Network Update Statistical Programming and Biostatistics #61

Programming

Bartosz Jab?oński - The SAS Packages Framework, version 20240529, is ready.

Release changes:

- aesthetic changes in log when running?%generatePackage()?macro,

- reshaped format of an automatic documentation header,

- little bug fix for automatic documentation generation.

Please, see the original post - Link

David Bosak - Replicating SAS? Procedures in R with the PROCS Package. The paper I wrote for #PharmaSUG on the procs package. This package replicates some SAS procedures. If you know SAS and are trying to learn R, this package can help you. Link

Thomas Charlon MEng PhD - sgraph: Graph Visualization Using 'sigma.js'. New R package has been published on CRAN !The sgraph package enables you to use the latest stable release of Sigma.js v2.4.0 to make awesome interactive graphs. CRAN Link

Darko Medin - has published the third part of Meta-analysis in R practical tutorial. Main topic is separating the indirect and direct evidence using the 'netmeta' R package and perspectives on their interpretation. I also show here how to make the forest plots showing all 3 types : indirect, direct and network evidence on the same forest plot and how to show the indirect evidence for comparisons that were not directly made in the study pool. Link

Joachim Schork - Regression outputs contain many different components, each providing crucial insights into the effectiveness and characteristics of the model.

Joachim has created a detailed explanation that will help you understand the various parts of the regression model output provided by R. (Call, Residuals, Coefficients, Significance codes, Residual Standard Error, Multiple R Squared, Adjusted R Squared, F-statistics, p-value). From the formula used to the statistical significance of the coefficients, each element plays a key role in interpreting the overall performance and validity of the model. Link

Robert Rachford prepared a primer for Biotstatisticians and Programmers about ADTTE (ADaM Time To Event) - the time to event dataset which is widely used in oncology trials. See his post to learn how Biostatisticians and statistical programmers should use this dataset. Link

Philip Bowsher Writes about using R for submissions. Writes about Novonordisk's communication wiht FDA, type C meetings, ADRG, R Submission Working Group and many more! Link

Johannes Ulander - From eProtocol to SDTM in 3 minutes.This is the demo I made at during my presentation with Kirsten Walther Langendorf - Partner at d4k at the #cdisctmf2024europe.Showing the potential of CDISC USDM and Biomedical Concepts when they work together. Link

Hengwei Liu - In the FDA submission, we need to submit a lot of files. We need to follow the folder structurein FDA technical conformance guide. It is of interest to know the number of files in each sub-folder of the submission folder. This can be done through Linux shell script or a SAS program. In this short paper I will show how to do that. Link

Biostatistics

Yuan J. and Tianjian Zhou - Bayesian Methods for Information Borrowing in Basket Trials: An Overview. This paper provides a review of statistical methods for tumor-agnostic clinical trials. In particular, the review focuses on basket trials and provides methodological insights into various Bayesian approaches. The key concept of borrowing information through Bayesian hierarchical models is emphasized, and some novel trial designs are introduced. The review is expected to provide oncology and biostatistics researchers with more exposure to powerful Bayesian methods for the design and analysis of tumor-agnostic clinical trials. Link

Dong Xi and Jialuo Liu - Covariate adjustment and estimation of difference in proportions in randomized clinical trials. Difference in proportions is frequently used to measure treatment effect for binary outcomes in randomized clinical trials. The estimation of difference in proportions can be assisted by adjusting for prognostic baseline covariates to enhance precision and bolster statistical power. Standardization or g-computation is a widely used method for covariate adjustment in estimating unconditional difference in proportions, because of its robustness to model misspecification. Extensive simulations are provided to demonstrate the performances of the proposed method, spanning a wide range of sample sizes, randomization ratios, and model specification. We apply the proposed method in a real data example to illustrate the practical utility. Link

F. Javier Rubio - An Index of #Cancer Survival to measure progress in cancer control: a tutorial is now available at the Cancer Epidemiology journal. We detail the construction of an index of cancer survival that summarises survival for all adults and cancer types into one single estimate, including the structure, the calculation of ‘sex-age-cancer’ specific weights and our proposed modelling strategy to estimate net survival. See the original post - Link

Haitao Chu - announces a recent publication on A Comprehensive Review andTutorial on Confounding Adjustment Methods for Estimating Treatment EffectsUsing Observational Data with Amy Shi and Paul Zivich. We discuss bias and precision, advantages and disadvantages, and software implementation for each method. Moreover, approaches are illustrated empirically with a reproducible case study. We conclude that different scientific questions are better addressed by certain estimands. No estimand is uniformly more appropriate. Upon selecting an estimand, decisions on which estimator can be driven by performance and available background knowledge. Link

Automated, efficient and model-free inference for randomized clinical trials via data-driven covariate adjustment. In May 2023, the U.S. Food and Drug Administration (FDA) released guidance for industry on "Adjustment for Covariates in Randomized Clinical Trials for Drugs and Biological Products". Covariate adjustment is a statistical analysis method for improving precision and power in clinical trials by adjusting for pre-specified, prognostic baseline variables. Though recommended by the FDA and the European Medicines Agency (EMA), many trials do not exploit the available information in baseline variables or make use only of the baseline measurement of the outcome. Kelly Van Lancker, Iván Díaz, Stijn Vansteelandt Link

