A new study published in the Lancet Digital Health shows that resting heart rate (RHR) and other metrics from wearable devices have the potential to improve real-time surveillance of influenza-like illness (ILI).
This US based study analysed de-identified data from 47,249 individuals who used a Fitbit consistently for at least 60 days. Daily measurements missing RHR or wear time or participants with wear time
Sensor data was compared with weekly estimates of influenza-like illness (ILI), identifying weeks where RHRs and sleep levels were increased. Over 31.3 million measures were obtained.
Pearson correlation was used to compare predicted versus reported ILI cases. Fitbit data significantly improved ILI predictions, with an average increase in Pearson correlation of 0·12 (SD 0·07) over baseline models, corresponding to an improvement of 6·3-32·9 per cent. In most cases, week-to-week changes in Fitbit users with abnormal data were associated with week-to-week changes in ILI rates.
These data show that improving real-time geographical influenza surveillance may be possible by accessing data from wearable devices. This could be vital to enact timely outbreak response measures and prevent further transmission.