Accuracy of Detecting Atrial Fibrillation: A Systematic Review and Meta-Analysis of Wrist-Worn Wearable Technology

Abstract

Atrial fibrillation (AF) is the most commonly diagnosed arrhythmia, and ECG remains the gold standard for diagnosing AF. Wrist-worn technologies are appealing for their ability to passively process near-continuous pulse signals. The clinical application of wearable devices is controversial. Our systematic review and metaanalysis qualitatively and quantitatively analyze available literature on wrist-worn wearable devices (Apple Watch, Samsung, and KardiaBand) and their sensitivity and specificity in detecting AF compared to conventional methods. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed, yielding nine studies (n = 1,581). Observational studies assessing the sensitivity and specificity of wrist-worn wearables in detecting AF in patients with and without a history of AF were included and analyzed using a fixed-effect model with an inverse-variance method. In patients with a history of AF, the overall sensitivity between device groups did not significantly differ (96.83%; P = 0.207). Specificity significantly differed between Apple, Samsung, and KardiaBand (99.61%, 81.13%, and 97.98%, respectively; P<0.001). The effect size for this analysis was highest in the Samsung device group. Two studies (n = 796) differentiated cohorts to assess device sensitivity in patients with known AF and device specificity in patients with normal sinus rhythm (NSR) (sensitivity: 96.02%; confidence intervals (CI) 93.85%-97.59% and specificity: 98.82%; CI:97.46%-99.57%). Wrist-worn wearable devices demonstrate promising results in detecting AF in patients with paroxysmal AF. However, more rigorous prospective data is needed to understand the limitations of these devices in regard to varying specificities which may lead to unintended downstream medical testing and costs.

Treating the double chin with hyaluronic acid injection

“…These range from common or immediate (e.g., bruising, edema, lumping, displacement), to uncommon or delayed (e.g., wound infection). [22][23][24] Vascular occlusion and their sequelae are among the most serious events, with the most devastating being vision loss, in which prompt management can improve outcomes. 25 Fortunately, complications remain rare, and are mostly associated with injection to the mid-or upper-face (including the nose, nasolabial fold, eyebrows, forehead, and glabella), 23 with the nasolabial fold being especially high-risk.…”

“…On the other hand, HA fillers are usually associated with fewer adverse events and minimal to mild swelling, which usually subside within 1–7 days. These range from common or immediate (e.g., bruising, edema, lumping, displacement), to uncommon or delayed (e.g., wound infection) 22–24 . Vascular occlusion and their sequelae are among the most serious events, with the most devastating being vision loss, in which prompt management can improve outcomes 25 .…”

“…25 Fortunately, complications remain rare, and are mostly associated with injection to the mid-or upper-face (including the nose, nasolabial fold, eyebrows, forehead, and glabella), 23 with the nasolabial fold being especially high-risk. 24 Contraindications of HA include the presence of infection or cutaneous disorders near the injection site, and hypersensitivity to the filler material or to lidocaine (which is frequently mixed with the filler). 26 In terms of cost, filler injections compare favorably to ATX-101 and other noninvasive procedures such as cryolipolysis or F I G U R E 1 A 52-year-old East-Asian woman with SMF (submental fullness).…”

Innovations in family medicine and the implication to rural and remote primary care

“…New wereable devices can detect rhythm abnormalities, and their accuracy had been evaluated in a systematic review. 10 Nine observational studies (n = 1581) assessing the sensitivity and specificity of wrist-worn wearables in detecting AF in patients with and without a history of AF were included. In patients with a history of AF, the overall sensitivity was high.…”

Early Warning of Atrial Fibrillation Using Deep Learning

“…The automated detection of AF regimes from recorded time-series data is a well-studied problem in the literature [9][10][11] . Recent approaches based on machine learning and neural networks have achieved over 99% accuracy in the classification task [12][13][14][15][16][17] , leading to functional applications on wearable devices of Apple, Fitbit, Samsung, and others [18][19][20][21][22] . Nonetheless, prediction of the onset of AF is still an open problem 23 .…”