Other factors like stress and other infections, may also increase the resting heart rate, the study said. (Photo Credit: Stock image )
Los Angeles:
Researchers have reported for the first time that the resting heart rate, and sleep data from wearable devices can be used for real-time prediction of infectious diseases like influenza, an advance that may lead to new ways of forecasting epidemic outbreaks. According to the study, published in the journal The Lancet Digital Health, people's resting heart rate spikes up during infections, and this is captured by wearable devices like smartwatches, and fitness trackers like Fitbit.
The researchers, including those from Scripps Research Translational Institute in the US, de-identified data from 47,249 Fitbit users, and retrospectively identified weeks during which they had elevated resting heart rate, and changes to routine sleep. They said tracking outbreaks of influenza -- which kills nearly 6,50,000 people every year globally -- had previously been attempted by analysing crowdsourced user search data in Google Flu Trends and Twitter.
However, the scientists said, in these methods it is impossible to separate out the activity of individuals with influenza from the heightened awareness people get from media during flu season.
In the current study, the researchers demonstrated the potential for metrics from wearable devices to enhance flu surveillance, and consequently improve public health responses.
Traditional surveillance, they said, usually takes 1-3 weeks to report the incidence of influenza outbreaks, which limits the ability to quickly roll out response measures like ensuring patients stay at home, wash hands, and deploying antivirals and vaccines.
But combined with the sensor data from smartwatches and fitness trackers, the scientists said real-time surveillance can be improved significantly at the state level.
"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," said Jennifer Radin, study co-author from Scripps Research Translational Institute.
As part of the study, the researchers assessed data from 2,00,000 users who wore a Fitbit wearable device that tracked their heart rate and sleep for at least 60 days during the study time from March 2016 to March 2018.
From these users, they found that 47,248 people from California, Texas, New York, Illinois and Pennsylvania wore a Fitbit device consistently during the study period, resulting in a total of 13,342,651 daily measurements.
According to the researchers, the average user was 43 years old, and 60 per cent were female. The average resting heart rate and sleep duration of the users were calculated, along with deviations to these parameters to help identify when these measures were outside of an individual's typical range.
In a week, the researchers said, a user was identified as abnormal if their weekly average resting heart rate was above their overall average, and their weekly average sleep was not below their overall average.
The scientists then arranged the users based on the state they lived in, and the proportion of users above the threshold was calculated each week.
Comparing this estimate to the weekly assessment for influenza-like illness rates reported by the US Centers for Disease Control (CDC), the researchers found that the influenza predictions at the state level were significantly improved.
The study noted that there was an improvement in real-time surveillance in all the five states from which the users stayed. According to the scientists, it may be possible to apply the method to more geographically refined areas, such as county or city-level with greater volumes of user data.
However, the researchers cautioned that the study could not control for seasonal fitness differences, or more short-term activity changes.
Citing another limitation of the study, they said, the weekly resting heart rate averages may include days when an individual is both sick and not sick, and this may result in underestimation of illness by lowering the weekly averages.
Other factors like stress and other infections, may also increase the resting heart rate, the study said.
