Multivariate Logistic Regression Analysis of Postoperative Complications and Risk Model Establishment of Gastrectomy for Gastric Cancer: A Single Center Cohort Report

Shougen Cao, Hao Wang, Yanbing Zhou. Affiliated Hospital of Qingdao University

Objective: To evaluate the risk factors of postoperative complications and establish logistic regression model in a real life cohort of patients with gastric cancer following gastrectomy.

Methods: We retrospectively analyzed data on 2795 gastric cancer patients underwent surgical procedure at the Affiliated Hospital of Qingdao University between June 2007 and June 2012, established multivariate logistic regression model to predictive risk factors related to the postoperative complications according to the Clavien-Dindo classification system .

Results: 24 out of 86 variables were identified statistically significant in univariate logistic regression analysis, 11 significant variables entered multivariate analysis were employed to produce the risk model. Liver cirrhosis, diabetes mellitus, Child classification, invasion of neighboring organs, combined resection, introperative transfusion, Billroth II anastomosis of reconstruction, malnutrition, surgical volume of surgeons, operating time and age were independent risk factors for postoperative complications after gastrectomy. Based on logistic regression equation, P=Exp∑BiXi/(1+Exp∑BiXi), multivariate logistic regression predictive model that calculated the risk of postoperative morbidity was developed, P=1/(1+e(4.810-1.287X1-0.504X2-0.500X3-0.474X4-0.405X5-0.318X6-0.316X7-0.305X8-0.278X9-0.255X10-0.138X11)). the accuracy,sensitivity and specificity of the model to predict the postoperative complications were 86.7%,76.2% and 88.6%, respectively.

Conclusions: This risk model based on Clavien-Dindo grading severity of complications system and logistic regression analysis can predict severe morbidity specific to an individual patient’s risk factors, estimate patients’ risks and benefits of gastric surgery as an accurate decision-making tool and may serve as a template for the development of risk models for other surgical groups.

Keywords: Postoperative Complications, Gastric Cancer, Surgery

« Return to SAGES 2016 abstract archive