Real World Evidence

Robert Szulkin - “Omitting Axillary Dissection in Breast Cancer with Sentinel-Node Metastases”, based on the results from the SENOMAC trial, was published in New England Journal of Medicine (NEJM Group) today. I am in particular very proud of this publication because I think this study will have an immediate impact on the treatment of many women with sentinel-node metastatic breast cancer, to relief the burden of severe side effects from major surgery. It has been a lot of work with the study the last year in a joint effort with the SENOMAC Trialists’ Group, and there is much more exciting research from the trial to be published soon! See Robert's post to read a few key points from this paper - Link

Robert Rachford writes about the use of Real World Data (RWD) to support Regulatory decision-making. See this post to understand better why it is useful and how can be used. Robert also provides information on how to start your journey with RWD and where to look for resources. Link

Alexandros S. shares a paper Real-world Overall survival using oncology electronic healht record data: Friends of Cancer research Pilot. It is sometime now that I have this very interesting paper that is reflecting many of my experiences, believes, but also worries on the use of #RWD and reproducibility of clinical readouts in the real world. Therefore, I like to focus on the broader picture, and not so much on the results, by highlighting few of the conclusions made by the authors. See the conclusions here - Link

Events and Webinars

Sunil Gupta - Join a new course that starts on June 6th to August 3rd! R-Guru Resource Hub is a curation of R resources and tips for easier search and navigation.??The pharmaceutical industry along with CDISC and FDA is making the transition to accept R programs in clinical study submissions. Unique practical R online class is focused on duplicating SAS programming methods as well as showing how to create SDTMs, ADaMs, Tables, Lists and Graphs. Link

Join the Joint PSI/EFSPI Data Science SIG Webinar for insights on developing digital measures (digital biomarkers) in drug development! Leveraging the expertise of the Mobilise D consortium, this webinar will explore:

?? What Mobilise D is and its importance for digital biomarkers?? Challenges and solutions for integrating digital measures in trials?? How Mobilise D's outputs can benefit your work

Date: Thursday, June 6th, 2024Time: 12:00-14:00 BST | 13:00-15:00 CESTLocation: Online via Zoom - Link

Michigan SAS Users Group is having a one-day SAS conference on June 12. For details, go to MISUG.org

Date:?Wednesday, June 12, 2024Time:?8:00 AM - 4:30

VisTaTech Center Schoolcraft College Livonia, MI 48152

2024 Midwest Biopharmaceutical Statistics Workshop! Dates: June 10-12, 2024Location: Carmel, IN, USALink: https://mbswonline.com/

Some of the topics:

A Statistician’s Guide to DMC – Overview, Standards, and Best Practices. David Kerr and Walter Boyle , Cytel Inc.

Open-Source Drug Development: ADAM, TLGs & Interactivity with R. Philip Bowsher and Richard Iannone , RStudio

IBIG - Italian Biostatistics Group Forum 2024 will be held in Parma from 29 to 31 October at Chiesi Italia. Day 1 will be dedicated to two theoretical and practical courses: - Approaches to use historical information for the design and analysis of clinical trials and their applications - Ga?lle Saint-Hilary & Pavel Mozgunov- Optimizing the Programming of ADaM CDISC Datasets for the Implementation of Estimands Framework - Marian Mitroiu On Day 2 and Day 3. speakers from a variety of European countries will lead us through themes such as: "Innovation in Statistics" (chairs Marco Costantini Veronica Sciannameo, "Statistics & Regulatory" (chair Giulia Zigon) and "Design & Analysis of Early Phase Studies" (chairs Elisa Rizzo Daniele Bottigliengo). Link

CDISC Vision and Roadmap: Transforming the Standards Paradigm and the First Step to Realize the CDISC Vision. With Chris Decker and Peter Van Reusel for a Webinar on the Includes Open Q&A Session with CDISC Leaders! May 30, 2024 05:00 PM?in Warsaw Link

From Kaspar Rufibach and Dr. Alexander Schacht - Dive into the world of estimands with The Effective Statistician Estimands Course! Learn from top experts and gain practical strategies for implementing estimands in your organization. Link

1?? Case study: hematology

2?? Hypothetical strategy to address ICEs: application to Covid-19

3?? Case study: treatment switching

4?? Estimation of average causal effect

5?? Subgroups by post-randomization event - principal stratification

6?? Estimation of principal effects

7?? Impact of ICH E9(R1) and conclusions

ASA Biopharmaceutical Section announce that the ASA BIOP Section is collaborating with the Statistics and Pharmacometrics Special Interest Group (SxP SIG) to bring you an exclusive session on Bayesian Complex Innovative Trial Designs (CIDs) for Drug Development in Rare and Pediatric Diseases.Speaker: Brad Carlin (Senior Advisor for Data Science and Statistics at PharmaLex)?? Date: June 10, 2024?? Time: 10.00 - 11.00 am ET??Register: Link

ASA Biopharmaceutical Section - The Early Development Estimand Nexus (EDEN) from the Estimands in Oncology WG (www.oncoestimand.org) shares in this fourth short video of the series how to?implement the ICH-E9 addendum and which opportunities it presents in early clinical development studies. Francois Mercier?and Stefan Englert explain in this video why it’s beneficial to embrace the estimand thinking in early clinical development and how to define estimands and associated estimators in this setting of Phase 1a (dose-escalation) and Phase 1b (expansion cohorts) studies. Link