• Heart Failure
  • Cardiovascular Clinical Consult
  • Adult Immunization
  • Hepatic Disease
  • Rare Disorders
  • Pediatric Immunization
  • Implementing The Topcon Ocular Telehealth Platform
  • Weight Management
  • Monkeypox
  • Guidelines
  • Men's Health
  • Psychiatry
  • Allergy
  • Nutrition
  • Women's Health
  • Cardiology
  • Substance Use
  • Pediatrics
  • Kidney Disease
  • Genetics
  • Complimentary & Alternative Medicine
  • Dermatology
  • Endocrinology
  • Oral Medicine
  • Otorhinolaryngologic Diseases
  • Pain
  • Gastrointestinal Disorders
  • Geriatrics
  • Infection
  • Musculoskeletal Disorders
  • Obesity
  • Rheumatology
  • Technology
  • Cancer
  • Nephrology
  • Anemia
  • Neurology
  • Pulmonology

AHA 2021: Novel Fitbit Algorithm Correctly Detected Undiagnosed Atrial Fibrillation


AHA 2021: Novel software algorithm used in Fitbit wearable devices accurately detected undiagnosed atrial fibrillation about 98% of the time, showed results of the Fitbit Heart Study.

©a2 studio/stock.adobe.com

©a2 studio/stock.adobe.com

A novel software algorithm used in Fitbit® wearable devices accurately identified undiagnosed atrial fibrillation (AF) approximately 98% of the time, according to results of the Fitbit Heart Study presented at the American Heart Association (AHA) Scientific Sessions 2021, held virtually from November 13-15, 2021.

Many digital fitness trackers and smartwatches passively detect irregular heart rhythms using pulse photoplethysmography (PPG) technology, which may help to identify persons with undiagnosed AF.

“Undiagnosed atrial fibrillation can lead to strokes, and early detection of atrial fibrillation may allow doctors to prescribe medications that are effective at preventing strokes,” said lead author Steven A. Lubitz, MD, MPH, associate professor of medicine, Harvard Medical School, cardiologist, Massachusetts General Hospital, Boston, in an AHA press release.

Lubitz and colleagues, along with fitness wearable manufacturer Fitbit® conducted a prospective single-arm remote clinical trial examining the validity of a novel PPG-based Fitbit algorithm for detecting AF.

The algorithm examined overlapping 5-minute pulse tachograms when the user was inactive and triggered a detection when 11 consecutive tachograms were irregular. The algorithm required approximately 30 minutes of sensing irregular heart rhythms to indicate the presence of possible AF.

"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."
-Steven A. Lubitz, MD, MPH

Investigators enrolled 455 699 US adults aged at least 22 years (median age, 47 years; 71% women; 73% White) with a compatible Fitbit fitness tracker or smartwatch and without a prior diagnosis of AF between May and October 2020. Participants were recruited via email, Fitbit app notifications, social media, and other marketing channels, and consented via mobile or web-based application. The data from their devices were analyzed with the novel algorithm.

Participants with an irregular heart rhythm detection (IHRD) were notified and invited to schedule a visit with a telehealth provider. After the telehealth visit, participants received a 1-week electrocardiogram (ECG) patch monitor to wear along with their Fitbit.

The primary endpoint was the positive predictive value (PPV) of the first IHRD during ECG monitoring, defined as the fraction of subjects with an IHRD with ≥30 seconds of concurrent AF confirmed on the ECG. The secondary endpoint was the proportion of 5-minute pulse tachograms within the first IHRD during the ECG that corresponded with ≥30 seconds of AF confirmed on the ECG.

IHRDs occurred in 4728 (1%) participants overall and 2070 (4%) of those aged ≥65 years, according to the study abstract. There were 1057 participants with an IHRD notification and subsequent analyzable ECG patch monitor data, among whom AF was present on the ECG patch monitor in 340 (32.2%).

An IHRD occurred during ECG monitoring in 225 participants, of whom 221 had concurrent AF on the ECG patch monitor, resulting in an IHRD PPV of 98.2% (95% confidence interval [CI], 95.5%-99.5%). For adults aged ≥65 years, the IHRD PPV was 97% (95% CI, 91.4%-99.4%).

During the first IHRD during ECG monitoring, 98.1% (95% CI, 96.4%-99.9%) of the 5-minute pulse tachograms corresponded to AF on the ECG, according to researchers.

“These results show that wearables have the ability to identify undiagnosed atrial fibrillation with high reliability,” said Lubitz. “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.”

“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,” added Lubitz.

The Fitbit algorithm is currently being reviewed by the US Food and Drug Administration for clearance and widespread use. The Fitbit Heart Study did not test whether screening for AF can lead to a decrease in strokes, which Lubitz noted warrants future research.

Reference: Lubitz SA, Faranesh T, Selvaggi C, et al. Detection of atrial fibrillation in a large population using wearable devices: The Fitbit Heart Study. Presented at the American Heart Association Scientific Sessions 2021.

Related Videos
© 2024 MJH Life Sciences

All rights reserved.