Predictive model for postoperative pneumonia in patients with esophageal cancer after esophagectomy Author names and affiliations

Jing Chen Qian Xiang Xiao-Jia Zheng ^* Xiao-Yan Jiang ^*

• Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital, Chengdu, China

Background: Pneumonia is one of the most common complications after esophagectomy and a risk factor affecting postoperative survival of esophageal cancer. The aim of this study was to identify risk factors and construct a predictive model for postoperative pneumonia (POP) in esophageal cancer.Methods: This retrospective cohort study included esophageal cancer patients who underwent therapeutic esophagectomy from June 2019 to December 2023. Least absolute shrinkage and selection operator (LASSO) regression was used to screen predictive factors for POP, and a nomogram was constructed based on the selected predictive factors after screening. The performance of the model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA).Results: A total of 667 esophageal cancer patients who underwent esophagectomy were included, of whom 61 (9.1%) developed postoperative pneumonia. After LASSO regression analysis, factors independently associated with POP included mechanical ventilation for more than 2 days (P=0.000) and blood transfusion (P=0.003). A nomogram was constructed based on these independent risk factors. The AUC of the predictive model for POP was 0.839 (95%CI: 0.768-0.911). The internal verification result showed a good discriminative power and the DCA results demonstrated a good predictive value.The predictive model constructed in this study can predict the risk of POP in patients with esophageal cancer, and may promote early intervention for high-risk patients by clinicians to reduce the incidence of POP.