Researchers at Stanford University analyzed resting heart rate and step counts from thousands of volunteers wearing consumer smartwatches and fitness trackers, comparing each person's data against their own normal baseline rather than a population average.
Among 32 confirmed COVID-19 cases in the study, a real-time alert built on elevated resting heart rate could have flagged 63 percent before symptoms began, and some changes appeared more than a week early, using only a smartwatch and no test.
The signal is a deviation from a person's own baseline, not a diagnosis, so it cannot say what someone is infected with, only that something is off. The team later refined the alert system to cut false alarms, and versions of the approach have since been tested for flagging other infections, not only COVID-19.
Read the original study
Mishra et al., Nature Biomedical Engineering, 2020 · doi.org/10.1038/s41551-020-00640-6
A watch noticed the infection before symptoms did.
Source
- Mishra, T., Wang, M., Metwally, A. A., Bogu, G. K., Brooks, A. W., Bahmani, A., Alavi, A., Celli, A., Higgs, E., Dagan-Rosenfeld, O., Fay, B., Kirkpatrick, S., Kellogg, R., Gibson, M., Wang, T., Hunting, E. M., Mamic, P., Ganz, A. B., Rolnik, B., . . . Snyder, M. P. (2020). Pre-symptomatic detection of COVID-19 from smartwatch data. Nature Biomedical Engineering, 4(12), 1208–1220. https://doi.org/10.1038/s41551-020-00640-6