Predictive value of gradient boosting decision trees for postoperative atelectasis complications in patients with pulmonary destruction.

Objective: To explore the application value of a gradient boosting decision tree (GBDT) in predicting postoperative atelectasis in patients with destroyed lungs.

Methods: A total of 170 patients with damaged lungs who underwent surgical treatment in Chest Hospital of Guangxi Zhuang Autonomous Region from January 2021 to May 2023 were retrospectively selected. The patients were divided into a training set (n = 119) and a validation set (n = 51).