Key result
Contactless facial video using deep learning achieves ~97% accuracy in detecting AF.
Why the study?
AF is often asymptomatic and paroxysmal, creating a need for screening and monitoring especially in high-risk individuals.
Does contactless facial video recording with a deep learning model accurately detect atrial fibrillation compared to 12-lead ECG in adult patients?
Cross-Sectional (n=453)
Single-blind
No
Does contactless facial video recording with a deep learning model accurately detect atrial fibrillation compared to 12-lead ECG in adult patients?
Contactless facial video recording using rPPG and deep learning can accurately detect atrial fibrillation, offering a potential non-invasive tool for large-scale screening.
No takes yet. Share an insight, caveat, or question.
Supports contactless AF screening research; hypothesis-generating and requires prospective validation before clinical adoption.
Sun et al. (2022) conducted a cross-sectional in Atrial fibrillation (n=453). Contactless facial video recording (rPPG) with deep learning models vs. 12-lead ECG was evaluated on Accuracy rate for discriminating AF from non-AF in 10-minute recording. Contactless facial video recording using remote photoplethysmography and deep learning models achieved 97.1% accuracy in discriminating atrial fibrillation from non-atrial fibrillation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: