Background: For mechanically ventilated patients with acute respiratory distress\nsyndrome (ARDS), suboptimal PEEP levels can cause ventilator induced lung injury\n(VILI). In particular, high PEEP and high peak inspiratory pressures (PIP) can cause over\ndistension of alveoli that is associated with VILI. However, PEEP must also be sufficient\nto maintain recruitment in ARDS lungs. A lung model that accurately and precisely predicts\nthe outcome of an increase in PEEP may allow dangerous high PIP to be avoided,\nand reduce the incidence of VILI.\nMethods and results: Sixteen pressure-flow data sets were collected from nine\nmechanically ventilated ARDs patients that underwent one or more recruitment\nmanoeuvres. A nonlinear autoregressive (NARX) model was identified on one or\nmore adjacent PEEP steps, and extrapolated to predict PIP at 2, 4, and 6 cmH2O PEEP\nhorizons. The analysis considered whether the predicted and measured PIP exceeded\na threshold of 40 cmH2O. A direct comparison of the method was made using the first\norder model of pulmonary mechanics (FOM(I)). Additionally, a further, more clinically\nappropriate method for the FOM was tested, in which the FOM was trained on a single\nPEEP prior to prediction (FOM(II)). The NARX model exhibited very high sensitivity\n(> 0.96) in all cases, and a high specificity (> 0.88). While both FOM methods had a high\nspecificity (> 0.96), the sensitivity was much lower, with a mean of 0.68 for FOM(I), and\n0.82 for FOM(II).\nConclusions: Clinically, false negatives are more harmful than false positives, as a high\nPIP may result in distension and VILI. Thus, the NARX model may be more effective\nthan the FOM in allowing clinicians to reduce the risk of applying a PEEP that results in\ndangerously high airway pressures.
Loading....