People with Type 1 diabetes may soon be able to count on an algorithm to keep their blood sugar levels within a healthy range, as research to tap the power of Big Data for automating personalized glucose monitoring and insulin delivery is underway at Rensselaer Polytechnic Institute in Troy, N.Y.
The project is getting funded by JDRF, formerly known as the Juvenile Diabetes Research Foundation, and it’s being led by Rensselaer chemical and biological engineer Wayne Bequette, PhD.
Much of the data for training the AI will come from thousands of continuous glucose monitors and insulin pumps presently in use, according to an announcement from the school.
The nonprofit Tidepool is making data available after de-identifying patients from whom it’s drawn through its Tidepool Big Data Donation Project.
Another aim of the research is to leverage AI for showing whether signals from glucose monitors is trustworthy.
“If we look at hundreds of people we can say, ‘Oh, certain problems occur more often in this age group, this type of population or with this particular type of sensor,’” Bequette says. “If, for example, you find that it’s more likely that people 8 to 12 years old have these types of irregularities, then you can account for that in your algorithm and provide more personalized control while reducing burden.”
Rensselaer notes Bequette has been interested in countering diabetes since his sister was diagnosed with the condition in the ’70s. His contributions to the science include developing a closed-loop artificial pancreas that automatically adjusts an insulin infusion pump based on signals from a continuous glucose monitor.
For the new AI-based project, Bequette will continue a long-running collaboration with colleagues at the Icahn School of Medicine and the University of Colorado.