A multivariate analysis of factors contributing to leakage of intestinal anastomoses

Abstract

Background: The study of anastomotic leaks is critically important to surgeons because morbidity and mortality increase many fold in the aftermath of an anastomotic disruption. Previous studies that have attempted to identify significant factors contributing to leakage of intestinal anastomoses used animal models or have analyzed retrospective data using univariate analysis. Our objective was to identify factors contributing to leakage of intestinal anastomoses.

Study design: We conducted a retrospective, multivariate analysis of 764 patients who underwent 813 intestinal anastomoses.

Results: The overall rate of anastomotic leakage was 3.4 percent. No difference was found in rates of leakage among different techniques of anastomosis or among different anastomotic locations. Colonic anastomoses leaked no more frequently than anastomoses of the small intestine. Proximal fecal diversion did not decrease the frequency of leaks. Multivariate analysis identified six significant predictive variables: a serum albumin level of less than 3.0 g/L, use of corticosteroids, peritonitis, bowel obstruction, chronic obstructive pulmonary disease, and perioperative transfusion of more than 2 U packed red blood cells. The in-hospital mortality rate in patients with and without leaks was 39.3 percent and 7 percent, respectively. Multivariate analysis showed that anastomotic leaks were an independent predictor of mortality.

Conclusions: Factors predictive of anastomotic leaks include chronic obstructive pulmonary disease, peritonitis, bowel obstruction, malnutrition, use of corticosteroids, and perioperative blood transfusion.