Archives: Agenda

Early-phase oncology development is evolving rapidly, with a growing need for smarter trial designs, faster regulatory pathways, and deeper collaboration with sites. This session explores how AI-driven protocol design, streamlined fast-track approvals, and strategic site partnerships can transform study execution from design to delivery. Through practical insights and real-world examples, we will discuss how technology and collaboration with regulators and sites can help bring therapies to patients faster.

• Fast, Furious, or Never-Ending: Entertaining Case Studies on Accelerating and Unexpectedly Inflating Phase Ib/II Trial Timelines and Budgets. A Site Team Perspective.

As with all therapeutic areas, artificial intelligence is generating significant buzz in oncology research. But where does it offer meaningful impact today, and where is there still work to be done? In this session, we’ll explore

• The practical realities of applying AI tools within the context of electronic clinical outcomes assessment (eCOA) in oncology trials where complex symptom profiles, high patient burden, and global trial scale demand more intelligent solutions.
• Discuss meaningful targets for AI use today, to generate operational efficiencies in study setup and translation
• Explore the future promise of adaptive, patient-facing tools that can better capture quality-of-life data and treatment response
• This session offers an honest look at what’s achievable now, what’s emerging, and how sponsors and CROs can think strategically about this fast-moving future in oncology.

We explore how Retrieval-Augmented Generation (RAG) can transform quantitative research workflows by enabling accurate, context-aware answers sourced from technical documentation.

• How to build RAG pipelines to handle complex, domain-specific queries efficiently
• What are the key technical challenges, like: retrieval strategies, query handling, grounding and answer generation
• How to train and evaluate these systems
• What are the best practices and learnings for designing robust, scalable AI assistants for quant and business decision-making