Video-based Detection of Atrial Fibrillation

The project focuses on the evaluation of a novel, contactless monitoring technology to measure the blood pulsatile signal based on the video recording of an individual's face. The variability of the pulse rate is computed to identify the presence of atrial fibrillation (AF). We propose to enroll 315 patients with symptomatic AF, paroxysmal or persistent, who go through successful radiofrequency ablation or electrical cardioversion. A computer tablet will be used by the subjects at home during 14 days after their procedure to read emails, browse the internet and watch videos. Facial video recordings will be automatically acquired during these daily activities by the tablet device. The subject will be wearing an ECG patch during the follow-up period. The one-lead continuous ECG will be used as a reference to verify the presence of AF rhythm during facial video recordings. The primary aim of the study is to demonstrate the validity and robustness of the video-based technology to detect the presence of AF when facial videos are acquired by the patients at home.