Extraction of Weak Surface Diaphragmatic Electromyogram Using Modified Progressive FastICA Peel-Off

Diaphragmatic electromyogram (EMGdi) is a crucial electrophysiological signal that contains information about human respiration. Although it is practical to record surface EMGdi (sEMGdi) noninvasively and conveniently by placing electrodes over chest skin, extraction of such weak sEMGdi from noise condition is a challenging task, limiting its clinical use compared with esophageal EMGdi. In this paper, a novel method is presented for extracting weak sEMGdi signal from high-noise condition based on fast independent component analysis (FastICA), constrained FastICA and a peel-off strategy. The constrained FastICA helps to extract and refine respiration-related sEMGdi signals, and the peel-off strategy ensures the complete extraction of weaker sEMGdi components. The method was validated using both synthetic signals and clinical signals. It was demonstrated that our method was able to extract sEMGdi signals efficiently with little distortion. It outperformed state-of-the-art comparison methods in terms of sufficiently high SIR and CORR at all noise levels when tested on synthetic data. Our method also achieved an accuracy of 95.06% and a F2-score of 96.73% for breath identification on clinical data. The study presents a valuable solution for noninvasive extraction of sEMGdi signals, providing a convenient and valuable way of ventilator synchrony. Our study also offers a significant potential in aiding respiratory rehabilitation and health.