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 ([Formula: see text]) 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 [Formula: see text] signals always get contaminated with that of the oscillatory-pressure-signal of the heart, which is known as the cardiogenic oscillation ([Formula: see text]) signal. However, the area of research addressing the removal of [Formula: see text] from [Formula: see text] 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 [Formula: see text] from [Formula: see text] signal utilizing the inherent periodicity and morphological property of the [Formula: see text] signal. The performance of the proposed technique is tested on [Formula: see text] signals collected from the patients admitted to the intensive care unit, cadavers, and also on synthetic [Formula: see text] signals. The efficiency of the proposed technique in removing [Formula: see text] from the [Formula: see text] signal is quantified through both qualitative and quantitative measures, and the mean opinion scores of the denoised [Formula: see text] 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.
Keywords: Cardiogenic oscillation; data-driven technique; esophageal pressure signal; mean opinion score; mechanical ventilation; singular spectrum analysis.