Prediction model using risk factors associated with anastomotic leakage after minimally invasive esophagectomy

Objective: To explore the risk factors of anastomotic leakage after minimally invasive esophagectomy (MIE) and to build a prediction model of the probability of postoperative anastomotic leakage. Methods: Clinical data of patients undergoing MIE, admitted in the Fourth Hospital of Hebei Medical University from March 2018 to March 2022, were retrospectively selected, and risk factors of anastomotic leakage after MIE were analyzed by univariate and multivariate logistic regression. A prediction nomogram model was established based on the independent risk factors, and its prediction effect was evaluated. Results: A total of 308 patients were included. Thirty patients had postoperative anastomotic leakage, with an incidence of 9.74%. Logistic regression analysis showed that age, postoperative delirium, pleural adhesion, postoperative pulmonary complications, high postoperative white blood cell count and low lymphocyte count were risk factors for postoperative anastomotic leakage. A nomograph prediction model was constructed based on these risk factors. The predicted probability of occurrence of the nomograph model was consistent with the actual probability of occurrence. The calculated C-index value (Bootstrap method) was 0.9609, indicating that the nomograph prediction model had a good discrimination ability. By drawing the receiver operating characteristic (ROC) curve, we showed that the area under the curve (AUC) of the nomograph prediction model was 0.9609 (95%CI: 0.937-0.985), which indicated a good prediction efficiency of the model. Conclusions: The nomograph prediction model based on the independent risk factors of anastomotic leakage after MIE can accurately predict the probability of postoperative anastomotic leakage.