Heart Disease

Fitness tracker algorithm catches 98% of irregular heart rhythm episodes

Results of a new study funded by Fitbit are currently being reviewed by the FDA
Results of a new study funded by Fitbit are currently being reviewed by the FDA

The first results have been revealed from a massive study testing a new algorithm designed to detect irregular heart rhythms using data from smartwatches and fitness trackers. Enrolling nearly half a million subjects, the study successfully detected undiagnosed atrial fibrillation in 98 percent of cases.

Irregular intervals between heart beats, known as atrial fibrillation, can be an early sign of cardiovascular disease. Serious episodes of atrial fibrillation can manifest in symptoms similar to that of a heart attack, but shorter episodes can be asymptomatic.

The advent of wearable health monitoring devices offers new ways to detect early asymptomatic episodes of abnormal heart rhythms but researchers are still improving the technology to increase accuracy and reliability. A large Stanford study in 2019 demonstrated the potential for Apple Watches to detect instances of atrial fibrillation, and now FitBit has followed with its own big study, slightly improving on Apple’s results.

Conducted by researchers from Massachusetts General Hospital (MGH) the study recruited around 455,000 fitness tracker users in the United States. Once activated, the novel algorithm tracks a user’s pulse rate during periods of inactivity. Possible atrial fibrillation is noted after at least 30 minutes of irregular heart rhythms.

In the study, when possible atrial fibrillation was detected the subject completed a telehealth consultation with a doctor and then received an electrocardiogram (ECG) patch to wear for one week alongside the fitness tracker. In the week that followed, the new algorithm effectively picked up 98 percent of atrial fibrillation episodes detected by the ECG patch.

“These results show that wearables have the ability to identify undiagnosed atrial fibrillation with high reliability,” says Steven Lubitz, a researcher from MGH working on the project. “Since so many consumers use wearables, it is possible that algorithms such as the one we studied could be applied widely to help identify undiagnosed atrial fibrillation, allowing patients to obtain care before devastating complications such as a disabling stroke may occur.”

Lubitz indicates the heart monitoring software would be most effective when used at night. So the goal would be to wear the fitness tracker during sleep when it can best track irregular heart rhythms.

“Most of the episodes of undiagnosed atrial fibrillation detected occurred during sleep, and we suspect that these episodes were asymptomatic,” adds Lubitz. “Since the algorithm is most active when wearers are physically inactive, the wearable should be worn during sleep for the greatest benefits.”

Fitbit is currently working with the US Food and Drug Administration (FDA) for market authorization to allow the algorithm to be widely deployed.

Source: American Heart Association

  • Facebook
  • Twitter
  • Flipboard
  • LinkedIn
3 comments
paul314
What was the false positive rate? Because when you're deploying something to tens of millions of people, that can be important.
CAVUMark
Well, I hate to say it but, sign me up.
michael_dowling
paul314 : I would rather risk a false positive,which can be ruled out pretty easily by wearing an electrocardiogram (ECG) patch for a week,than risk a stroke,which could be fatal or crippling.