In response to the pressure to reduce hospitalization costs for people who develop complications from not being able to manage diabetes, digital health and medical device companies are advancing apps that can help people take action to avoid developing hypoglycemic or hyperglycemic events.
InSpark Technologies has launched its Vigilant app in the U.S. that works with connected glucometers to search data for patterns and give users feedback on how well they are managing their condition and what they can do to improve. It claims to be able to inform them of their risk for developing hypoglycemic event 24 hours ahead of time. It uses pattern analysis to provide users assessments on when their blood glucose tends to be high or low in the morning, afternoon, and evening and what action they can take to improve on that.
When Investment Rhymes with Canada
Canada has a proud history of achievement in the areas of science and technology, and the field of biomanufacturing and life sciences is no exception.
The app is based on technology licensed from the University of Virginia Licensing and Ventures Group.
In a phone interview InSpark Founder Erik Otto, who previously worked for Johnson & Johnson, noted that the company had conversations with the U.S. Food and Drug Administration when it was developing the Vigilant app. The regulator classified its approach as a medical device data system and a medical app. It does not provide advice on dosages so it is not subject to 510(k) clearance. It also recently dropped a requirement that apps that connect to a glucometer require 510(k) clearance.
Otto also emphasized the value of its approach and what other companies, such as Medtronic, are doing. “There’s a lack of these technologies to analyze patient data and bring value to blood-glucose tests beyond telling people they are under or over. what their level should be. These technologies can provide meaningful feedback.”
Earlier this year, IBM and Medtronic announced a collaboration that would add a machine learning component to Medtronic’s app continuous blood glucose meter to predict hypoglycemic events a few hours ahead of time. Otto pointed out that the Medtronic-IBM collaboration involves many more variables and datasets than its own approach.
Asked if he considered InSpark’s approach machine learning, he said he preferred not to use the term machine learning. “It’s more accurate to call this pattern recognition.”
Looking ahead, it plans to seek regulatory approval for its app in Europe.
