Ventilator-induced lung injury is associated with increased morbidity and mortality. Despite intense efforts in basic and clinical research, an individualized ventilation strategy for critically ill patients remains a major challenge. However, an individualized mechanical ventilation approach remains a challenging task: A multitude of factors, e.g., lab values, vitals, comorbidities, disease progression, and other clinical data must be taken into consideration when choosing a patient's specific optimal ventilation regime. The aim of this work was to evaluate the machine learning ventilator decision system, which is able to suggest a dynamically optimized mechanical ventilation regime for critically-ill patients. Compare with standard controlled ventilation, to test whether the clinical application of the machine learning ventilator decision system reduces mechanical ventilation time and mortality.

Inclusion Criteria:

1. only the first ICU stay was eligible;
2. adults ≥ 18 years of age on ICU admission;
3. estimate mechanical ventilation time ≥24 hours;