Noncontact Detection of Sleep Apnea Using Radar and Expectation-Maximization Algorithm

Sleep apnea syndrome (SAS) requires early diagnosis because this syndrome can lead to a variety of health problems. If sleep apnea (SA) events can be detected in a noncontact manner using radar, we can then avoid the discomfort caused by the contact-type sensors that are used in conventional polysom...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE sensors journal Jg. 24; H. 20; S. 32748 - 32756
Hauptverfasser: Koda, Takato, Okumura, Shigeaki, Taki, Hirofumi, Hamada, Satoshi, Sunadome, Hironobu, Sato, Susumu, Chin, Kazuo, Sakamoto, Takuya
Format: Journal Article
Sprache:Englisch
Veröffentlicht: New York IEEE 15.10.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Accuracy
Adaptive algorithms
Antenna arrays
biomedical engineering
Clutter
Doppler radar
Error analysis
Error detection
Maximization
Optimization
Radar
Radar detection
Radar imaging
Radar measurement
radar measurements
radar signal processing
Sleep apnea
Synthetic aperture sonar
ISSN:1530-437X, 1558-1748
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Sleep apnea syndrome (SAS) requires early diagnosis because this syndrome can lead to a variety of health problems. If sleep apnea (SA) events can be detected in a noncontact manner using radar, we can then avoid the discomfort caused by the contact-type sensors that are used in conventional polysomnography (PSG). This study proposes a novel radar-based method for accurate detection of SA events. The proposed method uses the expectation-maximization (EM) algorithm to extract the respiratory features that form normal and abnormal breathing patterns, resulting in an adaptive apnea detection capability without any requirement for empirical parameters. We conducted an experimental quantitative evaluation of the proposed method by performing PSG and radar measurements simultaneously in five patients with the symptoms of SAS. Through these experiments, we show that the proposed method can detect the number of apnea and hypopnea events per hour with an error of 4.8 times/h; this represents an improvement in the accuracy by 1.8 times when compared with the conventional threshold-based method and demonstrates the effectiveness of our proposed method.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1530-437X
1558-1748
DOI:10.1109/JSEN.2024.3450890