• 1. Department of Thoracic Surgery, Affiliated Hospital of Qingdao University, Qingdao, 266071, Shandong, P. R. China;
  • 2. Medical Department of Nantong University, Nantong, 226000, Jiangsu, P. R. China;
JIAO Wenjie, Email: jiaowj@qduhospital.cn
Export PDF Favorites Scan Get Citation

Objective  To identify and analyze risk factors for acute renal failure (ARF) after lung transplantation and develop a predictive model. Methods  The data of patients in this study were obtained from the United Network for Organ Sharing (UNOS) database who underwent unilateral or bilateral lung transplantation between 2015 and 2022. Preoperative and postoperative clinical characteristics of the patients were analyzed. A combined approach using random forest and least absolute shrinkage and selection operator (LASSO) regression were employed to identify key preoperative factors associated with the incidence of ARF following lung transplantation. Random forest was used to assess the importance of each feature variable, while LASSO regression further filtered the variables contributing most significantly to the model. The predictive performance of the constructed model was evaluated in both training and validation sets, with receiver operating characteristic curve and area under the curve (AUC) used to verify and compare model effectiveness. Results A total of 15 110 lung transplantation patients were included in the study, comprising 6 041 males and 9 069 females, with a median age of 62.00 (54.00, 67.00) years. Findings indicated that between postoperative renal dialysis and non dialysis patients there were statistical differences in preoperative lung diagnosis, estimated glomerular filtration rate (eGFR), mechanical ventilation, preoperative ICU treatment, extracorporeal membrane oxygenation (ECMO) support, infection within two weeks before transplantation, Karnofsky Performance Status (KPS) score, donor age, waitlist duration, double-lung transplantation, and ischemia time (P<0.05). Five variables related to ARF after lung transplantation were selected through random forest and LASSO regression, including recipients' eGFR, preoperative ICU treatment, ECMO support, bilateral lung transplantation, and ischemia time, and a nomogram model was established. Model evaluation results demonstrated that the constructed predictive model achieved high accuracy in both the training and validation sets, with favorable AUC values, confirming its validity and reliability. Conclusion This study discusses common risk factors for ARF following lung transplantation and introduces an effective predictive model with potential clinical application.

Copyright © the editorial department of Chinese Journal of Clinical Thoracic and Cardiovascular Surgery of West China Medical Publisher. All rights reserved