Healthcare providers may soon be counting on Watson to help those with diabetes avoid hypoglycemic events.
In a partnership announced at this year’s CES conference in Las Vegas, Medtronic and IBM’s Watson Health division are joining forces to integrate cognitive computing into diabetes devices and mHealth platforms. The goal is to give diabetics and their caregivers the tools to identify potential hypoglycemic events, which sometimes prove fatal.
The project combines two of mHealth’s rising stars – wearables and predictive analytics. IBM and Medtronic officials say that data pulled from blood glucose meters and wearable activity trackers and analyzed by Watson can indicate a hypoglycemic trend as many as three hours before the crisis occurs. This could enable both patient and doctor to spot that downward spiral and take steps to prevent it before it becomes a crisis
“Managing diabetes varies greatly by individual and requires making numerous daily decisions related to eating, activity, exercise and medication in order to keep glucose levels under control,” Annette Bruls, president of Ireland-based Medtronic’s global diabetes service and solutions unit, said. “If a person with diabetes glucose levels drops too low, they face the threat of hypoglycemia, which can cause confusion or disorientation and in its most severe forms loss of consciousness, coma or even death. Conversely, if their glucose level is too high over a long period of time, they risk cardiac disease, blindness, renal failure and amputation of fingers and limbs.”
Diabetes is nearing epidemic proportions all over the world, and is often considered the most prevalent chronic condition – and a condition that could benefit greatly from mHealth. The International Diabetes Federation estimates the global diabetic population at more than 387 million, collectively creating a $612 billion healthcare bill in 2014. In the U.S., the American Diabetes Association estimates 29.1 million – or more than 9 percent of the population – have diabetes, with another 86 million having pre-diabetes and 1.4 million new cases being diagnosed each year.
IBM and Medtronic officials expect to launch their app this summer. The algorithms behind the app, they said, are based on de-identified data from some 150 million patient days gathered through Medtronic’s array of wearables. Adding Watson to the mix, they said, will give the app the ability to learn as it gathers data from each individual user.
“The models used in this pilot will be designed to continue to evolve according to a user’s nutrition and activity habits along with other contextual information, which may improve the ability of Watson to predict glycemic excursions and other trends through the Medtronic app,” Bruls said. “As our collaborative work continues, we expect to make more pattern discoveries that can be built into future additional predictive insights.”
"(I)magine you are a patient with diabetes - it would help you tremendously to know when I get up in the morning and I walk my glucose level is at this level, when I eat oatmeal it goes to this level, when I eat ice cream to this level," Deborah DiSanzo, general manager of IBM Watson Health, said in a press release issued at CES.
The platform also holds potential for population health programs. By combining the platform with EMRs, health claims and other data, providers can identify at-risk populations and develop targeted therapies.
“Using these types of critical insights, we can empower clinicians with protocols to intervene at the right moment, with the right therapies to improve outcomes and lower cost,” Bruls said. “In addition, we look to leverage real-time information to help care providers develop personalized care plans.”
It’s not the first time that providers have eyed mHealth tools in a bid to identify hypoglycemic events. In 2014, Boston’s Joslin Diabetes Center launched the HypoMap, a mobile tool developed by Glooko that enables diabetics and their caregivers to identify low blood sugar readings that are trending toward hypoglycemia.
Much like the Medtronic-IBM partnership, the platform gathers information from various sources – often independent of the patient’s monitoring efforts. This is especially important to the percentage of diabetics who can’t sense when their blood sugars are low, and thus have no way of knowing if they’re becoming hypoglycemic.
“Patients rarely have an accurate recollection of the factors leading up to a hypoglycemia episode that occurred months before, and the opportunity to identify underlying causes and, therefore, prevent recurrences is lost,” Howard Wolpert, MD, director of the Joslin Institute for Technology Translation, said in a 2014 press release. “For the first time, clinicians can have substantive discussions about specific hypoglycemic events using key contextual data such as symptoms, causes and treatments recorded in real-time, and subsequently help patients to improve their diabetes self-management skills and prevent future episodes.”
The Medtronic deal was one of three announced at CES, as IBM Watson makes a push to embed cognitive computing in several mHealth platforms. In separate deals, IBM will be partnering with Apple to integrate Watson-based apps in the HealthKit and ResearchKit platforms and working with Johnson & Johnson to create a “personal concierge service” that helps patients prepare at home for upcoming knee and hip surgeries.