Inferring Respiratory Minute Volume from Wrist Motion

Exposure to air pollutants poses major health risk for patients with chronic pulmonary diseases such as asthma, bronchitis, and emphysema. Such risk can be mitigated by continuous exposure tracking. The effective dose of exposure is directly proportional to the respiratory minute volume, aka minute ventilation (VE). Till date, the clinical standard for measuring VE is Spirometry, a highly invasive and cumbersome modality, which is not suitable for continuous day-to-day use. This paper presents a novel non-invasive method toward continuous assessment of VE using a wrist-mount wearable motion sensor. Data from 25 healthy subjects were collected while they performed ambulatory and sedentary activities and physical exercises. Noise and artifacts of the motion signal are removed and the processed signal is used to extract explanatory features. The features are used to train and evaluate multiple regression models, among which, the probabilistic Gaussian process regression achieves the best performance in inferring VE from the wearable motion signal. The effects of inter- and intra-personal variations are explored to demonstrate the potential of the proposed method for continuously monitoring pollutant exposure risk in respiratory health applications.