Medtronic and IBM Watson Health recently announced a new feature for the Sugar.IQ diabetes management app that can predict when low blood sugar will occur within the next 1-4 hours. This new feature, IQcast, is part of Medtronic’s iOS-compatible app and uses IBM’s artificial intelligence (AI) alongside Medtronic’s diabetes devices.
With over 100 million cases of diabetes being diagnosed worldwide, the disease is among the most common in the world. IBM notes that those with type 1 diabetes are estimated to face an average of 180 decisions a day about consuming food, sleep, insulin, and physical activity to manage their blood sugar. In the most severe cases of diabetes, those who simply skip a meal may experience hypoglycemia, characterized by dangerously low blood sugar.
Medtronic and IBM’s IQcast feature aims to alleviate this stress from the diabetic patient by using AI and diabetic tools to predict when one’s blood sugar is likely to become low hours in advance. To do this, IQcast applies machine learning algorithms to metrics generated from Medtronic’s Guardian Connect continuous blood sugar monitoring system. This AI-driven approach allows IQcast to not only predict when low-glucose events will occur, but to provide recommended steps to reduce the chance of a future dip in blood sugar.
“Simply put, IQcast acts like a weather forecast for people with diabetes so they can better prepare for their day,” said Dr. Robert Vigersky, senior director of medical and clinical affairs at Medtronic’s Diabetes Group. “By predicting the likelihood of a low glucose event … [it] helps people with diabetes better prepare for their day so they can live their life with greater freedom and better health.”
IQcast reports to the Sugar.IQ user about a potential upcoming hypoglycemic event by grading the risk severity as low, medium, or high. IBM claims that the prediction’s accuracy improves as the decrease in blood sugar becomes more impending.
“Hypoglycemia, or ‘going low’, is one of the most acute and frightening events that a person living with diabetes can experience,” said Dr. Lisa Latts, deputy chief health officer at IBM Watson Health. “Fueled by the right data, AI and machine learning can play a powerful role in helping to alleviate the burden of diabetes and the worry of a hypoglycemic event, and we’ve built the new IQcast features with this goal in mind.”
With Google’s recent launch of an AI program in Thailand that screens diabetic patient’s for eye disease, Medtronic and IBM are a part of the growing movement to implement AI into diabetes management. Machine learning has recently been used in many diagnostic processes as well, including cancer cell identification, cardiovascular disease, and visual deficiencies.
“Technology alone cannot alleviate the burden of managing diabetes,” said Latts. “As we continue to work with our partners to find greater ways in which technology can help clinicians and those living with diabetes to manage their condition, we are confident that the ultimate best solution will be one in which patient engagement, professional care, technology, data and informatics all come together to optimize treatment.”
Medtronic, IBM Watson diabetes app gains hypoglycemia prediction feature https://t.co/fAtEG9UlAi
— Berci Meskó, MD, PhD (@Berci) January 4, 2019