Characterisation of pulmonary air leak measurements using a mechanical ventilator in a bench setup.

Prolonged air leakage (AL) following pulmonary resections leads to prolonged hospital stay and post-operative complications. Intra- and postoperative quantification of AL might be useful for improving treatment decisions, but these measurements have not been characterised. AL calculations based on inspiratory and expiratory tidal volumes were investigated in an Intensive Care Unit mechanical ventilator circuit (Servo-I). AL was also measured by a digital chest drainage system. This study shows that AL measurements increase in accuracy when corrected for baseline deviations (R: 0.904 > 0.997, p < 0.001). Bland-Altman analysis revealed a funnel-shape, indicative of a detection threshhold. Corrected measurements were most accurate when averaged over five breaths and AL was >500 mL/min, with an estimated mean systemic bias of 7.4% (95%-limits of agreement [LoA]: 1.1%-13.7%) at 500 mL/min air leak. Breath-by-breath analysis showed most accurate results at AL >20 mL/breath (R: 0.989-0.991, p < 0.001) at tidal volumes between 350-600 mL. The digital drain had a mean systemic bias of -11.1% (95%-LoA: -18.9% to -3.3%) with homogenous scatter in Bland-Altman analysis and a strong correlation to the control measurement over a large range (0-2000mL/min, R: 0.999, p < 0.001). This study indicates that the Servo-I can be used for air leak quantification in clinically relevant ranges (>500 mL/min), but is unsuited for small leak detection due to a detection threshold. Researchers and clinicians should be aware of varying accuracy and interoperability characteristics between AL measurement devices.