Key result
The Amazfit Health Band 1S detected atrial fibrillation with 88.00% sensitivity and 96.41% specificity using PPG, and 87.33% sensitivity and 99.20% specificity using its ECG algorithm.
Why the study?
Detection of atrial fibrillation occurrence over a long duration has been a challenge in screening and follow-up, and wearable devices may offer a solution.
Does a smart wristband equipped with PPG, single-channel ECG, and an AI algorithm accurately detect atrial fibrillation in normal individuals and AF patients?
Cross-Sectional (n=401)
Does a smart wristband equipped with PPG, single-channel ECG, and an AI algorithm accurately detect atrial fibrillation in normal individuals and AF patients?
A smart wristband using PPG, single-channel ECG, and an AI algorithm demonstrated high sensitivity and specificity for detecting atrial fibrillation, suggesting potential utility for AF screening.
Answers are grounded in this paper and cite their sources.
Supports exploration of wristband PPG for AF detection; retrospective data leaves open need for prospective validation.
BackgroundDetection of atrial fibrillation (AF) occurrence over a long duration has been a challenge in the screening and follow-up of AF patients. Wearable devices may be an ideal solution.ObjectiveThe purpose of this study was to measure the sensitivity, specificity, and accuracy of a recently developed smart wristband device that is equipped with both photoplethysmographic (PPG) and single-channel electrocardiogram (ECG) systems and an AF-identifying, artificial intelligence (AI) algorithm, used in the short term.MethodsUse of the Amazfit Health Band 1S, which records both PPG and single-channel ECG data, was assessed in 401 patients (251 normal individuals and 150 ECG-diagnosed AF patients).ResultsECG and PPG readings could not be judged in 15 and 18 subjects, respectively. Subjects who were unable to be judged were defined as either false negative or false positive. The sensitivity, specificity, and accuracy of wristband PPG readings were 88.00%, 96.41%, and 93.27%, respectively, and those of wristband ECG readings were 87.33%, 99.20%, and 94.76%, respectively. When the original wristband ECG records were judged by physicians, the sensitivity, specificity, and accuracy were 96.67%, 98.01%, and 97.51%, respectively.ConclusionThis promising new combination of PPG, ECG, and AI algorithm has the potential to facilitate AF detection. Detection of atrial fibrillation (AF) occurrence over a long duration has been a challenge in the screening and follow-up of AF patients. Wearable devices may be an ideal solution. The purpose of this study was to measure the sensitivity, specificity, and accuracy of a recently developed smart wristband device that is equipped with both photoplethysmographic (PPG) and single-channel electrocardiogram (ECG) systems and an AF-identifying, artificial intelligence (AI) algorithm, used in the short term. Use of the Amazfit Health Band 1S, which records both PPG and single-channel ECG data, was assessed in 401 patients (251 normal individuals and 150 ECG-diagnosed AF patients). ECG and PPG readings could not be judged in 15 and 18 subjects, respectively. Subjects who were unable to be judged were defined as either false negative or false positive. The sensitivity, specificity, and accuracy of wristband PPG readings were 88.00%, 96.41%, and 93.27%, respectively, and those of wristband ECG readings were 87.33%, 99.20%, and 94.76%, respectively. When the original wristband ECG records were judged by physicians, the sensitivity, specificity, and accuracy were 96.67%, 98.01%, and 97.51%, respectively. This promising new combination of PPG, ECG, and AI algorithm has the potential to facilitate AF detection.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2020) conducted a cross-sectional in Atrial fibrillation (n=401). Amazfit Health Band 1S (PPG, single-channel ECG, and AI algorithm) vs. ECG-diagnosed AF (reference standard) was evaluated on Sensitivity, specificity, and accuracy for AF detection. The Amazfit Health Band 1S detected atrial fibrillation with 88.00% sensitivity and 96.41% specificity using PPG, and 87.33% sensitivity and 99.20% specificity using its ECG algorithm.
Synapse has enriched 10 related papers. Consider them for comparative context: