Office of AI Application and Innovation

The Office of AI Application and Innovation is focused on advancing the science and practice of patient safety using AI tools.

mission: create, integrate and sustain AI tools to improve patient safety.

Vision: Safer health care through augmented intelligence. Everywhere.

How AI connects different elements of life

There are presently three major programs in the office, each of which addresses our mission.


AI/QI Program Through ALPS and RAPiDS mechanisms, we explore and apply AI solutions to QI challenges.

AI in Medical Education We are developing a series of AI courses intended for physician learners. Aside from being prepared to address patient questions about AI in health care, these courses will develop a clinical workforce that is “collaboration-ready” to accelerate multidisciplinary teamwork with AI engineers.

AI Governance & Integration We work with the College of Medicine Office of Research to develop pathways to successfully and sustainably translate AI solutions into clinical workflows that directly impact patient care.

AI/QI Program


AI Labs for Patient Safety

Protected health information requires special security. While research use-cases of health care data can generally use de-identified materials, QI and clinical operational use-cases may occasionally require the use of patient and clinician identifiers. These use-cases also carry a wider array of stakeholders beyond publishers and funding agencies and can include department chairs, division chiefs and college leadership. We created the AI Labs for Patient Safety, or ALPS, to address this need.

Computer wires highlighted with purple, pink and orange light.

What is ALPS?

ALPS links PHI to GPU-accelerated, high-performance computing infrastructure within a secure enclave. This permits AI analyses to be performed on identifiable data. For QI and hospital operations, this allows us to extend research-level AI models to operational datasets.

ALPS is principally managed by Ray Opoku, MSc., in consultation with UF Research Computing and Ron Ison, M.S., P.M.P., in the Department of Anesthesiology.

How is ALPS Innovative?

ALPS was a key advance in allowing us to develop temporal graph neural networks (GNNs) for use with PHI.  Because temporal GNNs use date/timestamps of hospital events and require GPU acceleration for creation, and because attempts to anonymize through various obfuscation methods were deemed impermissible by the IRB, temporal GNN models would not be feasible outside of an ALPS-like enclave.

How is ALPS Being Used?

A sub-project within ALPS seeks to develop a core resource for examining social disparities using geospatial analysis. Using this core, we can attach social determinants of health to all modeling efforts, and back-translate findings to maps of disparities and social vulnerabilities. This is an operationally-enabled resource developed by Rulman Pebe, MSc., in consultation with Jiang Bian, Ph.D..



Rapid AI Prototyping and Development for patient Safety

To support the AI/QI program, we developed internal grant funding for Rapid AI Prototyping and Development for patient Safety (RAPiDS) projects. RAPiDS are intended to prototype novel AI solutions to QI challenges. In RAPiDS Cycle 1, we targeted funding to two small projects to develop data, high-performance computing and project management infrastructure through the Integrated Data Repository and UF Research Computing. RAPiDS Cycle 2 will extend this infrastructure to involve clinical teams tackling more complex challenges at the interface of AI and QI.

Glowing microchip with blue, red, white, and pink lights

Cycle 1

Cycle 1 focused on developing a Patient Safety Graph (PSG) as a test of infrastructure. The PSG is one of the first AI projects at UF Health that focuses on clinical care pathways. Using graph analysis methods, we have created a multigraph that maps how patients, patient characteristics, caregivers, medications, laboratory values, surgeries, intra-hospital transfers and more are interconnected. Moreover, we have used timestamps to examine how these connections evolve over time, culminating in outcomes of interest.

Cycle 2

RAPiDS Cycle 2 (RC2) aims to develop transdisciplinary collaborations of AI engineers and clinical experts to apply new AI infrastructure to critical QI problems at UF Health. Proposals should address health and health care challenges for select populations (maternal care; surgery, trauma & acute injury; and Alzheimer’s disease and related dementias and care of older adults) leveraging RAPiDS-supported AI resources including geospatial data and social determinants of health, Patient Safety Graph & care pathway optimization using Graph Neural Networks, and Natural Language Processing (NLP) of clinical text documents.

AI in Medical Education

In conjunction with Francois Modave, Ph.D., and Chris Giordano, M.D., we have developed a series of courses for physicians and medical students to learn more about AI. These courses are designed to accommodate physicians’ busy schedules and focused learning interests, providing a foundational understanding of the principles of AI in health care.

AI Governance & Integration

Working closely with UF Health, the Clinical and Translational Science Institute, the Intelligent Critical Care Center and UF Health’s chief data scientist, we are developing infrastructure supporting the College of Medicine.


For more information about the Office of AI Application and Innovation, contact Dr. Patrick Tighe, Associate Dean for AI Application and Innovation.