Surgery has remained the cornerstone of lung cancer therapy. Sleeve lobectomy, which is featured by not only the maximal resection of tumors but also the maximal preservation of functional lung parenchyma, has been proved to be a valid therapeutic option for the treatment of some centrally located lung cancer . Evidence points toward equivalent oncologic outcomes with improved survival and quality of life after sleeve resections compared with pneumonectomy. However, the postoperative morbidities and the long-term results after sleeve lobectomy remain controversial, especially in relation to nodal involvement and after induction therapy. With the development of technology, minimally invasive procedures have been performed more and more widely.
Abstract： Air leak is still a common postoperative complication after selective lobectomy. The majority of patients undergoing lobectomy have some risk factors of postoperative air leak or persistent air leak. Nowadays，preventive measures of postoperative air leak mainly include preoperative, intraoperative （surgical technique，reinforcement material，pleural cavity reduction），and postoperative （pleurodesis，chest drainage management） strategies. Many of these new measures have been applied in clinical practice with satisfactory outcomes.
ObjectiveTo develop a predictive model for postoperative pulmonary complications (PPC) following video-assisted thoracic surgery (VATS) in lung cancer patients by integrating cardiopulmonary exercise testing (CPET) parameters and machine learning techniques. MethodsA retrospective analysis was conducted patients with early-stage non-small cell lung cancer who underwent CPET and VATS at Guangdong Provincial People’s Hospital between October 2021 and July 2023. Patients were divided into a PPC group and a non-PPC group. The least absolute shrinkage and selection operator (LASSO) regression was used to select important features associated with PPC. Six machine learning algorithms were utilized to construct prediction models, including logistic regression, support vector machine, k-nearest neighbors, random forest, gradient boosting machine, and extreme gradient boosting. The optimal model was interpreted using SHapley Additive exPlanations (SHAP). ResultsA total of 325 patients were included, with an average age of 60.36 years, and 55.1% were male. Significant differences were observed between the PPC and non-PPC groups in age, diabetes, coronary heart disease, surgical approach, forced expiratory volume in 1 second (FEV1), forced vital capacity (FVC), FVC% predicted, peak oxygen uptake (peak VO2), anaerobic threshold (AT), and ventilatory equivalent for carbon dioxide slope (VE/VCO2 slope) (P<0.05). In the predictive model constructed by selecting 7 key features using LASSO regression, the random forest model demonstrated the best overall performance across various metrics, with an AUC of 0.930, an F1 score of 0.836, and a Brier score of 0.133 in the training set. It also exhibited good predictive ability and calibration in the test set. SHAP analysis ranked feature importance as follows: peak VO2, VE/VCO2 slope, age, FEV1, smoking history, diabetes, and surgical approach. ConclusionIntegrating CPET parameters, the random forest model can effectively identify high-risk patients for PPC and has the potential for clinical application.