Department of Mathematics, Duke University, Durham, North Carolina, United States of America.
School of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan.
Physiol Meas. 2024 Apr 3;45(3). doi: 10.1088/1361-6579/ad290b.
We aimed to fuse the outputs of different electrocardiogram-derived respiration (EDR) algorithms to create one higher quality EDR signal.We viewed each EDR algorithm as a software sensor that recorded breathing activity from a different vantage point, identified high-quality software sensors based on the respiratory signal quality index, aligned the highest-quality EDRs with a phase synchronization technique based on the graph connection Laplacian, and finally fused those aligned, high-quality EDRs. We refer to the output as the sync-ensembled EDR signal. The proposed algorithm was evaluated on two large-scale databases of whole-night polysomnograms. We evaluated the performance of the proposed algorithm using three respiratory signals recorded from different hardware sensors, and compared it with other existing EDR algorithms. A sensitivity analysis was carried out for a total of five cases: fusion by taking the mean of EDR signals, and the four cases of EDR signal alignment without and with synchronization and without and with signal quality selection.The sync-ensembled EDR algorithm outperforms existing EDR algorithms when evaluated by the synchronized correlation (γ-score), optimal transport (OT) distance, and estimated average respiratory rate score, all with statistical significance. The sensitivity analysis shows that the signal quality selection and EDR signal alignment are both critical for the performance, both with statistical significance.The sync-ensembled EDR provides robust respiratory information from electrocardiogram.Phase synchronization is not only theoretically rigorous but also practical to design a robust EDR.
我们旨在融合不同的心电信号衍生呼吸（EDR）算法的输出，以创建一个更高质量的 EDR 信号。我们将每个 EDR 算法视为一个软件传感器，从不同的角度记录呼吸活动，根据呼吸信号质量指数识别高质量的软件传感器，使用基于图连接拉普拉斯的相位同步技术对齐最高质量的 EDR，并最终融合这些对齐的高质量 EDR。我们将输出称为同步集成 EDR 信号。该算法在两个大规模的全夜多导睡眠图数据库上进行了评估。我们使用来自不同硬件传感器的三个呼吸信号评估了所提出算法的性能，并将其与其他现有的 EDR 算法进行了比较。总共进行了五次敏感性分析：EDR 信号的平均值融合，以及在没有和有同步以及没有和有信号质量选择的情况下的 EDR 信号对齐的四个案例。当通过同步相关系数（γ 评分）、最优传输（OT）距离和估计平均呼吸率评分进行评估时，同步集成 EDR 算法的性能均优于现有的 EDR 算法，均具有统计学意义。敏感性分析表明，信号质量选择和 EDR 信号对齐对于性能都至关重要，均具有统计学意义。同步集成 EDR 从心电图提供了稳健的呼吸信息。相位同步不仅在理论上严谨，而且在设计稳健的 EDR 方面也具有实际意义。
