Key result
The VidAF facial video screening model achieved an accuracy of more than 90% for atrial fibrillation identification in multiple challenging scenarios.
Why the study?
An estimated 30% of patients with AF are unaware of their condition, creating a need for facial video-based screening models that can overcome real-life motion disturbances.
Does the VidAF model accurately identify atrial fibrillation from facial videos despite motion disturbances?
Population
1200 samples of 100 AF patients and 100 non-AF subjects
Comparison
VidAF facial video model vs non-AF controls
Design
Model development and validation study
Authors
Loading...
Enables motion-robust video AF screening; leaves open prospective validation before clinical use.
Does the VidAF model accurately identify atrial fibrillation from facial videos despite motion disturbances?
The VidAF model provides a motion-robust, non-contact approach for opportunistic atrial fibrillation screening using facial videos with over 90% accuracy.
Liu et al. (2021) studied Atrial fibrillation (n=200). VidAF (facial video screening model) vs. Non-AF subjects was evaluated on Atrial fibrillation identification accuracy. The VidAF facial video screening model achieved an accuracy of more than 90% for atrial fibrillation identification in multiple challenging scenarios.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: