Fitbit data on heart rate and sleep duration could help predict flu outbreaks in real-time, says new study

Fitbit data on heart rate and sleep duration could help predict flu outbreaks in real-time, says new study
(Getty Images)

The Fitbit you wear can do much more than just track how active or lazy you are. It can actually help health officials predict flu outbreaks in real-time, according to a new study.

Analysis of de-identified data from wearable devices on resting heart rate and sleep shows improved real-time prediction of influenza-like illness in five US states compared to current surveillance methods, say researchers from the Scripps Research Translational Institute, US. 

To sufficiently measure changes at a population level, the researchers only evaluated users from the top five states with the most Fitbit users in their dataset: California, Texas, New York, Illinois, and Pennsylvania.

They found that by incorporating data from Fitbit trackers, influenza predictions at the state level were improved.

According to researchers, the study demonstrates the potential of data from wearable devices to improve the surveillance of infectious diseases. Resting heart rate tends to spike during infectious episodes and this is captured by wearable devices such as smartwatches and fitness trackers that track heart rate, they explain.


"Activity and physiological trackers are increasingly used in the US and globally to monitor individual health. By accessing these data, it could be possible to improve real-time and geographically refined influenza surveillance. This information could be vital to enact timely outbreak response measures to prevent further transmission of influenza cases during outbreaks," says the team in their findings published in The Lancet Digital Health.

"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 a weekly basis," says study author Dr Jennifer Radin, Scripps Research Translational Institute, in the analysis.

To sufficiently measure changes at a population level, the researchers only evaluated users from the top five states with the most Fitbit users in their dataset: California, Texas, New York, Illinois, and Pennsylvania (Getty Images)


Flu outbreaks in the US

Influenza results in up to 650,000 deaths worldwide each year. In the US, approximately 7 percent of working adults and 20 percent of children younger than 5 years of age get influenza annually. 

According to estimates by the US Centers for Disease Control and Prevention (CDC), from October 1, 2019, through January 11, 2020, there have been 13,000,000-18,000,000 flu illnesses and 6,600-17,000 flu deaths.

“Most people who get sick with flu will have a mild illness, will not need medical care or antiviral drugs and will recover in less than two weeks. Some people, however, are more likely to get flu complications that can result in hospitalization and sometimes death,” says the CDC.

Source: CDC


Conventional surveillance reporting takes one to three weeks to report. This limits the ability to enact quick outbreak response measures such as ensuring patients stay at home, wash hands, and deploying antivirals and vaccines, say health experts. 

"Traditional influenza surveillance relies largely on a combination of virologic and syndromic influenza-like illness (ILI) surveillance to estimate influenza trends. However, ILI surveillance has a 1–3-week reporting lag and is often revised weeks later by the CDC," says the study.

Several groups have attempted to use rapid influenza tests, data on internet search terms (for example, Google Flu Trends), and social media outlets such as Twitter to provide real-time influenza surveillance. However, despite some success, Google Flu Trends was found to miss early waves of the 2009 H1N1 pandemic influenza, and overestimate activity during outbreaks, say experts. 

"The challenge with using these methods is distinguishing between activity related to an individual’s own illness and those related to media or heightened awareness and interest about influenza during the influenza season. Consequently, there is a great need to enhance traditional ILI surveillance with new objective data streams that can provide real-time information on influenza activity," says the team.


How it worked

Through a research collaboration between Scripps Research Translational Institute and Fitbit, the team obtained de-identified data from a sample of 200,000 consistent users who wore a Fitbit device from March 1, 2016, until March 1, 2018. These users wore their Fitbit for at least 60 days during this study time and had only one Fitbit tracker for the whole period. 

"We originally obtained more than 65 million measurements from 200,000 Fitbit users. Among those, 47,249 users totaling 13,342,651 daily measurements from five of the most populous states met inclusion criteria. The mean age of included individuals was 42.7 and 28,465 (60.2 percent) were female," adds the study.

The research team calculated the average resting heart rate and sleep duration of the users, as well as deviations to this. This was done to identify when these measures were outside of an individual's typical range, that is, using standard deviation. 

The research team calculated the average resting heart rate and sleep duration of Fitbit users, as well as deviations to this (Getty Images)


During each week, a user was identified as abnormal if their weekly average resting heart rate was above their overall average - by more than a half or a full standard deviation.

Users were also identified as abnormal if their weekly average sleep was not below their overall average - by more than half a standard deviation.  The users were arranged by which state they lived in, and the proportion of users above the threshold each week was calculated. This data was compared to weekly estimates for influenza-like illness rates reported by the CDC. 

"In all five states, there was an improvement in real-time surveillance, and the closest alignment with CDC data was found when abnormal resting heart rate was defined as half a standard deviation above normal and sleep more than half a standard deviation below," says the study.

According to the authors, there are some limitations to the study. A general lack of activity data meant they could not control for seasonal fitness changes or more short-term activity changes.


Weekly resting heart rate averages may include days when an individual is both sick and not sick, and this may result in an underestimation of illness by lowering the weekly averages, they add. Other factors may also increase the resting heart rate, including stress or other infections. 

In a linked comment, Dr Cécile Viboud from the Fogarty International Center, National Institutes of Health, US, says the study "is a promising first step towards integrating wearable device measurements in predictive models of infectious diseases."  

"We welcome more health-related research involving Fitbit users, including studies that directly connect influenza sickness status with changes in resting heart rate. We anticipate that a large amount of real-time data generated by Fitbit and other personal devices will continue to prove useful for public health and augment traditional surveillance systems. The ever-expanding big data revolution offers unique opportunities to mine new data streams, identify epidemiologically relevant patterns, and enrich infectious disease forecasts," says Dr Viboud.


Disclaimer : This article is for informational purposes only and is not a substitute for professional medical advice, diagnosis, or treatment. Always seek the advice of your physician or other qualified health provider with any questions you may have regarding a medical condition.

Share this article:

 Your Fitbit Help Predict Flu Outbreaks Real Time heart rate sleep duration