Fitbit algorithm reliably detects atrial fibrillation

Reuters Health - 17/11/2021 - A novel photoplethysmography (PPG) software algorithm for Fitbit wearables and smartwatches may allow large-scale identification of undiagnosed atrial fibrillation (AF), according to the Fitbit Heart Study.

"These results show that wearables have the ability to identify undiagnosed atrial fibrillation with high reliability," Dr. Steven Lubitz, of Harvard Medical School and Massachusetts General Hospital, in Boston, said in a statement from the American Heart Association (AHA) scientific sessions, where he presented the results.

"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," said Dr. Lubitz.

The algorithm examines overlapping five-minute pulse tachograms during inactivity, with an irregular-heart-rhythm detection (IHRD) notification triggered when 11 consecutive tachograms are irregular.

The Fitbit Heart Study enrolled more than 455,000 adults (71% women) with no prior AF diagnosis. Their median age was 47 years, with 12% aged 65 and older.

During the study, IHRDs occurred in 4,728 (1%) individuals overall, including 2,070 (4%) of those aged 65 and older.

Among the 1,057 individuals with an IHRD notification who subsequently wore an ECG patch monitor, "32% had atrial fibrillation confirmed on the monitor," Dr. Lubitz reported at a press briefing featuring the study.

The overall positive predictive value (PPV) of the PPG Fitbit algorithm for AF diagnosis was 98%. The PPV was 97% for individuals aged 65 and older.

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

The algorithm is currently being reviewed for clearance by the U.S. Food and Drug Administration.

The study was funded by Fitbit. Several authors have financial relationships with the company.

SOURCE: https://bit.ly/3kE1RL7 American Heart Association (AHA) Scientific Sessions 2021, presented November 13, 2021.

By Megan Brooks



Posted on 17 November 20217 December 2021