Life sciences organizations have invested heavily in generating real-world evidence (RWE), yet many struggle to translate those insights into sustained changes in clinical practice, patient behavior, and organizational decision-making. This presentation introduces the concept of execution architecture and explores how implementation science, knowledge translation, and human-centered design can bridge the gap between evidence generation and real-world impact.

Decision-grade RWE starts with the research question, not the dataset. To scale beyond pilots, RWD needs must be built into development planning early, shaping trial design, feasibility, endpoints, comparators, and follow-up. Sponsors need a reliable data supply chain incorporating data quality, provenance, curation, documentation, and traceability. Regardless of use case, regulatory and access needs should be anticipated upfront. The goal is repeatable, reviewable evidence—not bespoke success stories.

As AI capabilities rapidly advance, pharmaceutical organizations are rethinking how evidence is generated, verified, and communicated. This session compares AI adoption journeys of Clinical Development and Real-World Evidence teams, highlighting how priorities have evolved from task automation to workflow transformation. Speakers will share practical lessons on strategy, governance, and implementation, and discuss the future role of AI in enabling faster, more scalable and effective evidence generation across the research enterprise.

Pragmatic trials increasingly use real-world data (RWD) and privacy-preserving linkage to extend follow-up beyond protocol windows, reduce participant burden, and capture outcomes from routine care. However, dataset selection often relies on simple token overlap (i.e., whether a participant appears in a dataset), which may obscure whether required variables are available with sufficient completeness. A cloud-first approach enables secure, early feasibility assessment to guide fit-for-purpose RWD selection without moving underlying data.

Clinical development timelines are routinely stressed, often because underlying assumptions are misaligned with real-world clinical settings. Estimates of eligible patients, clinical events of interest and sites often rely on experience alone. RWD-derived patient journeys can shape some of these anecdotal assumptions into data-informed decisions reflecting real-world target populations. This talk explores how RWD, carefully grounded against its biases, can sharpen clinical evidence without replacing expert-led decision governance.

Shakespeare's rose smells as sweet by any other name. In real-world evidence, the reverse problem matters more: the same name in a protocol can select very different patients. Drawing on examples from ASCVD, GLP-1 eligibility, and depression, this session shows how definition choices quietly reshape cohorts, outcomes, and conclusions — and what makes a definition transparent and defensible to regulators, payers, and peers.

Ultra-rare disease trials are challenged by small, dispersed patient populations and fragmented real-world data (RWD) across registries, electronic health records, clinical notes, claims, and digital sources. Using a case study, this session will outline an AI-enabled framework for integrating and harmonizing these data to develop external control arms. It will address endpoint alignment, causal inference, confounding adjustment, missing data, bias assessment, and the creation of transparent, traceable, and inspection-ready evidence for regulatory decision-making.

Electronic health record (EHR) to electronic data capture (EDC) interoperability has been proven through pilots, established standards, and advancing technology, yet adoption remains fragmented across the clinical research ecosystem. If the technology exists, what barriers remain for EHR-to-EDC to scale globally? This session explores a shared vision for a future in which research-relevant EHR data can be exchanged and reused across sponsors, sites, studies, and technology platforms without bespoke implementations or proprietary dependencies.

Drawing on TransCelerate's EHR Connectivity initiative, presenters will share insights from ecosystem assessments and stakeholder engagement, highlighting the progress achieved and the technical, operational, governance, and validation barriers that remain. Attendees will explore what it will take to move from isolated successes to broad adoption and will be challenged to join a holistic industry effort to build the roadmap, partnerships, and reusable assets needed to make scalable EHR-to-EDC interoperability a reality.

The life of clinical trial data can go beyond database lock. Drawing on experience connecting trial data to privacy-preserving real-world data linkages and post-approval data collection, this talk explores how teams can design trial infrastructure that supports evidence generation well beyond approval. Learn about practical approaches to building systems that serve regulatory, safety, and long-term evidence needs—without compromising patient privacy or slowing trial execution.

The promise of AI-assisted statistical analysis in clinical development is significant, yet deploying AI into a highly regulated production environment remains difficult. We describe a pragmatic, two-stage strategy—recognizing that the path to trustworthy AI runs through standardization, not around it. An iterative interim platform built on validated, reusable analytical modules delivers faster, reproducible analyses today while serving as a context-engineering engine: modularizing the statistical workflow into steps that must remain deterministic and those that allow flexibility, enabling early process and SOP development, and refining modules through user feedback. Throughout, the effort empowers, not replaces, statisticians.

This presentation will explore how ATLAS uses AI-enabled capabilities to help streamline trial operations, connect information across workflows, identify insights, and support proactive decision-making. The discussion will also highlight practical considerations for responsible AI adoption, including data quality, governance, integration, and human oversight.