Date: Thursday 16th November 2023
Time: 14:00-15:30 GMT | 15:00-16:30 CET
Speakers: Alessandra Serra (Saryga / University of Cambridge), Sandrine Guilleminot (Servier), Nils Ternès (Sanofi), and Karl Köchert (Bayer AG).
Who is this event intended for? Everybody interested to learn more about the importance of biomarkers in clinical development.
What is the benefit of attending? Please join the discussion on how to improve clinical development using biomarkers.
This event is free to attend, for both Members and Non-Members of PSI.
To register your place for this event, please click here.
In this webinar, you will get to know how an innovative adaptive design can increase the probability of success of your early phase clinical trial as well as hear the latest and greatest of the Machine Learning workstream from the Biomarkers ESIG.
Presentation 1: A promising adaptive biomarker-based design strategy for early phase clinical trials
Alessandra Serra and Sandrine Guilleminot
Identifying predictive biomarkers is crucial in patient-centric clinical development. Enrichment strategies in late stages of drug development have been widely studied in the literature. However, implementing these strategies in early stages presents significant challenges due to the small sample size and numerous uncertainties that arise at this point in the development process. These uncertainties encompass biomarker (BMK) predictive value, cutoff value of the biomarker used to identify patients in the BMK-positive subgroup, the proportion of patients in the BMK-positive subgroup and the magnitude of the treatment effect in patients BMK-positive and BMK-negative. Early phase adaptive designs can improve trial efficiency by allowing for adaptions during the course of the trial. In this work, we are interested in adaptations based on interim analysis permitting a refinement of the existing study population according to their predictive biomarkers. Simulations show that the proposed design leads to better decision-making compared to a classical design that does not consider an enrichment expansion. Specifically, in the considered settings, gains up to 30% in the overall probability to hit the study success criteria at the end of the trial were achieved in comparison to a conventional design.
Presentation 2: Machine Learning as an enabler of precision medicine
Nils Ternès and Karl Köchert
Since the re-creation of the Biomarkers ESIG in 2022, people from different horizons and job titles have expressed some interest in machine learning (ML) and artificial intelligence (AI) methods applied to drug development, from research to clinical. With this fact and the increasing interest in ML/AI from the scientific community and beyond, a group of a dozen people was set-up in the past months with the ambition to create a cross-company best practices guidance on the use of AI/ML in drug development. The group started with some proactive joint discussions to better understand each other’s interest in this area and has already contributed to the review and feedback to FDA’s recent discussion paper on usage of AI/ML in drug development. Now, the group is in a highly dynamic ideation phase to identify and choose topics which have the potential to impact drug development, e.g., virtual twin (VT) technology, GxP compliant AI/ML, use of image-based or digital biomarkers.
|
Speaker |
Biography |
|
|
Alessandra is a Research Associate in the field of adaptive clinical trial designs at the MRC Biostatistics Unit (Cambridge, UK). She also provides private consultancy on clinical trial designs and analysis at Saryga. Alessandra has concluded her PhD at the MRC BSU in Cambridge working on adaptive designs and methods to improve the efficiency of drug development. |
|
|
Sandrine is the Head of the Translational Statistics Group at Servier R&D. Jointly with her team members, she provides advanced statistical support and strategic insight into preclinical/early clinical development phases across Servier’s programs in oncology, Inflammation & Immunology and Central Nervous System. Since 2016, she is also an active member of Societé Française de Statistique's Biopharmacy and Health group. Prior to joining Translational Medicine, Sandrine worked in Clinical Development at Fovea, Sanofi and Servier giving her a rich and successful history in biostatistic issues in drug development, including a track record of successful regulatory interactions with global health authorities. Her main research interests focus on quantitative decision making, innovative designs, predictive models, and BMK-driven strategies. |
|
|
Nils Ternès is a statistical biomarker leader at Sanofi R&D in France where he leads the biomarker-related statistical activities on several compounds in clinical development across all phases mostly in Oncology and Inflammation & Immunology. With this position, Nils is continuously looking for data and analytical methods innovations as well as operational efficiency in order to ensure effective decision making and increase the productivity of drug development. Before joining Sanofi, Nils studied statistics applied to public health at Paris-Saclay University (MSc) and holds a PhD in Biostatistics (2016) at Gustave Roussy cancer institute on advanced penalized regression techniques for the identification of prognostic and predictive biomarkers in high-dimensional settings. With a constant interest in learning and promoting the use of ML/AI technics to support clinical development, he is now co-leading the Machine Learning workstream from the Biomarkers ESIG. |
|
|
As Head of Biomarker & Data Insights at Bayer AG (Berlin, Germany) Karl leads a team of data scientists / statisticians. With a background in omics data science and precision medicine, his team’s major objective is to advance drug development by enabling holistic understanding of complex biological systems - namely the patients in need. In this vein, their current endeavour is to understand how applied AI/ML can help to detect highly complex safety and efficacy signals in interventional clinical trials and how that can be utilized as a basis for creating virtual twins of specific disease indications. Karl, being a Biochemist by training, discovered his passion for mathematical modelling of complex biological systems during his PhD at Humboldt University (Berlin, Germany) and subsequently devoted himself to applied machine learning during postdocs at TU-Dresden (Germany) and the Max-Delbrück-Center for Molecular Medicine (Berlin, Germany) before joining Bayer AG in 2014. At Bayer he has held positions of increasing responsibility as Study and Project Biomarker statistician for interventional trials of all phases in oncology. In August 2023 Karl has joined Niles Ternès as co-lead of the Machine Learning workstream from the Biomarker ESIG. |
