In recent years, remarkable advances have been made in lung transplantation regarding donor evaluation, perioperative support, and immune regulation, laying a foundation for improving the long-term survival of recipients. The rational application of extended criteria donor lungs and the popularization of ex vivo lung perfusion technology have enhanced the utilization efficiency and safety of marginal donor lungs. Refined assessment of risk factors such as donors’ smoking history and infectious status has reduced the incidence of primary graft dysfunction and postoperative infection. In terms of recipient management, individualized assessment systems have been gradually optimized. The standardized application of intraoperative extracorporeal membrane oxygenation and the development of minimally invasive surgical techniques have effectively alleviated perioperative injuries. The optimization of postoperative immunosuppressive regimens and advances in rejection monitoring technologies have further improved the long-term survival of grafts. Nevertheless, chronic graft dysfunction and recurrent or refractory infections remain the major bottlenecks restricting long-term prognosis. Future research should focus on expanding donor sources, improving the repair quality of marginal donor lungs, promoting precise immunosuppression and anti-infection strategies, and comprehensively enhancing the long-term survival rate and quality of life of lung transplant recipients.

Lung transplantation is an important means to treat end-stage lung disease and improve the survival rate and quality of life of patients. However, many postoperative complications seriously affect the prognosis of recipients. Accurate identification of key prognostic factors and construction of individualized and accurate prediction models are of great significance for postoperative prognosis evaluation, treatment strategy formulation and clinical decision-making. In recent years, the clinical prediction model of lung transplantation has gradually changed from traditional statistical methods to machine learning-driven. Compared with traditional models such as Cox regression and Logistic regression, machine learning models such as random forest, support vector machine and artificial neural network have certain advantages in postoperative survival rate prediction, early warning of complications and pulmonary function evaluation. However, their application is also affected by insufficient sample size and poor interpretability of models. Under the condition of small samples, the traditional model still has important value in prediction accuracy. The appropriate prediction model should be selected according to the clinical status of lung transplantation in China, considering the factors such as sample size, variable complexity and model interpretability. In the future, a multi-center, large-sample lung transplantation database should be constructed to further optimize and tap the potential of machine learning algorithms to improve the robustness and clinical applicability of the model.

Lung transplantation is an important means to treat end-stage lung disease and improve the survival rate and quality of life of patients. However, many postoperative complications seriously affect the prognosis of recipients. Accurate identification of key prognostic factors and construction of individualized and accurate prediction models are of great significance for postoperative prognosis evaluation, treatment strategy formulation and clinical decision-making. In recent years, the clinical prediction model of lung transplantation has gradually changed from traditional statistical methods to machine learning-driven. Compared with traditional models such as Cox regression and Logistic regression, machine learning models such as random forest, support vector machine and artificial neural network have certain advantages in postoperative survival rate prediction, early warning of complications and pulmonary function evaluation. However, their application is also affected by insufficient sample size and poor interpretability of models. Under the condition of small samples, the traditional model still has important value in prediction accuracy. The appropriate prediction model should be selected according to the clinical status of lung transplantation in China, considering the factors such as sample size, variable complexity and model interpretability. In the future, a multi-center, large-sample lung transplantation database should be constructed to further optimize and tap the potential of machine learning algorithms to improve the robustness and clinical applicability of the model.