Philips Research, Eindhoven, The Netherlands.
Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands.
Physiol Meas. 2021 May 11;42(4). doi: 10.1088/1361-6579/abf01f.
. Measurement of respiratory rate and effort is useful in various applications, such as the diagnosis of sleep apnea and early detection of patient deterioration in medical conditions, such as infections. A chest-worn accelerometer may be an easy and non-intrusive method, provided it is accurate and robust. We investigate the use of a novel method that can perform under realistic sleeping conditions such as variable sensor positions and body posture.. Twenty subjects (aged 46-65 years) wore an accelerometer on the chest and a respiratory impedance plethysmography band as a reference. The subjects underwent an experimental protocol lasting approximately 90 min, under various postures and with different sensor positions. We used a novel, constrained, and recursive form of principal component analysis (PCA) to estimate the respiratory effort signal robustly. To obtain an estimate for the respiratory rate, first, multiple estimates were aggregated into a single frequency. Subsequently, a quality index was determined, such that unreliable estimates could be identified, and a trade-off could be made between coverage (percentage of time that the quality index is above a threshold) and limits of agreement.. Results were determined over all recorded data, including changes in sensor position and posture. For respiratory effort, it was found that recursive and constrained computation of PCA reduced the estimation error significantly. For respiratory rate, a relation between coverage and limits of agreement was determined. If a minimum coverage of 80% was required, the limits of agreement could be kept below 1.45 breaths per minute. If the limits of agreement were constrained to 0.2 breaths per minute, a mean coverage of 5% was still attainable.. We have shown that chest-worn accelerometery can be a robust and accurate method for measurement of respiratory features under realistic conditions.
呼吸频率和努力程度的测量在各种应用中都很有用，例如睡眠呼吸暂停的诊断和感染等医疗条件下患者病情恶化的早期检测。佩戴在胸部的加速度计可能是一种简单且非侵入性的方法，只要它准确且稳健。我们研究了一种新方法的使用，该方法可以在现实的睡眠条件下运行，例如传感器位置和身体姿势的变化。
二十名受试者（年龄 46-65 岁）在胸部佩戴加速度计和呼吸阻抗体积描记带作为参考。受试者进行了大约 90 分钟的实验方案，在各种姿势下和不同的传感器位置下进行。我们使用了一种新颖的、受约束的和递归形式的主成分分析（PCA）来稳健地估计呼吸努力信号。为了获得呼吸频率的估计值，首先将多个估计值聚合为单个频率。随后，确定了一个质量指数，以便可以识别不可靠的估计值，并可以在覆盖范围（质量指数高于阈值的时间百分比）和一致性界限之间进行权衡。
结果是根据所有记录的数据确定的，包括传感器位置和姿势的变化。对于呼吸努力，发现递归和约束计算 PCA 大大降低了估计误差。对于呼吸率，确定了覆盖范围和一致性界限之间的关系。如果需要 80%的最小覆盖率，则可以将一致性界限保持在 1.45 次/分钟以下。如果将一致性界限约束在 0.2 次/分钟，则仍可实现 5%的平均覆盖率。
我们已经表明，在现实条件下，佩戴在胸部的加速度计可以成为一种稳健且准确的测量呼吸特征的方法。
