A30-09 Simultaneous Estimation of Sleep Duration and Sleep Apnea Hyponpnea Using Millimeter Wave Radar

Abstract Rationale Comorbid insomnia and sleep apnea (COMISA) is associated with poor health outcomes, and the condition remains underdiagnosed, partly because of the limitations of contact-based monitoring methods such as polysomnography (PSG) and wearable devices. Millimeter-wave radar (MWR) might represent a non-contact alternative for the simultaneous assessment of sleep-disordered breathing and sleep duration. Objective To assess the accuracy of MWR in estimating the respiratory event index (REI) and sleep duration and identify the optimal post-movement exclusion windows for each metric to enhance concordance with PSG-derived standards. Methods Sixty-two adults underwent overnight PSG alongside MWR recording. REI and the estimated sleep duration (ESD) were calculated by excluding data within 1, 2, or 3 min following large body movements. Agreements between REI and PSG-derived AHI and between ESD and PSG-derived total sleep time (TST) were evaluated using Bland-Altman analysis. Results The 3-min exclusion window yielded the smallest bias and narrowest limits of agreement for REI mean bias = +0.1 events/h; 95% confidence interval (CI) = −8.2 to 8.4, closely matching PSG-derived AHI (18.9 ± 16.9 events/h vs. 19.0 ± 14.4 events/h). Conversely, the 1-min exclusion window provided the best agreement for sleep duration (mean bias = −26 min; 95% CI = -72 to 20), aligning with PSG-derived TST (422 ± 80 min vs. 396 ± 71 min). These findings support metric-specific optimization, namely a 3-min exclusion window for REI and a 1-min window for ESD (Figure 1). Bland-Altman analysis further confirmed that tailored exclusion windows enhanced concordance with PSG metrics. Conclusions MWR enables the simultaneous, non-contact estimation of sleep-disordered breathing and the objective sleep duration with clinically acceptable concordance with PSG. This radar-based approach could facilitate low-burden screening and management of COMISA, positioning MWR as a viable alternative to wearable devices for COMISA screening and management in both clinical and home environments. This abstract is funded by: a project, JPNP23019, subsidized by the New Energy and Industrial Technology Development Organization (NEDO), KYOTO Industrial Support Organization 21