This session explores how Interactive Response Technology (IRT/IWRS) has become a cornerstone of modern clinical data acquisition — connecting EDC, CTMS, and supply systems to drive randomization accuracy, and real-time trial oversight. Through practical examples and a forward-looking lens, attendees will see how thoughtful IRT design, automation and use case transform compliance from a checkpoint into a built-in advantage.

Key Learning Outcomes

1. Connect the systems — Explain how IRT/IWRS integrates with EDC, CTMS, and clinical supply systems to enable single data entry, instant randomization, and reduced manual rework across the trial lifecycle.
2. Design for quality upstream — Recognize how early design stability, UAT readiness, and governance decisions shape downstream data integrity, site burden, and inspection readiness.
3. Apply automation and AI strategically — Identify opportunities where standardization, automation, and AI improve timeliness, traceability, and consistency — turning regulatory compliance into an operational advantage rather than a reactive exercise.

Simplified and Standardised systems and AI readiness are today design and execution questions, not technical infrastructure questions. The output that’s wrong but sounds right. The system that can’t be improved. The requirement that demands the impossible. The business case that was never translated into something measurable. Such failures are often the consequences of gaps in skills and relevant expertise.

At the SCDM SDE, in the Technology track, we bring forward stories of good implementation strategies leading to improved efficiency, quality, and patient focus.  Through implemented case studies and examples, our speakers will share their blueprint for clinical data science.

We will go through principles and approaches for data readiness and operational clarity where models, agents, and applications work together to bring to the data scientist the required output right when she gets to work. Can dependence on a curated output add risks to study quality and integrity? We will discuss moving past the “Blind Men & the Elephant” trap—to an ecosystem of holistic anticipation. When we anticipate failure modes, we build better. A database well designed and systems well built are signs of mastery on the study requirements and the tools. We will see how Clinical Data Scientists address this need with some case studies.  As we do this, we will not lose sight of the non eDC data surge.

Models, agents, and applications have all got to do what they are meant to do. We will learn from experts about the foundations, the principles of good governance, and regulatory compliance as we navigate these changes.

This session explores the transformative role of Agentic AI in Integrated Data Review (IDR) within clinical data management, showcasing how autonomous, context-aware AI systems can significantly enhance data quality, efficiency, and decision-making. The presentation highlights the shift from manual, fragmented review processes toward an intelligent, risk-driven, and continuously evolving data review ecosystem. Through a real-world case study, attendees will gain insight on how an Agentic AI–enabled architecture integrates study context, automates multi-step review processes, and delivers real-time insights while maintaining strong governance, human oversight and accountability.

Expected learning outcomes:

• Understand the concept of Agentic AI and how it differs from traditional automation and generative AI in clinical data workflows
• Identify key challenges in current IDR processes, including manual fragmentation, cross-functional inefficiencies, and dependency on SMEs
• Explain how Agentic AI can enable integrated, risk-based, and continuous data review through context-aware and multi-step decision support
• Recognize the architectural and operational components of an AI-enabled IDR ecosystem, including centralized review systems and human-in-the-loop governance
• Evaluate the measurable impact of AI-driven IDR implementation, including improvements in efficiency, consistency, and early issue detection
• Importance of governance, accountability, and human oversight in deploying AI solutions in regulated clinical environments