If your Apple Watch knows you’ll get diabetes, who can it tell?

“On the morning of February 7, the Hilton New Orleans Riverside was packed with researchers for the final day of the Association for the Advancement of Artificial Intelligence’s thirty-second annual conference,” Caroline Haskins writes for The Outline. “Avesh Singh and Johnson Hsieh were there to present the first published research from their app Cardiogram, made using Apple’s HealthKit app developer.”

“Cardiogram’s machine learning algorithm, called ‘DeepHeart,’ ingested large amounts of health data, like heart rates and step counts, from wearables like Apple Watches and FitBit volunteered by participants. It also used information about users’ exercise, sleep, and emotional habits, which was handed over to Cardiogram from Health eHeart, a research project from the University of California San Francisco,” Haskins writes. “With all this information, DeepHeart predicted early signs of diabetes, high cholesterol, high blood pressure, and sleep apnea in more than 14,000 people. It turned out DeepHeart was accurate 85 percent of the time.”

“By tantalizing people with the idea of predicting diabetes or other health issues, apps like Cardiogram or devices like the Apple Watch get people to volunteer personal biometric data that can be synthesized together,” Haskins writes. “But these companies can pass that data on to new services, apps, and research projects, without giving people a clear sense of where the data is going or what their rights are. Sometimes the data is collected in such a way that the people who were talked into volunteering it have few rights to it at all — not who sees it, where it lives, or how long it’s kept.”

Read more in the full article here.

MacDailyNews Take: Of course, this is an important issue that we need to tackle as wearables and machine learning become more prevalent.


  1. Cardiogram has issues.
    I read about this app and installed it.

    While my Apple Watch was sitting on a desk charging at night it showed a heart rate of well over 110 BPM which would be considered Tachycardia. The measurements from when I had the watch on showed a resting rate of about 60 BMP.

    Not sure how a watch can record an elevated HR when it is not being worn.

  2. For those who have diabetes Type 1 or 2 monitoring blood sugar levels by glancing at your Watch (without any other attachments) will be a game changer and make it so much easier to monitor and control. It would make a huge difference.

Reader Feedback

This site uses Akismet to reduce spam. Learn how your comment data is processed.