Prediction Model for PPCs in Patients Undergoing Lung Transplantation Using Machine Learning

Since the first human lung transplantation in 1963, significant advancements in immunosuppressive agents from the mid-1990s have greatly improved the quantity and quality of such procedures. In 2004, a total of 1,815 lung transplantations were globally reported. Patients undergoing this procedure are typically elderly and experience not only impaired lung function but also overall health instability. Despite successful outcomes, postoperative pulmonary complications (PPCs) can lead to serious consequences, including deterioration and fatality. PPCs resulting from lung transplantation may lead to prolonged hospitalization, increased complications, and the need for additional treatment. Various factors, such as age, smoking, pre-existing lung diseases, immunosuppressive drug use, diabetes, hypertension, infections, allergies, and immune disorders, are associated with the development of PPCs. The retrospective analysis of medical records from adult patients who underwent lung transplantation aims to investigate patient characteristics, anesthesia methods, intraoperative tests, and the occurrence of PPCs, with the ultimate goal of analyzing the incidence and risk factors of postoperative respiratory complications and developing a predictive model through machine learning.