Identification of Respiratory Pauses during Swallowing by Unconstrained Measuring Using Millimeter Wave Radar

• Published in: Sensors (Basel, Switzerland) Vol. 24; no. 12; p. 3748
• Main Authors: Kadono, Toma, Noguchi, Hiroshi
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI AG 09.06.2024; MDPI
• Subjects: Adult; Deglutition - physiology; Dysphagia; Endoscopy; Female; Humans; Machine Learning; Male; Methods; millimeter wave radar; Older people; Pneumonia; Radar; Respiration; respiratory waveform; Sensors; Swallowing; unconstrained measuring; Young Adult; respiratory waveform; millimeter wave radar; swallowing; unconstrained measuring; machine learning
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s24123748

Breathing temporarily pauses during swallowing, and the occurrence of inspiration before and after these pauses may increase the likelihood of aspiration, a serious health problem in older adults. Therefore, the automatic detection of these pauses without constraints is important. We propose methods for measuring respiratory movements during swallowing using millimeter wave radar to detect these pauses. The experiment involved 20 healthy adult participants. The results showed a correlation of 0.71 with the measurement data obtained from a band-type sensor used as a reference, demonstrating the potential to measure chest movements associated with respiration using a non-contact method. Additionally, temporary respiratory pauses caused by swallowing were confirmed by the measured data. Furthermore, using machine learning, the presence of respiring alone was detected with an accuracy of 88.5%, which is higher than that reported in previous studies. Respiring and temporary respiratory pauses caused by swallowing were also detected, with a macro-averaged F1 score of 66.4%. Although there is room for improvement in temporary pause detection, this study demonstrates the potential for measuring respiratory movements during swallowing using millimeter wave radar and a machine learning method.