Mechanical ventilation system monitoring: Automatic detection of dynamic hyperinflation and asynchrony

Automatic monitoring of mechanical ventilation system becomes more and more important with respect to the number of patients per clinician. In this paper, the automatic detections of dynamic hyperinflation (PEEPi) and asynchrony in a monitoring framework are considered. The proposed detection methods are based on a robust non-parametric hypothesis testing, namely Random Distortion Testing (RDT), that requires no prior information on the signal distribution. The experiment results have shown that the proposed algorithms provide relevant detection of abnormalities during mechanical ventilation.