Using Neural Networks to Identify Airway Obstructions in Anesthetized Patients based on Photoplethysmography

Photoplethysmography has been recently studied as a non-invasive indicator of circulatory and respiratory function. In this study, the analysis of this signal and its features is used to identify airway status in patients under the influence of anesthetics. A neural network is utilized with reasonable accuracy to classify segments as being times of `obstructed' vs. `normal' airways status.