Article

Workshop sheds light on important statistical advances for the biopharma industry

Lin Li
Lira Pi

Statistical advancements to solve important questions surrounding drug development and regulatory science were explored in depth during the recent ASA Biopharmaceutical Section Regulatory-Industry Statistics Workshop (RISW). The workshop, held in Rockville, Maryland from 24 to 26 September 2025, attracted 1,000+ statistician professionals from industry and regulatory agencies as well as academia.¹

General impression

Statistical science is being leveraged more frequently during interdisciplinary collaboration, including the use of AI/ML that informs data-driven decision-making in the biopharmaceutical industry.

The FDA paper “Artificial Intelligence & Medical Products” exemplifies how the different centers at the US Food and Drug Administration (FDA) work together to explore the development and use of AI across the medical product life cycle.²
The theme of the RISW conference, “Future in Statistics: Collaboration and Innovation in the AI/ML Era”, is an indicator of the new trend of integrating statistics with AI. That has been echoed at other prominent conferences such as the 2025 Joint Statistical Meetings, themed “statistics, data science, and AI enriching society”³, and is expected to be top of mind at the 2026 ENAR Biometrics Meeting with the theme of “The role of statistics in an AI-augmented world."⁴

RISW key takeaways

Statistics and AI/ML have empowered modern clinical trials to rigorously leverage external information to obtain clinical evidence that can be used for regulatory decisions. Randomized clinical trials could be made more efficient with Bayesian adaptive designs. This could result in a higher statistical power with the same sample size or, assuming the same power, a smaller expected sample size or shorter expected duration.

Borrowing information from external controls, such as natural history or real-world data (RWD), could potentially reduce the need for large control groups, especially in rare diseases or when a placebo arm presents ethical concerns. Proper statistical approaches make single-arm trial design possible and feasible. In addition, statistical frameworks combining machine learning and causal inference can learn from external information while addressing confounding and bias properly. Such approaches have shown promise in clinical trials to estimate treatment effect in a principled, data-adaptive way. As a result, a smaller trial is possible given the same statistical power.

Another important focus area during the workshop was patient enrichment strategies for clinical trials. Discussions focused on the potential these strategies have for increasing the efficiency of drug development and supporting precision medicine.

Often such strategies are centered around assessing heterogeneous treatment effect and identifying patients more likely to benefit from specific treatments (e.g., treatment-responsive subgroups). The potential outcome framework, a core concept in causal inference, is increasingly integrated into causal ML to discover patterns in clinical trial data and identify patient subgroups. In the context of biomarkers, this could lead to co-development of companion diagnostics and important statistical and design considerations in studies such as bridging studies.

Workshop conclusions

The workshop raised important considerations about statistical advancements, supported by AI/ML, to address many of the questions and challenges clinical trials and drug development face. By leveraging statistical advancements, biopharmaceutical companies can apply broader and deeper insights to the design and conduct of clinical trials and to more efficient drug development.

About the authors:

Lin Li is Head of Clinical Statistics and Computational Biology at Cencora. He provides data-driven and tailored solutions that integrate biostatistics, bioinformatics, computer science, and biology to tackle challenges in discovery and clinical development.

Lira Pi is Associate Director, Statistics at Cencora. She is a statistical methodologist who leads the development and application of novel statistical approaches, such as AI/ML and Bayesian methods, throughout both non-clinical and clinical stages of research.

Disclaimer:
The information provided in this article does not constitute legal advice. Cencora, Inc., strongly encourages readers to review available information related to the topics discussed and to rely on their own experience and expertise in making decisions related thereto.

Entrez en contact avec notre équipe

Notre équipe d’experts en valeur de premier plan se consacre à la transformation des données probantes, des informations sur les politiques et des renseignements sur le marché en stratégies efficaces d’accès au marché mondial. Laissez-nous vous aider à naviguer en toute confiance dans les méandres complexes des soins de santé d’aujourd’hui. N’hésitez pas à nous contacter pour découvrir comment nous pouvons vous aider à atteindre vos objectifs.

Nous contacter

Sources

^1. ASA Biopharmaceutical Section Regulatory-Industry Statistics Workshop. https://www.amstat.org/meetings/asa-biopharmaceutical-section-regulatory-industry-statistics-workshop
^2. Artificial intelligence and medical products: How CBER, CDER, CDRH and OCP are working together, FDA. OMP CDER AI Discussion Paper
^3.Joint Statistical Meetings 2025, Nashville, TN, 2-7 August 2025. https://ww2.amstat.org/meetings/jsm/2025/index.cfm
^4. ENAR 2026 Spring Meeting, March 15-18, Indianapolis, IN. ENAR 2026 Spring Meeting: Meetings - ENAR <cfoutput>2026</cfoutput> Spring Meeting

Ressources connexes

Webinaire

How to avoid the 5 most relevant inspection findings related to the QPPV

Article

RAPS Convergence 2025: Transparency, Trust, and Resilience in Regulatory Science

Article

The complex path to meeting promotional materials requirements in Europe

Cencora.com fournit des traductions automatiques pour faciliter la lecture du site Web dans des langues autres que l’anglais. Pour ces traductions, des efforts raisonnables ont été faits pour fournir une traduction précise, cependant, aucune traduction automatique n’est parfaite et n’est pas destinée à remplacer les traducteurs humains. Ces traductions sont fournies en tant que service aux utilisateurs de Cencora.com et sont fournies « en l’état ». Aucune garantie d’aucune sorte, expresse ou implicite, n’est donnée quant à l’exactitude, la fiabilité ou l’exactitude de ces traductions effectuées de l’anglais vers une autre langue. Certains contenus (tels que les images, les vidéos, Flash, etc.) peuvent ne pas être traduits avec précision en raison des limitations du logiciel de traduction.

Toute divergence ou différence créée lors de la traduction de ce contenu de l’anglais vers une autre langue n’est pas contraignante et n’a aucun effet juridique pour la conformité, l’application ou toute autre fin. Si des erreurs sont identifiées, veuillez nouscontacter. Si vous avez des questions sur l’exactitude des informations contenues dans ces traductions, veuillez vous référer à la version anglaise de la page.