Real-Time Algorithm-Driven Ventilation Feedback to Improve Lung-Protective Ventilation in Patients With ARDS (REALVENT-study)

The REALVENT trial is designed to evaluate whether a real-time, algorithm-driven ventilation feedback strategy can improve lung-protective ventilation (LPV) achievement rates in critically ill patients receiving invasive mechanical ventilation. This multicentre randomised controlled trial will compare real-time respiratory waveform monitoring with automated feedback against standard ICU care. The primary endpoint is the LPV achievement rate over the first 72 hours.

Inclusion Criteria: * Age between 18 and 75 years * Receiving invasive mechanical ventilation via endotracheal intubation at the time of screening * Initiation of invasive mechanical ventilation within the past 24 hours * PaO₂/FiO₂ ≤ 200 mmHg on PEEP ≥ 8 cmH₂O or, if arterial blood gas is unavailable: SpO₂/FiO₂ ≤ 235 with SpO₂ ≤ 97% * Chest imaging (chest X-ray or CT) showing bilateral pulmonary infiltrates not fully explained by pleural effusions, lobar collapse, or pulmonary nodules * Respiratory failure not fully explained by cardiac failure or fluid overload * Expected to require invasive mechanical ventilation for ≥ 72 hours after enrollment Exclusion Criteria: * Receipt of extracorporeal membrane oxygenation (ECMO) or high-frequency oscillatory ventilation at screening * Brain death or anticipated withdrawal of life-sustaining treatment within 72 hours * Pregnancy * Known neuromuscular disease affecting spontaneous respiratory effort * Prisoners or individuals unable to provide informed consent or surrogate consent * Simultaneous enrollment in another interventional ICU study * Lack of digital infrastructure for real-time ventilator waveform acquisition