU PA08 multi-stakeholder methodology workshop (Amsterdam, 23 November 2023).

Topics included:- complex clinical trials and use of innovative designs;- paediatric clinical trials;- pragmatic clinical trials;- decentralised clinical trials;- "beyond RCT" approaches;- validation of digital endpoints;- patient centricity, inclusion and representativeness in clinical trials. Link

PHUSE 2024 US Connect 2024 Event Agenda is ready. Check here - Link

7th International Clinical Trials Methodology Conference 2024. ICTMC is the leading international platform for researchers and practitioners to present the very latest in trials methodology. The meeting also offers valuable networking and training opportunities, with 900 delegates from 16 countries attending in 2022. 30 September 2024. Link

Online course "Adaptive Clinical Trial Designs". The course consists of six two-hour online modules released every two months starting in January 2024 and ending in November 2024. Speakers include Thomas Jaki (University of Regensburg), Chris Jennison (University of Bath), Sofia S. Villar (University of Cambridge), Sarah Walker (University College London), Pavel Mozgunov (University of Cambridge).The course is jointly organised by Ecraid and the European Respiratory Society (ERS) and is supported by the EU-funded ECRAID-Base project. Link