Here is a sample screenshot of the Sugar.IQ smart diabetes assistant, co-developed by Medtronic and IBM Watson Health.Medtronic plc and IBM Watson Health
A year ago Medtronic and IBM Watson Health launched a co-developed app dubbed the Sugar.IQ smart diabetes assistant.
The app was designed to simplify and improve daily diabetes management by leveraging artificial intelligence and analytic technologies from IBM Watson Health to continually analyze how an individual's glucose level responds to their food intake, insulin dosages, daily routines, and other factors. The idea is that the app will help people with diabetes uncover patterns that affect their glucose levels, which can help them make small adjustments throughout the day to stay on track.
So far, it appears to be working.
Researchers presented real-world data on Medtronic's Guardian Connect continuous glucose monitoring (CGM) system and the Sugar.IQ app at the American Diabetes Association's annual meeting in San Francisco this week.
The data found that people using the Guardian Connect system with the Sugar.IQ app experienced 4.1% more time in range (63.4%) compared to those who used the Guardian Connect alone (59.3%) which represents about one extra hour a day. Those who also used the optional Glycemic Assist feature to review their response to specific foods increased their time in range by an additional 4% compared to those not using that feature.
Time in range is the percentage of time people with diabetes spend in the optimal glycemic range of 70-180 mg/dL. Every 4% change in the time in range represent an approximate 0.3% change in A1C2. The goal of diabetes management is to increase the time spent in this target range and to minimize high and low glucose levels. The study found that Sugar.IQ users found the insights helpful in managing their diabetes 91% of times.
The study, which collected data from more than 3,100 people with diabetes who used Guardian Connect system for at least five days, also found the overall system's predictive alerts reduced low sensor glucose excursions by almost two-fold and high sensor glucose excursions by four-fold compared to those not using Sugar.IQ. Avoidance of high and low episodes is a critical aspect of diabetes management. These data were shared during a poster presentation on "Real-World Performance of the Guardian Connect System with Sugar.IQ" by Siddharth Arunachalam.
"Sugar.IQ is the first app to use machine-learning to detect glucose level patterns for advanced notification of low and high events associated with diabetes," said Michael Hill, vice president and general manager of the multiple daily injection solutions business, which is part of Medtronic's diabetes group. "These results suggest the Sugar.IQ diabetes assistant, together with our Guardian Connect system, may help patients better understand glucose trends and increase their time in range, aiding in behavior change which may ultimately help improve clinical outcomes."
For other MD+DI coverage of this year's American Diabetes Association meeting, see these stories: Abbott's FreeStyle Gets Real-World Results, Could Revita DMR be an Alternative to Insulin Use?