Functional Residual Capacity Predictions through Three Personalized Basis Functions in a Virtual Patient Model for PCV
Trudy Caljé-van der Klei, Qianhui Sun, Cong Zhou, Geoff Chase, Thomas Desaive · IFAC-PapersOnLine · 2024
Current methodology around mechanically ventilating a patient is generalized and determining a patient-specific positive-end-expiratory-pressure (PEEP) is not standardized, causing problems not only around the efficiency of ventilation but the risk mitigation of such. The inclusion of recruitment maneuvers with subsequent PEEP in mechanical ventilation (MV) have proven highly effective in recruiting lung volume and preventing alveolar collapse. These recruitment maneuvers reopen collapsed alveolar by providing a temporary increase in airway pressure. Utilizing patient-specific, personalized monitoring enables more appropriate delivery of ventilation, with a model that will evolve as the patients condition does by continuously modelling the patients lung mechanics and altering ventilation predictions based on their condition. This research analysed pressure controlled ventilation (PCV) using data from the Maastricht trial. This mode of ventilation sets driving pressure to minimise overdistension in the lungs. In this study, functional residual capacity has been analysed using hysteresis loop analysis (HLA) and three separate potential basis functions, Exponential (EXP), Parabolic (PARA) and Cumulative (CUMU). These basis function sets were compared based on their performance in predicting functional residual capacity ( V FRC ). Additional components of lung mechanics have been previously analysed and compared, however this particular research prioritized the accuracy of V FRC predictions. Data provided spanned across 15 patients and 4 different baseline PEEP levels ranging from 6 cmH 2 O through to 12 cmH 2 O. Up to 6 prediction steps were analysed from each baseline PEEP to determine the accuracy across a range of case numbers yielding 293 cases. The results showed that all three basis function sets displayed the highest R 2 values for cumulative prediction steps 1-6. EXP and CUMU sets both yielded a final R 2 of 0.88 and the PARA set had a final R 2 value of 0.87. However, the EXP set showed higher R 2 over each prediction step, yielding it the most efficient as the higher PEEP levels are more clinically relevant for invasive mechanical ventilation (IMV).