Diabetes prevention is the impetus behind a new collaboration announced this week between New York University, NYU Langone Medical Center and Independence Blue Cross (IBC) in which researchers will try to take advantage of artificial intelligence for disease prediction.
Researchers will create algorithms using machine learning, a form of AI in which computers learn to pull information from data sets to develop informed analyses that often result in predictions. The algorithms then would be applied to IBC's medical and pharmacy claims data to try to determine which patients have either undiagnosed or pre-diabetes.
Philadelphia-based IBC plans to spend roughly $1 million, according to the Philadelphia Inquirer, which includes a $600,000 grant.
"We feel that this can be a game-changer," Somesh Nigam, a senior vice president and CIO at IBC, told the Inquirer."[P]eople sometimes show up at their doctor's doorstep and the disease is far along."
Researchers from Indiana University determined earlier this year that machine learning can improve both the cost and quality of healthcare in the U.S. An AI framework used by IU researchers showed how simulation modeling that "understands and predicts" the outcomes of health treatments could reduce healthcare costs and improve patient incomes by about 50 percent.
The approach taken by the researchers was not disease-specific and, they said, could work for any diagnosis or disorder.
Roughly 25 million people in the U.S. alone suffer from diabetes, with one-third of those unaware of their condition, according to the NYU announcement.