Finnsson Eysteinn, Erlingsson Ernir, Hlynsson Hlynur D, Valsdóttir Vaka, Sigmarsdottir Thora B, Arnardóttir Eydís, Sands Scott A, Jónsson Sigurður Æ, Islind Anna S, Ágústsson Jón S
Nox Research, Nox Medical, Katrínartún 2, 105, Reykjavík, Iceland.
Department of Computer Science, Reykjavik University, Reykjavik, Iceland.
Sleep Breath. 2025 Apr 11;29(2):155. doi: 10.1007/s11325-025-03325-z.
Accurately identifying sleep states (REM, NREM, and Wake) and brief awakenings (arousals) is essential for diagnosing sleep disorders. Polysomnography (PSG) is the gold standard for such assessments but is costly and requires overnight monitoring in a lab. Home sleep testing (HST) offers a more accessible alternative, relying primarily on breathing measurements but lacks electroencephalography, limiting its ability to evaluate sleep and arousals directly. This study evaluates a deep learning algorithm which determines sleep states and arousals from breathing signals.
A novel deep learning algorithm was developed to classify sleep states and detect arousals from respiratory inductance plethysmography signals. Sleep states were predicted for 30-s intervals (one sleep epoch), while arousal probabilities were calculated at 1-s resolution. Validation was conducted on a clinical dataset of 1,299 adults with suspected sleep disorders. Performance was assessed at the epoch level for sensitivity and specificity, with agreement analyses for arousal index (ArI) and total sleep time (TST).
The algorithm achieved sensitivity and specificity of 77.9% and 96.2% for Wake, 93.9% and 80.4% for NREM, 80.5% and 98.2% for REM, and 66.1% and 86.7% for arousals. Bland-Altman analysis showed ArI limits of agreement ranging from - 32 to 24 events/hour (bias: - 4.4) and TST limits from - 47 to 64 min (bias: 8.0). Intraclass correlation was 0.74 for ArI and 0.91 for TST.
The algorithm identifies sleep states and arousals from breathing signals with agreement comparable to established variability in manual scoring. These results highlight its potential to advance HST capabilities, enabling more accessible, cost-effective and reliable sleep diagnostics.
准确识别睡眠状态（快速眼动睡眠、非快速眼动睡眠和清醒）以及短暂觉醒（微觉醒）对于诊断睡眠障碍至关重要。多导睡眠图（PSG）是此类评估的金标准，但成本高昂且需要在实验室进行过夜监测。家庭睡眠测试（HST）提供了一种更便捷的替代方法，主要依靠呼吸测量，但缺乏脑电图，限制了其直接评估睡眠和微觉醒的能力。本研究评估了一种深度学习算法，该算法可根据呼吸信号确定睡眠状态和微觉醒。
开发了一种新型深度学习算法，用于对睡眠状态进行分类并从呼吸感应体积描记术信号中检测微觉醒。以30秒间隔（一个睡眠时段）预测睡眠状态，同时以1秒分辨率计算微觉醒概率。在一个包含1299名疑似睡眠障碍成年人的临床数据集上进行验证。在时段水平上评估敏感性和特异性，并对微觉醒指数（ArI）和总睡眠时间（TST）进行一致性分析。
该算法对于清醒状态的敏感性和特异性分别为77.9%和96.2%，对于非快速眼动睡眠为93.9%和80.4%，对于快速眼动睡眠为80.5%和98.2%，对于微觉醒为66.1%和86.7%。布兰德 - 奥特曼分析显示，ArI的一致性界限为每小时 - 32至24次事件（偏差： - 4.4），TST的一致性界限为 - 47至64分钟（偏差：8.0）。ArI的组内相关性为0.74，TST的组内相关性为0.91。
该算法可从呼吸信号中识别睡眠状态和微觉醒，其一致性与传统手动评分的可变性相当。这些结果凸显了其提升HST能力的潜力，使睡眠诊断更便捷、经济高效且可靠。
