Authors: Martha Powell, Future Science Group
A study assessing de-identified resting heart rate and sleep data from wearable devices has suggested that this could improve the real-time prediction of influenza-like illness.
Past studies have tried to utilized crowdsourced data, such as Twitter and Google flu trends, as indicators of flu-like illness, with results demonstrating variable success as independent surveillance methods. In this research, recently published in The Lancet Digital Health, the team studied de-identified data from 200,000 Fitbit users across five US states on the rationale that resting heart rate tends to spike during infectious episodes, and that this information is captured by wearable devices.
The Fitbit users – who were from California, Texas, New York, Pennsylvania and Illinois – wore their device consistently during the study period, which constituted at least 60 days between March 2016 and March 2018. The team collected a total of 13,342,651 daily measurements and each user’s average resting heart rate and sleep duration were calculated, as well as deviations to this, to identify when these measures were outside of an individual’s typical range.