A-spiro: Towards continuous respiration monitoring

This paper introduces A-spiro, a single-point wearable sensing technique to estimate respiratory flow and volume, in addition to respiratory rate. We show that when coupled with an inertial measurement unit, our system can accurately measure breathing parameters, even when the user is ambulatory. A-spiro can model lung hysteresis to separately predict increasing and decreasing trends of breathing flow. Existing techniques either monitor breathing rate only, or estimate volume and flow when the user is immobile, for example, sleeping. We validate our system for 20 users of different age, weight, height, and ethnicity, and capture breathing data across 6 different activities. For a total of 578 min of data, we show that A-spiro's generalized model for flow has an accuracy of 93% across 6 activities when compared to a spirometer. The estimated minute ventilation has an accuracy of 94.4%, while the estimated respiratory rate has a mean accuracy of 96% across all activities when compared to ground truth. We also compare A-spiro to a state-of-the-art system available commercially.