EMBÍ·NET
Work & ImpactFocus areas

Focus of his work

A career spent turning health data and evidence into trustworthy knowledge and AI — and into health systems that continuously learn — to improve care, accelerate discovery, and strengthen the public good.

Embí’s work sits at the intersection of biomedical informatics, health AI, research infrastructure, and learning health systems. Across institutions and national initiatives, he has helped define fields, build organizations, create technologies, and shape governance approaches for the responsible use of data and AI in health.

01
Evidence, discovery & translation

A field he helped establish

Embí is credited among the founders of clinical research informatics — the discipline that uses electronic health records and health data to make biomedical research faster, broader, and more rigorous. His early studies of EHR-based clinical trial recruitment and of computerized clinical documentation became widely cited reference points for the field, helping make real-world health data a foundation for evidence generation, discovery, and translation.

02
Effective & ethical health AI

Algorithmovigilance

Embí conceived and named algorithmovigilance: the systematic, ongoing surveillance of clinical AI after deployment for safety, bias, and performance drift — modeled on the way medicine monitors drugs once they reach patients. It reframes AI safety as a continuous, operational responsibility rather than a one-time approval.

  • Originated the concept and the term now used across the field
  • Leadership in national efforts on the responsible use of health AI
03
AI-enabled learning health systems

Closing the loop between care and discovery

Across roles at University of Cincinnati, The Ohio State University, IU Health, Regenstrief, and Vanderbilt, Embí has built systems where everyday care and research continuously inform each other — so health systems learn and improve as a matter of routine rather than exception.

04
Trustworthy biomedical knowledge

Computable, AI-ready knowledge

Turning the health and biomedical data and the medical literature into structured, connected, machine-usable knowledge — and governing it for integrity, so that what clinical AI learns from can itself be trusted.

Current efforts

In progress · since 2025
TRAIN

A national learning network for trustworthy health AI

Helping health care organizations generate shared evidence, governance approaches, and practical tools for safe, effective, and responsible AI adoption.

VAMOS Collaborative

Operationalizing algorithmovigilance

Building shared approaches for monitoring AI in real-world clinical settings — including safety, effectiveness, equity, performance drift, and value.

AI governance · Vanderbilt

From principles to practice

Translating responsible AI principles into institutional governance, review, monitoring, and accountability mechanisms.

Vanderbilt ADVANCE AI Center

AI discovery and vigilance

Leading work to develop, evaluate, and responsibly deploy AI across research and care.