This study focuses on developing an explainable machine learning model based on cardiopulmonary interaction characteristics to achieve early prediction of acute lung injury (ALI) in patients undergoing major liver surgery. The research will establish a digital early-warning system for ALI to provide support for clinical diagnosis and treatment decisions, thereby reducing the incidence and fatality rate of ALI.
Age ≥ 18 years
Undergoing major liver surgery (including two-segment or more hepatectomy, liver transplantation, etc.)
Voluntary participation with signed informed consent
None
* Patient refusal * Presence of comorbidities affecting outcome assessment * Incomplete outcome records * Postoperative follow-up failure * Participation in other studies that may interfere with outcome assessment
Cohort
Other
None-placebo
Other interventionThis observational cohort study is non-interventional. Perioperative treatment plans are made based on model - suggested results and anesthesiologists' thought processes, without adding new medicines for patients.
Occurrence of ALI within 7 Days after Surgery
Berlin Definition: 1. Onset: Acute exacerbation of known injury or new/worsening respiratory symptoms within 1 week. 2. Chest Imaging (X-ray or CT): Bilateral pulmonary shadows not fully explained by exudation, atelectasis, or nodules. 3. Pulmonary Edema Etiology: Respiratory failure not fully attributed to heart failure or fluid overload; if no related risk factors, objective tests (e.g., Doppler echocardiography) are needed to exclude hydrostatic pulmonary edema. 4. Oxygenation Levels: Mild - With CPAP/PEEP \>5 cmH2O, 200 mmHg \< PaO2/FiO2 \< 300 mmHg; Moderate - With CPAP/PEEP \>5 cmH2O, 100 mmHg \< PaO2/FiO2 \< 200 mmHg; Severe - With CPAP/PEEP \>5 cmH2O, PaO2/FiO2 \< 100 mmHg.
Click on the lead sponsor to view all of their trials.
