John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
John Taylor, Professor of Economics at Stanford University and developer of the "Taylor Rule" for setting interest rates | Stanford University
Researchers at Stanford Medicine have developed an AI-based algorithm to better understand Type 2 diabetes by using data from continuous blood glucose monitors. This tool can help identify three of the four most common subtypes of the disease, offering insights into its underlying biology.
Michael Snyder, PhD, a professor of genetics who co-led the study, stated that this technology could allow individuals to take preventative measures if their levels indicate a prediabetes warning. He noted that "dietary or exercise habits could be adjusted" accordingly.
With approximately 13% of the U.S. population diagnosed with diabetes and another 98 million with prediabetes, Snyder emphasized that "a widely accessible technology that pinpoints diagnostic details would be a game changer for diabetes care."
Tracey McLaughlin, MD, a professor of endocrinology and co-senior author of the study alongside Snyder, highlighted the complexity within Type 2 diabetes. She explained that while many people are simply labeled as having 'Type 2,' there are different physiologies leading to this condition. “Our goal was to find a more accessible, on-demand way for people to understand and improve their health,” she said.
The AI-powered algorithm has shown promise in identifying metabolic subtypes such as insulin resistance and beta-cell deficiency with greater accuracy than traditional tests. The study included 54 participants who used continuous glucose monitors alongside oral glucose tests conducted in clinical settings.
McLaughlin mentioned additional benefits for those using these monitors: “Even if a person with insulin resistance doesn’t develop diabetes, it’s still important to know because insulin resistance is a risk factor for other health conditions.”
The research paper was published on December 23 in Nature Biomedical Engineering. Ahmed Metwally, PhD, formerly at Stanford Medicine and now at Google, served as lead author.
The project received funding from several institutions including The National Institutes of Health and The American Diabetes Association.
Stanford's Department of Genetics and Department of Medicine supported this work.
Alerts Sign-up