Mobile App Warns Diabetics of Dangerous Sugar Levels

A new predictive tool analyzes blood glucose data to determine the likelihood of a hypoglyemic episode within the next several hours.

The Medtronic (Dublin, Ireland) Sugar.IQ app is a personal diabetes assistant with cognitive abilities that uses IBM (Armonk, NY, USA) Watson analytics capabilities to find patterns in diabetes data and offer real-time, personalized diabetes insights by continually analyzing how blood glucose levels respond to food intake, insulin dosages, daily routines, and other factors. Together with the Guardian Connect continuous glucose monitor (CGM), the Sugar.IQ app can turn trend patterns into personalized diabetes care.


Sugar.IQ is powered by the IBM Watson IQcast feature, which uses artificial intelligence (AI) predictive modelling to improve prognostic capabilities over time. A study presented at the last American Diabetes Association Scientific Sessions, which was held in July 2018 in Orlando (FL, USA), showed that Sugar.IQ users are more likely to achieve an extra 36 minutes per day in a healthy glucose range of 70-180 mg/dL, experiencing 30 minutes less time per day in hyperglycemia, and six minutes less daily in hypoglycemia.

“Avoiding complications like hypoglycemia is a tremendous burden, but fortunately it is a problem that can help be alleviated by learning from data, which is where AI comes in,” said Lisa Latts, MD, deputy chief health officer at IBM Watson Health. “Using machine learning models and predictive algorithms, IQcast analyzes multiple signals coming from a user, such as glucose levels, insulin data, food logs, and prior hypoglycemic events to assess whether a user has a low, medium, or high chance of experiencing hypoglycemia within the upcoming four hours.”