Prediction medicine: Which patients will have complications?
UW-developed AI software helps docs anticipate problems in the operating room, study shows.
During surgery, anesthesiologists monitor and manage patients to ensure they are safe and breathing well. But they can’t always predict when complications will arise.
University of Washington researchers have developed a machine-learning system called Prescience that uses patient data and operating-room sensors to predict the likelihood that a patient in surgery will develop hypoxemia, or slightly low blood oxygen. The condition can have serious consequences such as infections and abnormal heart behavior.
The team published its findings Oct. 10 in Nature Biomedical Engineering, estimating that Prescience could improve the ability of anesthesiologists to anticipate and prevent 2.4 million more hypoxemia cases in the United States every year.
“This research will allow us to better anticipate complications and target our treatment to each patient,” said co-author Monica Vavilala, professor of anesthesiology and pain medicine at the UW School of Medicine. “If we know there’s one aspect that’s causing the problem, then we can approach that first and more quickly. This could really change the way we practice, so this is a really big deal.”