Does a 50-layer convolutional neural network accurately detect Atrial Fibrillation episodes from ambulatory wrist-worn photoplethysmograms?
A 50-layer convolutional neural network can accurately detect atrial fibrillation from ambulatory wrist-worn PPG signals with an AUC of 95%.
We develop an algorithm that accurately detects Atrial Fibrillation (AF) episodes from photoplethysmograms (PPG) recorded in ambulatory free-living conditions. We collect and annotate a dataset containing more than 4000 hours of PPG recorded from a wrist-worn device. Using a 50-layer convolutional neural network, we achieve a test AUC of 95% in presence of motion artifacts inherent to PPG signals. Such continuous and accurate detection of AF has the potential to transform consumer wearable devices into clinically useful medical monitoring tools.
Shen et al. (Thu,) studied this question.