Respiration pattern recognition by wearable mask device

• Published in: Biosensors & bioelectronics Vol. 169; p. 112590
• Main Authors: Tipparaju, Vishal Varun, Wang, Di, Yu, Jingjing, Chen, Fang, Tsow, Francis, Forzani, Erica, Tao, Nongjian, Xian, Xiaojun
• Format: Journal Article
• Language: English
• Published: England Elsevier B.V 01.12.2020
• Subjects: asthma; Biosensing Techniques; biosensors; blood pressure; body temperature; clinical examination; Heart Rate; lung function; Mask; metabolism; Monitoring, Physiologic; principal component analysis; Principle component analysis; Respiration; Respiration pattern; Respiratory rate; sleep; Steady state; tidal volume; Wearable device; Wearable Electronic Devices; Mask; Respiratory rate; Wearable device; Steady state; Principle component analysis; Respiration pattern
• ISSN: 0956-5663; 1873-4235; 1873-4235
• DOI: 10.1016/j.bios.2020.112590

Compared to heart rate, body temperature and blood pressure, respiratory rate is the vital sign that has been often overlooked, largely due to the lack of easily accessible tool for reliable and natural respiration monitoring. To address this unmet need, we designed and built a wearable, stand-alone, fully integrated mask device for accurate tracking of respiration in free-living conditions. The wearable mask device can provide comprehensive respiration information in a wearable and wireless manner. It can not only accurately measure respiratory rate, tidal volume, respiratory minute volume, and peak flow rate but also recognize unique respiration pattern of the subject via Principle Component Analysis (PCA) algorithms. The reported wearable mask device and respiratory pattern recognition algorithms could be widely used in routine clinical examination, lung function assessment, asthma and chronic obstructive pulmonary disease (COPD) management, metabolic rate measurement, capnography, spirometry, sleep pattern analysis, and biometrics. •A wearable, stand-alone, fully integrated mask device for accurate tracking of respiration in free-living conditions.•Accurate measurement of respiratory rate, tidal volume, respiratory minute volume, and peak flow rate.•Respiration pattern recognition via Principle Component Analysis (PCA) algorithms.•Offering an easily accessible tool for reliable and natural respiration monitoring in routine clinical examination.