University of Vermont gets up to $38M for AI-powered ICU digital twins

Advertisement

Burlington-based University of Vermont has received a research and development contract worth up to $38 million from the Advanced Research Projects Agency for Health to build AI-powered digital twins that help clinicians personalize treatment for critically ill patients.

The contract is the largest research award in UVM history, the university said Sept. 30. It funds a project called ReSCUED, or Reprogramming Severe Critical Illness Using Extensible Digital Twins, led by Gary An, MD, a trauma surgeon and researcher at UVM’s Larner College of Medicine.

The project will model a patient’s immune response in real time to guide treatment of ICU conditions such as sepsis, severe trauma and burns. Researchers will draw blood every six hours, feed immune measurements into a patient-specific digital twin and test treatment strategies using FDA-approved drugs virtually before clinicians give them to the patient. The team will also use the digital twin to train an AI “virtual consultant” that suggests individualized interventions.

“The complexity of critical illness exceeds what any individual can interpret in real time,” Dr. An said in a news release.

The anticipated five-year, milestone-based initiative is part of ARPA-H’s Critical Illness Immunological Reprogramming and Control Point Learning Engine, or CIRCLE, program. Researchers believe the technology could reduce ICU length of stay by 25%. Currently 4.6 million Americans are treated in ICUs each year, at a cost of up to $70 billion annually, according to the university.

Patient data will be collected at Wake Forest University School of Medicine in Winston-Salem, N.C., the University of Alabama at Birmingham, and St. Louis-based Washington University School of Medicine. DNA Medicine Institute will supply a bedside molecular testing platform, and InflammaSense will provide wearable vagus nerve monitoring technology.

During the first three years, researchers will develop and validate the digital twin; clinical trials in critically ill patients would follow only if the project meets its milestones.

Advertisement

Next Up in Artificial Intelligence

Advertisement