Despite now being hailed as the auto show, this year’s Consumer Electronics Show also featured quite a few healthcare technologies. During the opening keynote, IBM CEO Ginni Rometty and Medtronic CEO Omar Ishrak took the stage to announce a research concept for a cognitive app that uses predictive analytics to detect patterns in diabetic patients. Anticipated for release this summer, the app uses Watson’s cognitive computing power to integrate data from Medtronic’s continuous glucose monitoring devices and insulin pumps to get real trends, and will be able to predict a hypoglycemic event three hours in advance. “Watson takes it to a different league of performance,” said Ishrak during the keynote.
Leveraging predictive analytics could be a powerful tool in the new healthcare environment of improving clinical outcomes and lowering costs. In a Q&A with MedTech Intelligence, Annette Brüls, president of Diabetes Service and Solutions at Medtronic discusses the potential for the Medtronic-Watson app, which is still in development.
MedTech Intelligence: How does this app address daily challenges that diabetes patients face?
Annette Brüls: Every day, people with diabetes manage their disease by constantly monitoring the amount of sugars they take in and physical activity they exert to keep a stable glucose level. If their glucose level drops too low, they face the threat of hypoglycemia—an adverse event that can cause anything from confusion and disorientation to loss of consciousness, coma or, in the most severe cases, death. Conversely, if their glucose level is too high over a long period of time, this can often lead to cardiac disease, blindness, renal failure and amputation.
Medtronic’s app, once developed, will be able to analyze glucose levels in real-time by integrating data from a wearable activity tracker, a picture of the meal eaten, and through continuously analyzing the data from a glucose sensor and insulin pump. Based on these factors, the app could help users track and manage their glucose levels simply and efficiently.
The really exciting aspect of this app will be its predictive nature, however. Although additional study is required, early research suggests that this first-of-its-kind cognitive technology may be able to predict low blood sugar patterns as many as three hours in advance of a potential hypoglycemic event.
MTI: How do you foresee the cognitive app improving patient adherence in managing diabetes?
Brüls: Individuals with diabetes are one of the most informed and educated patient populations today. They are continuously tracking their physical activity levels as well as their carbohydrate and sugar consumption. An app like the one we are envisioning will further empower users to accurately monitor this information. Additionally, through the cognitive computing power of IBM Watson, notifications of potential hypoglycemic events will provide users with real-time insights to help them understand the impact of their daily activities on their diabetes and make adjustments as needed—making adherence easier than ever before.
MTI: Can you expand on the role that predictive analytics will play in the overall scheme of value-based healthcare?
Brüls: While we are currently focused on building a cognitive solution for managing diabetes, as the leading medical technology and healthcare solutions and services company in the world, we recognize the unique role predictive analytics will play in improving patient outcomes and lowering overall costs—the two central principles for transforming healthcare to a value-based system. Technologies that help keep patients healthy and prevent emergency room visits or readmissions will be critical to ensuring the adoption of value-based healthcare principles.
It’s not first of its kind. The PredictBGL App has been doing this (and cheaper and better I might add) since April 2015. You don’t need an insulin pump OR a CGMs to use predictions from PredictBGL.