Prediction Model for Postoperative Pulmonary Complications in Patients Undergoing Lung Transplantation Using Machine Learning: a Retrospective Cohort Study

After the first report of lung transplantation in humans in 1963, rapid advancements in immunosuppressive agents since the mid-1990s have led to significant progress in both the quantity and quality of lung transplantation. In 2004, a total of 1,815 lung transplantations were reported worldwide. Patients undergoing lung transplantation are typically elderly, often experiencing not only impaired lung function but also overall instability in their health. Despite successful outcomes in lung transplantation, the occurrence of pulmonary complications after surgery can lead to deterioration or even fatal consequences.

Postoperative pulmonary complications (PPCs) can result in prolonged hospitalization, increased complications, and the need for additional treatment. Various factors are associated with the development of PPCs after lung transplantation, including age, smoking, pre-existing lung diseases (such as chronic obstructive pulmonary disease, pulmonary fibrosis, etc.), immunosuppressive drug use post-transplant, diabetes, hypertension, pulmonary hypertension, heart disease, infections, allergies, and immune disorders. The retrospective analysis of medical records of adult patients who underwent lung transplantation aims to investigate patient characteristics, anesthesia methods, intraoperative tests, and the occurrence of PPCs. The goal is to analyze the incidence and risk factors of postoperative respiratory complications and develop a predictive model through machine learning.