Development and Prospective Validation of the AutoEIT Foundation Model for ARDS

Acute Respiratory Distress Syndrome (ARDS) is a highly heterogeneous condition, making precision mechanical ventilation challenging. Electrical Impedance Tomography (EIT) provides real-time monitoring of regional lung ventilation, but interpreting its complex spatiotemporal data relies on subjective clinical experience. This multicenter ambispective cohort study aims to develop and validate an all-in-one Artificial Intelligence Foundation Model (AutoEIT). The study consists of two phases: (1) A Retrospective Phase (data from 2020 to 2025, N=1000) to train the AutoEIT model using continuous EIT images and synchronous high-frequency ventilator waveforms; and (2) A Prospective Temporal Phase (January 2026 to December 2026, N=200) to rigorously test the model's performance in a real-world clinical setting. The AutoEIT model is a deep multi-task learning framework designed to simultaneously perform five core clinical tasks: (1) classify ARDS subphenotypes, (2) recommend individualized positive end-expiratory pressure (PEEP), (3) detect occult patient-ventilator asynchrony, (4) predict ventilation/perfusion (V/Q) ratio, and (5) continuously estimate the non-invasive PaO₂/FiO₂ ratio. Ultimately, this system aims to reduce ventilator-induced lung injury (VILI) and improve precision respiratory care.

Inclusion Criteria: * Age ≥ 18 years; * Admitted to the Intensive Care Unit (ICU); * Receiving invasive mechanical ventilation for at least 24 hours; * Diagnosed with moderate-to-severe ARDS according to the Berlin Definition as PaO2/FiO2 ≤ 200 mmHg with PEEP ≥ 5 cmH2O.; * Underwent continuous EIT monitoring during the ICU stay; * Availability of synchronized high-frequency ventilator waveforms and concurrent arterial blood gas (ABG) results; * (Specific for Prospective Cohort): EIT, ventilator, and clinical event times must be prospectively synchronized via precise time-stamping before data recording. Exclusion Criteria: * Extremely poor EIT signal quality (e.g., severe artifacts, electrode detachment lasting \> 50% of the monitoring time); * Patients receiving Extracorporeal Membrane Oxygenation (ECMO) therapy prior to or during the EIT monitoring period; * Severe thoracic deformity, un-drained severe pneumothorax, or extensive chest burns precluding proper EIT belt placement; * Decision to withhold or withdraw life-sustaining treatment do-not-resuscitate/do-not-intubate (DNR/DNI) at the time of enrollment.