Franz König: Statistical Issues with Adaptive Designs for Confirmatory Clinical Trials

08.04.2024

Our dsUniVie Talk on 8 April 2024 features Franz König from the Institute of Medical Statistics, Center for Medical Data Science of the Medical University of Vienna

Monday, 8 April 2024 @ 14:00–15:00 CET

On-site:

University of Vienna
Seminarraum 9 (OG01)
Kolingasse 14–16
1090 Vienna

Online:

Zoom-Link: https://univienna.zoom.us/j/68154688415?pwd=anBCaXlnZ0ZRZ0R2YkV0U2hMSXdIQT09
Meeting-ID: 681 5468 8415
Passcode: 517043

 

Statistical Issues with Adaptive Designs for Confirmatory Clinical Trials

 

Abstract:

Since the first methodological papers on adaptive designs [1, 2, 3, 4] , some published more than 25 years ago, adaptive designs have gained increasing attention in drug development. Especially in confirmatory phase III clinical trials, their use is subject to enhanced scrutiny by regulators as the increased complexity of flexible study designs also increases the risk of operational and statistical biases and hidden fallacies. Broad enthusiasm about potential applications of such designs faced critical positions regarding their statistical efficiency. Despite, or possibly because of, this controversy, the methodology and its areas of applications grew steadily over the years. In the meantime, such type of adaptive designs have become the subject of three major regulatory guidance documents in the US and Europe [5].

The main goal of this tutorial is to give an introduction to the key principles and statistical methodologies of adaptive designs for confirmatory clinical trials [6]. Adaptive (flexible) designs allow for mid-course design adaptations based on interim data without compromising the overall type I error rate. Important applications of adaptive designs include sample size reassessment, treatment selection procedures, and population enrichment designs. The change of design parameters at an adaptive interim analysis may depend on any internal and external data available, e.g., interim estimates of the variance, the observed treatment effect and safety parameters. Using adaptive multiple test procedures [8] the type I error rate can be controlled even if the selection rule, the number of selected treatments or the final sample sizes are not prefixed. We will discuss the most recent developments of adaptive master protocols [7, 8] which add a new complexity to the statistical planning and analysis.

References:

  1. Bauer P, Bretz F, Dragalin V, König F., and Wassmer G. Twenty-five years of confirmatory adaptive designs: opportunities and pitfalls. Statistics in Medicine, (Early View 2015). Free download from  http://dx.doi.org/10.1002/sim.6472
  2. Bauer P. Multistage testing with adaptive designs. Biometrie und Informatik in Medizin und Biologie 1989; 20:130–148.
  3. Bauer P, Köhne K. Evaluation of experiments with adaptive interim analyses. Biometrics 1994; 50:1029–1041, correction in Biometrics 1996, 52:380.
  4. Proschan MA, Hunsberger SA. Designed extension of studies based on conditional power. Biometrics 1995; 51: 1315–1324.
  5. EMA. Reflection Paper on Methodological Issues in Confirmatory Clinical Trials Planned with an Adaptive Design. European Medicines Agency: London, UK, 2007. http://www.ema.europa.eu
  6. Bretz F, König F, Brannath W, Glimm E, Posch M. Adaptive Designs for Confirmatory Clinical Trials. Statistics In Medicine 2009  Apr 15;28(8):1181-217.
  7. Meyer, E. L., Mesenbrink, P., ... & König, F. (2020). The evolution of master protocol clinical trial designs: a systematic literature review. Clinical Therapeutics, 42(7), 1330-1360.
  8. Koenig, F., Spiertz, C., Millar, et al. (2024). Current state-of-the-art and gaps in platform trials: 10 things you should know, insights from EU-PEARL. Eclinicalmedicine, 67. https://doi.org/10.1016/j.eclinm.2023.102384

 

Bio:

Franz König is Associate Professor at the Section of Medical Statistics at the Medical University of Vienna, Austria. He is also member of the ethics committee in Vienna.  From 2008 till 2010 he was seconded to the European Medicines Agency (London, UK) as statistical expert. His main research interests are multiple testing, adaptive/flexible designs, interim analyses, data safety monitoring boards (DSMB) and master protocols focusing on platform trials. For example he was work package leader of the work package "adaptive designs" in the EU FP7- funded research project IDEAL (Grant Agreement No 602552), co-WP lead in the IMI project EU-Pearl on platform trials; and deputy coordinator of an EU Horizon 2020 funded Marie Curie ITN network IDEAS on early drug development studies (Grant Agreement No 633567).

 

Contact:

franz.koenig@meduniwien.ac.at