A Fitbit could spot when you’re coming down with flu – before symptoms have even developed.
Researchers analysed 60 days of data from 47,248 Fitbit users living in the US to try and predict when they would get sick.
Tell-tale signs someone was about to get ill were higher heart rates than normal or excessive amounts of sleeping, both of which could be measured by the Fitbit.
The researchers said the breakthrough would allow at-home devices to predict flu outbreaks earlier so health officials could react faster to contain them.
Flu outbreaks can be controlled by making sure people get vaccinated and urging patients to stay at home and wash their hands regularly.
Antiviral drugs can also be used to limit the virus. Measures like this could be deployed sooner if doctors got early warning signs that the illness was spreading.
Fitbits are popular watch-like devices which users wear on their wrists to track their physical activity, heart rate and sleep patterns.
Study author Dr Jennifer Radin, from the Scripps Research Translational Institute in California, said: ‘Responding more quickly to influenza outbreaks can prevent further spread and infection, and we were curious to see if sensor data could improve real-time surveillance at the state level.
‘We demonstrate the potential for metrics from wearable devices to enhance flu surveillance and consequently improve public health responses.
‘In the future as these devices improve, and with access to 24/7 real-time data, it may be possible to identify rates of influenza on a daily instead of weekly basis.’
The study comes amid flu outbreaks in the UK and US, which have added extra pressure to hospitals already overwhelmed by winter demand.
The illness is more intense than a common cold and causes symptoms such as a fever, aching muscles, exhaustion, a lost appetite and headaches.
Flu kills around 650,000 people across the world every year.
The findings of the latest study were reported in the medical journal Lancet Digital Health.
People were flagged up as a flu risk if their weekly average heart rate rose above their normal level, or if they were sleeping more than they usually did. People become more tired when they catch flu because their body uses up its energy fighting the virus.
The data was then compared to weekly estimates for flu-like illness rates reported by the US Centers for Disease Control (CDC).
Dr Radin and her colleagues found that by incorporating the data from Fitbits, they were able to predict outbreaks sooner.
It was the first time heart rate trackers and sleep data had been used to predict flu, or any infectious disease, in real-time.
Scientists added that it may be possible to apply the method to larger areas such as counties or cities.
Traditional surveillance takes one to three weeks to collect reports from doctors, which limits the ability to be proactive and fight against flu outbreaks.
All users were notified when they bought their devices that their data could be used for research.
However, Dr Radin and her colleagues identified several limitations to the study.
Firstly, the general lack of activity data meant they could not account for how heart rates and amount of sleep may change because of other factors.
For example, a user’s average heart rate may have increased or decreased based on how much exercise they were getting and how physically fit they were.
In addition, weekly resting heart rate averages include days when an individual is both sick and not sick, and this may result in underestimation of illness by lowering the weekly averages.
They also warned that devices such as Fitbits have been known to be inaccurate, although the researchers recognised they would improve with advancing technology.
And because those who took part in the study were mainly middle-aged adults and likely higher than average earners, they were less likely to suffer from other problems which might make them more likely to get infections like the flu.
The researchers initially reviewed data from 200,000 Fitbit users.
The average user was 43 years old and 60 per cent were female.
The sample size was reduced by only using data from those who used their Fitbits consistently during the study period, which was from March 2016 to March 2018.