Prediction and simulation of PEEP setting effects with machine learning models

Objective To establish a new machine learning-based method to adjust positive end-expiratory pressure (PEEP) using only already routinely measured data. Design Retrospective observational study. Setting Intensive care unit (ICU). Patients or participants 51811 mechanically ventilated patients in multiple ICUs in the USA (data from MIMIC-III and eICU databases). Interventions No interventions. Main variables of interest Success parameters of ventilation (arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance) Results The multi-tasking neural network model performed significantly best for all target tasks in the primary test set. The model predicts arterial partial pressures of oxygen and carbon dioxide and respiratory system compliance about 45 min into the future with mean absolute percentage errors of about 21.7%, 10.0% and 15.8%, respectively. The proposed use of the model was demonstrated in case scenarios, where we simulated possible effects of PEEP adjustments for individual cases. Conclusions Our study implies that machine learning approach to PEEP titration is a promising new method which comes with no extra cost once the infrastructure is in place. Availability of databases with most recent ICU patient data is crucial for the refinement of prediction performance.