Digital Intelligence Early Warning System for Acute Lung Injury During Major Liver Surgery Based on Cardiopulmonary Interaction

What this Trial Is About

Researchers are developing a machine learning model to predict acute lung injury (ALI) early in patients undergoing major liver surgery. This study focuses on using cardiopulmonary interaction data collected before, during, and after surgery to create a digital early-warning system. The goal is to support clinical decisions, reduce ALI cases, and lower death rates related to this complication. The study involves gathering data from adult patients who have major liver surgeries such as two-segment or larger hepatectomy or liver transplantation. It includes both retrospective and prospective groups, with no new treatments or medications given as part of the study. Instead, clinical care follows usual protocols, and the machine learning model is developed using methods like logistic regression, random forest, support vector machines, and neural networks. The model's accuracy and other performance metrics will be tested to ensure reliability. Participants will have their routine medical data collected throughout the surgical process, from one day before surgery to seven days after, to monitor for ALI occurrence. Researchers will evaluate the model's ability to predict ALI during this perioperative period. There are no study interventions, and patient care remains standard. The study aims to improve early detection tools to aid doctors in managing and treating ALI in liver surgery patients.

Digital Early Warning System for Acute Lung Injury in Liver Surgery