Postoperative pulmonary infection (PPI) is a serious complication following thoracoscopic surgery for lung cancer, affecting recovery and prognosis. Early identification of high-risk patients could enable targeted interventions. In this retrospective study, 432 lung cancer patients who underwent thoracoscopic surgery were randomly divided into a training set (n = 302) and a validation set (n = 130). Multivariable logistic regression was used to identify independent predictors of PPI and construct a nomogram. Model performance was assessed using the concordance index (C-index), calibration curves, and decision curve analysis. The final nomogram included 5 routinely available predictors: pulmonary disease, reduced pulmonary function (FEV1 <80%), hypoalbuminemia (albumin <35 g/L), advanced pathological stage (III–IV), and thoracic drainage time ≥3 days. The model showed good discrimination with C-index values of 0.90 in the training set and 0.87 in the validation set, with satisfactory calibration and net benefit on decision curve analysis. This nomogram provides an interpretable tool for early postoperative prediction of PPI risk after thoracoscopic lung cancer surgery and may support individualized perioperative management.
Luo et al. (2026) studied this question.