We recently reported that the Apple Watch can detect hypertension and sleep apnea with very high accuracy. Now a new Cardiogram and UCSF study came out with a staggering result: The Apple Watch can detect diabetes with 85% accuracy!
Cardiogram co-founder Johnson Hsieh stated that their deep learning neural network called Deepheart, analyzed more than 200 million heart rate and step measurements, from a sample size of 14 thousand individuals. Deepheart was able to distinguish individuals with and without diabetes with extremely high accuracy.
Brandon Ballinger from Cardiogram also adds: “According to the CDC, more than 100 million U.S. adults are now living with prediabetes or diabetes. 1 in 4 of those with diabetes are undiagnosed and, even worse, 88.4% of people with prediabetes don’t realize they have it. While there have been many attempts to build special-purpose glucose-sensing hardware to detect diabetes, this is the first large-scale study showing that ordinary heart rate sensors—when paired with an artificial intelligence-based algorithm—can identify early signs of diabetes.”
These and previous results from Cardiogram’s Deepheart neural network are very promising. We reported that the Cardiogram team helped predict hypertension with 82% and sleep apnea with 90% accuracy.
The problem with these medical conditions is that they very frequently remain undiagnosed, which can lead to more health related issues later on. If only the heart rate sensor on your wrist and Cardiogram’s Deepheart neural network can with a high probability predict medical conditions, then everyone should own an Apple Watch, just for its health benefits. Some health insurance companies, as well as doctors highly recommend using an Apple Watch as a health monitoring device.
Rest assured that 2018 will be a promising year for the intersection between the Apple Watch and its new health applications.