Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep MedicineMar 28, 2024

Using wireless radar and deep learning to measure obstructive sleep apnea severity

GLP-1 Therapies Weekly Brief ↗PubMed ↗DOI ↗

Updated Mar 31, 2026

Abstract

A strong correlation (ρ = 0.91) between the apnea-hypopnea index and the radar-based respiratory disturbance index (RDI) was identified.

The average difference between the apnea-hypopnea index and RDI was 0.59 events per hour.
95.41% of cases (187 out of 196) fell within the 95% confidence interval of differences between the two methods.
A model for moderate-to-severe obstructive sleep apnea (OSA) achieved an accuracy of 90.3% with a cut-off threshold of 19.2 events per hour.
A model for severe OSA reached an accuracy of 92.4% with a cut-off threshold of 28.86 events per hour.
The mean accuracy for multiclass classification performance using these thresholds was 83.7%.

Simplified

STUDY OBJECTIVES: The gold standard for diagnosing obstructive sleep apnea (OSA) is polysomnography (PSG). However, PSG is a time-consuming method with clinical limitations. This study aimed to create a wireless radar framework to screen the likelihood of 2 levels of OSA severity (ie, moderate-to-severe and severe OSA) in accordance with clinical practice standards.

METHODS: We conducted a prospective, simultaneous study using a wireless radar system and PSG in a Northern Taiwan sleep center, involving 196 patients. The wireless radar sleep monitor, incorporating hybrid models such as deep neural decision trees, estimated the respiratory disturbance index relative to the total sleep time established by PSG (RDI), by analyzing continuous-wave signals indicative of breathing patterns. Analyses were performed to examine the correlation and agreement between the RDIand apnea-hypopnea index, results obtained through PSG. Cut-off thresholds for RDIwere determined using Youden's index, and multiclass classification was performed, after which the results were compared. PSG_TST PSG_TST PSG_TST

RESULTS: A strong correlation (ρ = 0.91) and agreement (average difference of 0.59 events/h) between apnea-hypopnea index and RDIwere identified. In terms of the agreement between the 2 devices, the average difference between PSG-based apnea-hypopnea index and radar-based RDIwas 0.59 events/h, and 187 out of 196 cases (95.41%) fell within the 95% confidence interval of differences. A moderate-to-severe OSA model achieved an accuracy of 90.3% (cut-off threshold for RDI: 19.2 events/h). A severe OSA model achieved an accuracy of 92.4% (cut-off threshold for RDI: 28.86 events/h). The mean accuracy of multiclass classification performance using these cut-off thresholds was 83.7%. PSG_TST PSG_TST PSG_TST PSG_TST

CONCLUSIONS: The wireless-radar-based sleep monitoring device, with cut-off thresholds, can provide rapid OSA screening with acceptable accuracy and also alleviate the burden on PSG capacity. However, to independently apply this framework, the function of determining the radar-based total sleep time requires further optimizations and verification in future work.

CITATION: Lin S-Y, Tsai C-Y, Majumdar A, et al. Combining a wireless radar sleep monitoring device with deep machine learning techniques to assess obstructive sleep apnea severity.. 2024;20(8):1267-1277. J Clin Sleep Med

Funding

Competing interests

All authors have seen and approved the manuscript. This study was funded by the Taiwan Ministry of Science and Technology (grant number MOST 110–2634–F-002–049) and the Taiwan National Science and Technology Council (grant number NSTC 111-2634-F-002-021). The funders had no role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The authors report no conflicts of interest.

PubMed

Using wireless radar and deep learning to measure obstructive sleep apnea severity

Abstract

Funding

Competing interests

You found one interesting study. We’ll send the next 7.

What Lands in Your Inbox Each Week:

Recent issues from the glp-1 therapies brief

Abstract

Funding

Competing interests

Related papers

You found one interesting study. We’ll send the next 7.

What Lands in Your Inbox Each Week:

Recent issues from the glp-1 therapies brief