ABSTRACT
Noninvasive ventilation is a clinical procedure that enables patients with chronic respiratory failure to reduce the work of breathing and to improve blood oxygenation. In order to attain such goals, the ventilation support is expected to be phase synchronized with the patient spontaneous breathing. Unfortunately, asynchrony events are not rare. In order to provide more effective ventilation schemes, the patient-ventilator interactions should be better understood both during normal rhythm and asynchronism. This paper investigates this problem using data-driven modeling. Hence the estimation of input-output and autonomous models from pressure and airflow time series is discussed and illustrated. Issues concerning the nonlinearity of the interactions and modeling assumptions are dealt with. The results presented include models obtained from airflow and pressure measurements of a set of patients.