Objective: Assessing the respiratory and lung mechanics of the patients in intensive care units is of utmost need in order to guide the management of ventilation support. The esophageal pressure ( $\boldsymbol {P}_{ \boldsymbol {eso}}$ ) signal is a minimally invasive measure, which portrays the mechanics of the lung and the pattern of breathing. Because of the close proximity of the lung to the beating heart inside the thoracic cavity, the $\boldsymbol {P}_{ \boldsymbol {eso}}$ signals always get contaminated with that of the oscillatory-pressure-signal of the heart, which is known as the cardiogenic oscillation ( $\boldsymbol {CGO}$ ) signal. However, the area of research addressing the removal of $\boldsymbol {CGO}$ from $\boldsymbol {P}_{ \boldsymbol {eso}}$ signal is still lagging behind. Methods and results: This paper presents a singular spectrum analysis-based high-efficient, adaptive and robust technique for the removal of $\boldsymbol {CGO}$ from $\boldsymbol {P}_{ \boldsymbol {eso}}$ signal utilizing the inherent periodicity and morphological property of the $\boldsymbol {P}_{ \boldsymbol {eso}}$ signal. The performance of the proposed technique is tested on $\boldsymbol {P}_{ \boldsymbol {eso}}$ signals collected from the patients admitted to the intensive care unit, cadavers, and also on synthetic $\boldsymbol {P}_{ \boldsymbol {eso}}$ signals. The efficiency of the proposed technique in removing $\boldsymbol {CGO}$ from the $\boldsymbol {P}_{ \boldsymbol {eso}}$ signal is quantified through both qualitative and quantitative measures, and the mean opinion scores of the denoised $\boldsymbol {P}_{ \boldsymbol {eso}}$ signal fall under the categories ‘very good’ as per the subjective measure. Conclusion and clinical impact: The proposed technique: (1) does not follow any predefined mathematical model and hence, it is data-driven, (2) is adaptive to the sampling rate, and (3) can be adapted for denoising other biomedical signals which exhibit periodic or quasi-periodic nature.

中文翻译：

---

一种基于奇异谱分析的数据驱动技术，用于去除食道压力信号中的心源性振荡

客观的：评估重症监护病房患者的呼吸和肺力学是最需要的，以指导通气支持的管理。食管压力（ $\boldsymbol {P}_{ \boldsymbol {eso}}$ ) 信号是一种微创措施，它描绘了肺的力学和呼吸模式。由于肺靠近胸腔内跳动的心脏， $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号总是被心脏的振荡压力信号污染，这被称为心源性振荡（ $\boldsymbol {CGO}$ ） 信号。然而，研究领域解决了去除 $\boldsymbol {CGO}$ 从 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号仍然滞后。 方法和结果： 本文提出了一种基于奇异谱分析的高效、自适应和鲁棒的技术，用于去除 $\boldsymbol {CGO}$ 从 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号利用固有的周期性和形态特性 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号。所提出技术的性能在 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 从入住重症监护室的患者、尸体以及合成材料上收集的信号 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号。所提出的技术在去除 $\boldsymbol {CGO}$ 来自 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 信号通过定性和定量测量进行量化，并且去噪后的平均意见得分 $\boldsymbol {P}_{ \boldsymbol {eso}}$ 根据主观测量，信号属于“非常好”类别。 结论和临床影响： 所提出的技术：(1) 不遵循任何预定义的数学模型，因此，它是数据驱动的，(2) 适应采样率，以及 (3) 可适用于对表现出周期性或准的其他生物医学信号进行去噪- 周期性。