Fitbit data could help predict flu outbreaks

Public health experts said the use of data from wearable devices such as Fitbits should not be overplayed, as research emerged showing that such data could help to predict outbreaks of influenza-like illnesses.

The research, published in The Lancet Digital Health journal, explains that resting heart rate tends to spike during infectious episodes and this is captured by devices. The researchers reviewed de-identified data from 200,000 Fitbit users and compared it to weekly estimates for influenza-like illness rates reported by the US Centers for Disease Control (CDC). As a result, there was an improvement in real-time surveillance.

Will Durant, campaigns and communications executive at the Royal Society for Public Health, said: “In England, Public Health England uses a number of measures when it reports back on a flu season, including self-reported surveys, reports from GPs on their consultations, lab tests and many more. Fitbit data could add to this flu-monitor arsenal, with the added value of being in real-time and giving geographical detail.”

However, he added: “Tech is not a preventative measure in and of itself, and should not be regarded as a substitute for effective prevention such as immunisation or targeted hygiene.”

His concerns echoed the limitations that the researchers themselves identified with their work. “Claims about its potential should not be overplayed,” Durant said. “Not everyone has a Fitbit, so the data may be biased towards people with good mobility who have the device, which is a problem because less mobile groups such as the elderly and people with chronic conditions are at far greater risk of flu and are very important to monitor.”

Influenza results in 650,000 deaths worldwide annually. Approximately 7% of working adults and 20% of children aged under five years get flu each year, according to The Lancet.