Pulse Harmonic Strength of facial video signal for the detection of atrial fibrillation

摘要: It is estimated that 3.2 million people have developed atrial fibrillation (AF) in the United States and 30% of AF patients are unaware their diagnosis (silent AF). We tested a new technology for contactless detection based on facial video recordings undergoing electrical cardioversion AF. The proposed technique uses signal to extract beat-to-beat variations skin color reflecting cardiac pulsatile signal. concept Pulse Harmonic Strength (PHS) capture patterns from this Also, we quantified variability heart rate pulse using additional measurements variability. Eleven subjects (65±6 years, 8 males) were enrolled study 407 epochs 15 sec. acquired simultaneously with ECG signals. PHS was associated 20% error reference human interpretation while rates automatic ECG-based ranged between 17% 29% across investigated HRV parameters.