“We designed the AI algorithm entirely using a mathematical simulator, and yet when the algorithm was validated on real-world data from people with type 1 diabetes at OHSU, it generated recommendations that were highly similar to recommendations from endocrinologists,” said lead author Nichole Tyler, MD, PhD, in a press release.
Tyler added that this is a significant finding since people with diabetes go approximately 3 to 6 months between appointments with their endocrinologist. Patients can be at risk of dangerous complications if glucose levels in their blood rise too high or fall too low.
The algorithm developed by OHSU scientists uses data collected from a continuous glucose monitor and wireless insulin pens to provide guidance on adjustments. Paired with a smart phone app called DailyDose, the recommendations from the algorithm were shown to be in agreement with physicians 67.9% of the time, according to the press release.
The new study involved monitoring 16 people with type 1 diabetes over the course of 4 weeks, showing that the model can help reduce hypoglycemia. If hypoglycemia is left untreated, it can cause coma or death.
“There are other published algorithms on this, but not a lot of clinical studies,” said senior author Peter Jacobs, PhD, in a press release. “Very few have shown a statistically relevant outcome—and most do not compare algorithm recommendations with those of a physician. In addition to showing improvement in glucose control, our algorithm-generated recommendations that had very high correlation with physician recommendations with over 99% of the algorithm’s recommendations delivered across 100 weeks of patient testing considered safe by physicians.”