Predictive model for intraoperative decision-making in video-assisted thoracoscopic lobectomy: optimizing chest drain placement for high-risk patients.

Background: For years, it has been the common and widely accepted practice in thoracic surgery to place apical and basal drains after a lobectomy to completely drain the pleural cavity. With the development of thoracoscopic technology, it became apparent that the use of a single chest tube provided the same clinical results. However, sometimes tension pneumothorax occurs with the need for additional pleural drainage. The aim of this study was to develop a prognostic model to identify high risk patients intraoperatively and to insert additional pleural drainage to prevent the development of pneumothorax after video-assisted thoracoscopic surgery (VATS) lobectomy. Methods: This was a retrospective multicenter study of patients (registry data was analyzed) who underwent VATS lobectomy via a standardized multiport approach between 2014 and 2022. In all cases, a single drain was used postoperatively. We used a machine learning algorithm and data synthesis to expand patient selection according to Riley's method. A total of 418 cases were analyzed in this study. After determining the prognostically significant factors, we performed a binary logistic regression analysis using reverse step-by-step inclusion of variables according to the Akaike information criterion. After validation of the model by bootstrap (400 iterations) and with the original dataset, a nomogram with a specific point distribution for each risk factor was created. Results: The rate of tension pneumothorax was 4.53% (n=66). The most significant variables associated with the need for additional drainage were adhesions, intraoperative lung suturing, fused interlobar fissure, enlarged intrapulmonary lymph nodes, chronic obstructive pulmonary disease (P<0.001). The C-index of the model was 0.957, the mean absolute calibration error was 0.6%, and the slope of the calibration curve was 0.959. A score of 26 points indicated a 95% risk of postoperative tension pneumothorax. Conclusions: The nomogram achieved good predictive performance for tension pneumothorax after minimally invasive lobectomy. High-risk patients could be identified, and additional drainage may be placed intraoperatively to reduce the risk of lung collapse in the postoperative period.