UVM researchers developing AI ‘digital twins’ to help personalize ICU care

By Charlotte Hancox

Click here for updates on this story

    BURLINGTON, Vermont (WPTZ) — ReSCUED is a new UVM-led research project aimed at patients in the intensive care unit. Researchers will use artificial intelligence to create what they call a “digital twin” of a patient’s immune system.

By collecting blood samples and monitoring a patient’s condition, the system would create a virtual model that updates in real time.

“[It] gives us a platform to be able to evaluate, discover and test potential therapies, often requiring multiple medications,” said Dr. Gary An, the vice chair of surgical research.

An said while today’s technology can keep more critically ill patients alive, some can become stuck in the ICU when their immune system struggles to recover. He said that immune response can be too complex for any one person to fully analyze in real time, and that’s where the AI system comes in.

“It processes that information and says, ‘oh, I’ve seen this before. If we don’t do anything, this patient will go this way, but we can do X, Y, and Z, and maybe that will make them better,'” said An.

The five-year project is the largest research award in UVM history, with federal funding worth up to $38 million.

“This is our mission to do good in the world. This is our common ground values, our commitment to our state and to people all over the world. And it’s going to save lives,” said Marlene Tromp, the president of UVM.

The patient data will not be collected in Vermont. Instead, three partner sites around the country will collect information from a broader range of patients including Wake Forest University, the University of Alabama, and Washington University.

At UVM, researchers will lead the project and develop the model behind the digital twin.

“This may improve survival from critical care illness. It may then also shorten the time in the ICU shorten their hospitalization. This could reduce health care costs,” said Richard Page, the Dean of Larner College of Medicine.

With the hope that by the end of the project, the technology will be ready for clinical trials. The ultimate goal is to reduce ICU stays by at least 25 percent and improve outcomes for some of the most critically ill patients.

And while this project is specifically focused on ICU patients, researchers said if the digital twin model proves successful, it could be applied to any health care problem.

Please note: This story was provided to CNN Wire by an affiliate and does not contain original CNN reporting. This content carries a strict local market embargo. If you share the same market as the contributor of this article, you may not use it on any platform.

• Category: CNN Regional