Automatic Artificial Ventilation Therapy Using the ARDSNet Protocol Enforcing Dynamical Constraints

In this work, a medical expert system is further developed for automatic ventilation therapy based on the well-known ARDSNet protocol by imposing additional dynamical constraints. This protocol-driven approach strengthens the overall treatment of patients with acute lung injury in terms of improving oxygenation dynamics. The proposed dynamics of quick action and long idleness are introduced on two independent ventilatory variables, namely fraction of inspiratory oxygen (FiO(2)) and positive end-expiratory pressure (PEEP). The therapeutic algorithm is realizable forming additional rules for automatic control of artificial ventilation for the treatment of acute respiratory distress syndrome (ARDS). Furthermore, the proposed algorithm is applicable in real clinical practice. A validation test was performed on a 52-kg induced-ARDS pig with outstanding results to meet all ventilation goals.