Wulterkens Bernice M, Fonseca Pedro, Hermans Lieke W A, Ross Marco, Cerny Andreas, Anderer Peter, Long Xi, van Dijk Johannes P, Vandenbussche Nele, Pillen Sigrid, van Gilst Merel M, Overeem Sebastiaan
Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
Philips Research, Eindhoven, the Netherlands.
Nat Sci Sleep. 2021 Jun 28;13:885-897. doi: 10.2147/NSS.S306808. eCollection 2021.
There is great interest in unobtrusive long-term sleep measurements using wearable devices based on reflective photoplethysmography (PPG). Unfortunately, consumer devices are not validated in patient populations and therefore not suitable for clinical use. Several sleep staging algorithms have been developed and validated based on ECG-signals. However, translation from these techniques to data derived by wearable PPG is not trivial, and requires the differences between sensing modalities to be integrated in the algorithm, or having the model trained directly with data obtained with the target sensor. Either way, validation of PPG-based sleep staging algorithms requires a large dataset containing both gold standard measurements and PPG-sensor in the applicable clinical population. Here, we take these important steps towards unobtrusive, long-term sleep monitoring.
We developed and trained an algorithm based on wrist-worn PPG and accelerometry. The method was validated against reference polysomnography in an independent clinical population comprising 244 adults and 48 children (age: 3 to 82 years) with a wide variety of sleep disorders.
The classifier achieved substantial agreement on four-class sleep staging with an average Cohen's kappa of 0.62 and accuracy of 76.4%. For children/adolescents, it achieved even higher agreement with an average kappa of 0.66 and accuracy of 77.9%. Performance was significantly higher in non-REM parasomnias (kappa = 0.69, accuracy = 80.1%) and significantly lower in REM parasomnias (kappa = 0.55, accuracy = 72.3%). A weak correlation was found between age and kappa ( = -0.30, p<0.001) and age and accuracy ( = -0.22, p<0.001).
This study shows the feasibility of automatic wearable sleep staging in patients with a broad variety of sleep disorders and a wide age range. Results demonstrate the potential for ambulatory long-term monitoring of clinical populations, which may improve diagnosis, estimation of severity and follow up in both sleep medicine and research.
人们对使用基于反射式光电容积脉搏波描记法（PPG）的可穿戴设备进行不干扰的长期睡眠测量非常感兴趣。不幸的是，消费级设备尚未在患者群体中得到验证，因此不适合临床使用。已经开发并验证了几种基于心电图信号的睡眠分期算法。然而，将这些技术转换为可穿戴式PPG得出的数据并非易事，需要将传感模式之间的差异整合到算法中，或者直接使用目标传感器获得的数据对模型进行训练。无论哪种方式，基于PPG的睡眠分期算法的验证都需要一个包含适用临床人群的金标准测量值和PPG传感器数据的大型数据集。在此，我们朝着不干扰的长期睡眠监测迈出了这些重要步骤。
我们开发并训练了一种基于腕部佩戴的PPG和加速度计的算法。该方法在一个由244名成年人和48名儿童（年龄：3至82岁）组成的独立临床人群中进行了验证，这些人患有多种睡眠障碍。
该分类器在四类睡眠分期上达成了实质性一致，平均科恩kappa系数为0.62，准确率为76.4%。对于儿童/青少年，一致性更高，平均kappa系数为0.66，准确率为77.9%。在非快速眼动睡眠行为障碍中表现显著更高（kappa = 0.69，准确率 = 80.1%），在快速眼动睡眠行为障碍中表现显著更低（kappa = 0.55，准确率 = 72.3%）。发现年龄与kappa之间存在弱相关性（ = -0.30，p<0.001），年龄与准确率之间也存在弱相关性（ = -0.22，p<0.001）。
本研究表明了在患有多种睡眠障碍且年龄范围广泛的患者中进行自动可穿戴睡眠分期的可行性。结果证明了对临床人群进行动态长期监测的潜力，这可能会改善睡眠医学和研究中的诊断、严重程度评估及随访。
