CVS and IBM are teaming up to use AI to predict when people are getting sick

IBM will begin to use its Watson artificial intelligence system to improve patient care for a growing number of people, especially those with chronic diseases, the company said Thursday, in a statement announcing a new partnership with CVS.

Teaming up with CVS - which has more than 7,800 pharmacies and more than 900 MinuteClinics - will give IBM a chance to unleash its Watson Health platform on the massive population of patients served by the pharmacy giant. The resulting analytics, IBM suggests, could help patients manage chronic diseases like diabetes and hypertension and help predict which patients are getting sicker - sometimes before they even know it.

"We're very excited about the ability to leverage a data-driven [approach] and cognitive analytics to better understand and predict what's going to happen with folks," Kathy McGroddy-Goetz, VP of Partnerships and Solutions for Watson Health, told Tech Insider.

Patients tend to be at their local CVS much more frequently than at the doctor, McGroddy-Goetz pointed out. People are also increasingly using fitness trackers like FitBits, smartwatches, and even Bluetooth-enabled scales that are all collecting data patients can choose to share with a provider. All that data isn't worth much though unless it is carefully interpreted - something Watson can do much more efficiently than a team of people.

"The Watson computing system can access health records, pharmacy information and other resources to help CVS Health employees provide guidance to patients and work with primary care doctors," Jennifer Calfas explained in USA Today.

A drop in activity levels, a sudden change in weight, or prescriptions that aren't being filled are the kinds of things that might be flagged by the system, McGroddy-Goetz suggested, adding that the way it works will vary depending on what information a patient chooses to share and what chronic conditions they are managing. Certain changes could even indicate a developing sickness before someone feels ill - and certainly before someone decides to visit the doctor.

McGroddy-Goetz also mentioned the potential usefulness of a Watson-CVS combined system to insurance companies and self-insured employers especially. "It could help address absenteeism and help people have a better quality of life," she said. "That's a win for everyone."

While McGroddy-Goetz emphasized that users will get to decide how much data they want to share, "big data" solutions to healthcare problems often raise some privacy concerns.

"Federal patient privacy rules ... don't apply to most of the information the gadgets are tracking," Ariana Eunjung Cha pointed out in The Washington Post, in a story on digital health in general, not Watson in particular. "Unless the data is being used by a physician to treat a patient, the companies that help track a person's information aren't bound by the same confidentiality, notification and security requirements as a doctor's office or hospital."

That's part of the trade-off in what McGroddy-Goetz calls "empowering [patients] to take care of their own health."

The specifics and logistics of the partnership are still being worked out. IBM hopes to roll out the Watson system in CVS stores starting sometime in 2016.