Wearable Devices Can Predict Clinical Lab Measurements

Commercial wearable devices containing sensors can predict clinical laboratory measurements, including a more precise depiction of resting heart rate, than measurements taken in the clinic, according to a study published online May 24 in Nature Medicine.

Jessilyn Dunn, Ph.D., from the Stanford University School of Medicine in California, and colleagues examined whether vital signs as measured by consumer wearable devices can predict clinical laboratory test results using machine learning models.

The researchers found that compared with measurements taken in the clinic, vital sign data collected from wearables gave a more consistent and precise depiction of resting heart rate. Data collected from wearables could also predict several clinical laboratory measurements with lower prediction error than predictions based on vital sign measurements obtained clinically. The performance of the machine learning models was largely reliant on the length of time over which vital signs were monitored and the proximity of the monitoring period to the date of prediction.

“I think this is just the beginning,” Dunn said in a statement. “Devices are becoming much more sensitive and with many more capabilities. As the technology continues to advance, people will be better equipped to understand what’s going on with their own health in real time, just through their wearable devices.”

One author disclosed financial ties to the medical device industry.

Abstract/Full Text (subscription or payment may be required)

Read More About Cardiology