Date: Wednesday 24th March 2026
Time: 14:30 - 16:30 (GMT) / 15:30 - 17:30 (CET)
Location: Online via Zoom
Speakers: Tina Lang, PhD (Bayer Pharmaceuticals AG), Christian Schmid, PhD (F. Hoffmann – La Roche AG)
Who is this event intended for?:
CMC Statisticians organized in the EFSPI SIG ‘CSNE’ and interested colleagues
What is the benefit of attending?:
Attendees will see successful examples how to position statistical expertise as essential to AI initiatives from project inception, ensuring their contributions shape, rather than merely validate, AI implementations in pharmaceutical development.
This webinar is free to both Members of PSI and Non-Members.
To register for this event, please click here
The rapid adoption of AI in pharmaceutical development has created both challenges and opportunities for CMC statisticians. While initial AI enthusiasm sometimes prioritized speed over statistical rigor, leading voices now recognize that sustainable AI implementation requires balancing agility with robust data governance and statistical rigour.
This webinar presents two complementary perspectives on successfully integrating statistical expertise into AI initiatives. Statisticians bring unique value through asking the right questions, applying critical thinking, and understanding both the nature of the objective and the data. They articulate and communicate model limitations while advocating for data integrity, interoperability, and contextualization. These core competencies become particularly critical in assessing and validating agentic models, where statistical frameworks ensure AI systems meet the stringent quality standards required in pharmaceutical manufacturing while maintaining the agility needed for innovation.
Tina Lang (Bayer) presents "The Importance of Being Human," sharing lessons on meaningful statistical inclusion in AI programs. Christian Schmid (Roche) follows with "Statistical Frameworks for Computerized Validation of Generative AI".
Together, these presentations illustrate that as AI matures in pharma, the statistician's role evolves from gatekeeper to strategic partner: ensuring innovations are both rapid and solid.
| Speaker | Biography | Abstract |
| Tina Lang, PhD Bayer Pharmaceuticals AG |
Tina Lang studied statistics at TU Dortmund where she also earned her PhD. She joined Bayer in 2009 as a preclinical statistician, supporting in vitro and in vivo experiments across the indication portfolio. Additionally, she is highly invested in elevating statistical literacy within the company and leads several training initiatives. In 2024 she transferred to the department of Data Science & Artificial Intelligence, where she has more insights into AI tools and their use within the drug development process. | Quality in Preclinical Research - The Importance of Being Human Preclinical experiments form the empirical foundation of translational medicine by assessing the feasibility, safety, and efficacy of new therapeutic approaches. Yet, unlike the highly regulated standards of clinical trials, preclinical research often exhibits substantial methodological heterogeneity, leading to concerns about reproducibility, bias, and the robustness of conclusions. These challenges are further compounded by the emerging use of artificial intelligence (AI). While AI has the potential to increase efficiency and support data analysis, uncontrolled or poorly understood applications can amplify existing weaknesses in study quality. In this presentation, we discuss the critical importance of human judgment, statistical rigor, and transparent study design for ensuring reliable preclinical evidence. We examine key dimensions of analytical quality across study design, data generation, and evaluation, and consider how AI - particularly large language models (LLMs) and foundation models - can support, rather than undermine, methodological integrity. From a biometrical perspective, safeguards for uncertainty quantification, error control, and interpretability are essential when integrating AI into preclinical research. Ultimately, methodological progress depends on a careful balance between human expertise, statistical inference, and computational tools. Illustrative examples highlight both opportunities and pitfalls at the interface of biostatistics, data science, and translational medicine, emphasizing that maintaining human oversight is crucial for generating reproducible and interpretable evidence. |
| Christian Schmid, PhD F. Hoffmann – La Roche AG |
Christian Schmid is a Senior Statistical Scientist at Roche and a founding member of the CMC Statistical Network Europe, where he has served on the steering committee since its inception. In his role, he primarily supports Roche’s commercial manufacturing and has recently expanded his work to include several AI validation initiatives. He earned his PhD in Statistics from The Pennsylvania State University, with a specialization in computational methods. | Validating GenAI (Generative Artificial IntelligenceI) in GxP (Good x Practice) environments requires moving beyond traditional "exact match" testing to a framework built on statistical confidence and risk management This presentation proposes a validation framework for GenAI applications, where rigorous testing strategies are used to quantify the reliability of non-deterministic outputs. We will explore technical controls for risk mitigation, specifically the use of Retrieval-Augmented Generation (RAG) architectures and parameter adjustments, such as temperature and top-p, to control output variability. The session will cover specific methods for combining automated scoring with structured Subject Matter Expert (SME) review to evaluate correctness and detect hallucinations, ensuring that probabilistic systems meet the safety standards required for regulated healthcare applications. |
