Comparative Accuracy of Millimeter-Wave Radar and Polysomnography in Sleep Apnea Detection

毫米波雷达与多导睡眠图在睡眠呼吸暂停检测中的准确性比较

阅读:1

Abstract

BACKGROUND Obstructive Sleep Apnea-Hypopnea Syndrome (OSAHS) is a common and serious sleep disorder characterized by recurrent episodes of partial or complete airway obstruction during sleep. Polysomnography is considered the gold standard for diagnosing OSAHS and evaluating its severity. However, traditional sensory monitoring methods, while effective, are often cumbersome, expensive, and unsuitable for home use. The present study introduces a non-sensory millimeter-wave radar sleep monitor, which provides a contactless, portable, and cost-effective alternative for assessing sleep apnea. The goal was to evaluate the consistency of results from the radar-based system with those from polysomnography, in monitoring sleep apnea. MATERIAL AND METHODS Sixty-eight subjects who met the inclusion criteria were recruited from our center. Each subject underwent simultaneous sleep monitoring with both polysomnography and the radar system. The collected data were analyzed using the chi-square test, Kappa coefficient, and sensitivity and specificity calculations. A significance level of P<0.05 was used for all statistical tests. RESULTS The radar-based sleep monitor demonstrated a sensitivity of 92.7%, specificity of 84.6%, and a Kappa coefficient of 0.731 (P<0.01). For moderate-to-severe OSAHS cases, the Kappa value increased to 0.831 (P<0.01), indicating high consistency with polysomnography. CONCLUSIONS The novel sensorless millimeter-wave radar sleep apnea monitoring technology offers several advantages, including non-invasiveness, ease of use, and comfort. It provides a reliable and convenient alternative for OSAHS diagnosis, particularly in resource-limited settings, and can complement traditional sleep studies.

特别声明

1、本页面内容包含部分的内容是基于公开信息的合理引用;引用内容仅为补充信息,不代表本站立场。

2、若认为本页面引用内容涉及侵权,请及时与本站联系,我们将第一时间处理。

3、其他媒体/个人如需使用本页面原创内容,需注明“来源:[生知库]”并获得授权;使用引用内容的,需自行联系原作者获得许可。

4、投稿及合作请联系:info@biocloudy.com。