Key result
A deep neural network approach using wrist-worn photoplethysmography and accelerometry detected atrial fibrillation with a pooled AUC of 0.95 and an accuracy of 91.8%.
Why the study?
Does a deep learning approach using wrist-worn PPG signals accurately detect atrial fibrillation?
Observational (n=98)
Does a deep learning approach using wrist-worn PPG signals accurately detect atrial fibrillation?
Effect estimate: AUC 0.95
A novel deep learning algorithm using wrist-worn PPG signals and accelerometry can accurately detect atrial fibrillation with an AUC of 0.95.
Authors
No takes yet. Share an insight, caveat, or question.
Supports wearable AF screening in ambulatory care; extends deep learning validation from ECG to wrist PPG in RCT data.
Shashikumar et al. (2017) conducted an observational in Atrial Fibrillation (n=98). Deep neural network approach using wrist-worn PPG and accelerometry vs. Single channel ECG was evaluated on Detection of atrial fibrillation (AUC 0.95). A deep neural network approach using wrist-worn photoplethysmography and accelerometry detected atrial fibrillation with a pooled AUC of 0.95 and an accuracy of 91.8%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: