A Simple Framework for Integrating AI into Real-World Evidence Generation

AI is changing how teams generate real-world evidence (RWE), but AI workflows must still produce evidence that stands up to scientific scrutiny. Realizing AI’s potential requires a clear approach to deciding which tasks agents can take on, how their work is validated, and where human-based scientific judgment is essential.

In this white paper, Datavant’s Nicolle Gatto, Katie Mues, and Ulka Campbell share a phased framework to help RWE teams:

Identify where to introduce AI into their workflows, beginning with well-defined, rule-bound tasks.
Clarify the roles of subject matter experts in executing, directing, and governing AI-supported workflows.
Establish documented processes, evaluation standards, and escalation rules before expanding agents’ responsibilities.
Prepare for the evolving role of epidemiologists as AI becomes more integrated into the workflow.

Datavant is the data collaboration platform trusted for healthcare. With a mission to make the world’s health data secure, accessible, and actionable, Datavant works with payers, providers, life sciences, legal and insurance clients globally to accelerate insights. Datavant enables more than 60 million healthcare records to move between thousands of organizations across the healthcare ecosystem, more than 80,000 hospitals and clinics, 75% of the 100 largest health systems, and 350+ real-world data partners. Datavant has office locations in Boston, New York and San Diego, with international offices in Barcelona and Galway.

Achieve your boldest ambitions