Key result
Verily Study Watch algorithm detects AF with ~96% sensitivity and high specificity vs patch ECG.
Why the study?
Existing consumer wrist-worn devices perform only periodic checks when stationary and lack clearance for clinical decision-making, leaving an unmet need for medical-grade devices providing continuous AF monitoring.
Does a wrist-worn device with continuous photoplethysmography and a deep learning algorithm accurately detect atrial fibrillation and estimate AF burden compared to a 14-day continuous ECG monitor in patients with paroxysmal AF?
Observational (n=111)
Yes
Does a wrist-worn device with continuous photoplethysmography and a deep learning algorithm accurately detect atrial fibrillation and estimate AF burden compared to a 14-day continuous ECG monitor in patients with paroxysmal AF?
A wrist-worn device using continuous photoplethysmography and a deep learning algorithm demonstrated high sensitivity and specificity for detecting atrial fibrillation and accurately estimated AF burden compared to a 14-day continuous ECG monitor.
Answers are grounded in this paper and cite their sources.
May support wearable PPG monitoring in paroxysmal AF; extends validation data yet leaves open outcome impact in practice.
Background Wearable devices may be useful for identification, quantification and characterization, and management of atrial fibrillation (AF). To date, consumer wrist‐worn devices for AF detection using photoplethysmography‐based algorithms perform only periodic checks when the user is stationary and are US Food and Drug Administration cleared for prediagnostic uses without intended use for clinical decision‐making. There is an unmet need for medical‐grade diagnostic wrist‐worn devices that provide long‐term, continuous AF monitoring. Methods and Results We evaluated the performance of a wrist‐worn device with lead‐I ECG and continuous photoplethysmography (Verily Study Watch) and photoplethysmography‐based convolutional neural network for AF detection and burden estimation in a prospective multicenter study that enrolled 117 patients with paroxysmal AF. A 14‐day continuous ECG monitor (Zio XT) served as the reference device to evaluate algorithm sensitivity and specificity for detection of AF in 15‐minute intervals. A total of 91 857 intervals were contributed by 111 subjects with evaluable reference and test data (18.3 h/d median watch wear time). The watch was 96.1% sensitive (95% CI, 92.7%–98.0%) and 98.1% specific (95% CI, 97.2%–99.1%) for interval‐level AF detection. Photoplethysmography‐derived AF burden estimation was highly correlated with the reference device burden ( R 2 =0.986) with a mean difference of 0.8% (95% limits of agreement, −6.6% to 8.2%). Conclusions Continuous monitoring using a photoplethysmography‐based convolutional neural network incorporated in a wrist‐worn device has clinical‐grade performance for AF detection and burden estimation. These findings suggest that monitoring can be performed with wrist‐worn wearables for diagnosis and clinical management of AF. Registration Information URL: https://www.clinicaltrials.gov ; Unique identifier: NCT04546763.
No takes yet. Share an insight, caveat, or question.
Poh et al. (2023) conducted an observational in Paroxysmal atrial fibrillation (n=111). Verily Study Watch with PPG-based convolutional neural network algorithm vs. 14-day continuous reference patch ECG monitor (Zio XT) was evaluated on Sensitivity and specificity for detection of atrial fibrillation in 15-minute intervals (Sensitivity 96.1%, Specificity 98.1%, 95% CI 92.7%-98.0%). The Verily Study Watch PPG algorithm achieved 96.1% sensitivity and 98.1% specificity for 15-minute interval AF detection against reference patch ECG.
Synapse has enriched 10 related papers. Consider them for comparative context: