Background: Poor glycaemic control during cardiac surgery is known to be associated with high morbidity. This study aimed to determine effect of intraoperative intensive glycaemic control with modified glucose-insulin-potassium solution by hyperinsulinaemic normoglycaemic clamp on the rate of 30-day postoperative infection by clinical and cytokines assessment.

Methods: A prospective, randomised, double-blind trial was conducted in cardiac surgical patients with cardiopulmonary bypass. One hundred and ninety-nine adult patients were randomly allocated to the intensive or the conventional group with a target glucose level of 4.4-8.3 mmol L^-1 and   < 13.8 mmol L^-1, respectively. The primary outcomes were clinical infection and cytokine levels, including interleukin (IL)-6 and IL-10. The secondary outcomes were morbidity and mortality.

Results: The clinical postoperative infection rate was 17% in the intensive group and 13 % in the conventional group (p = 0.53). In the intensive group, the baseline median IL-6 level was significantly lower than the conventional group (p = 0.01), while the 4-hour postoperative median IL-10 level was significantly higher (p = 0.04). Hypoglycaemia was significantly higher in the intensive group (23%) than the conventional group (3%) (p < 0.001). Morbidity and mortality rates were similar for both groups. Postoperative IL-6 level 55-110 pg mL^-1 (VS < 55 pg mL^-1), smoking status (ex VS never) and length of ICU stay > 48 hours (VS < 24 hours) were independent factors to predict postoperative infection.   

Conclusions: Intensive intraoperative glycaemic control significantly increased the risk of hypoglycaemia but its effect on postoperative infection on clinical assessment cannot be concluded, possibly due to the small sample size resulting from early termination of the study. Postoperative IL-6 level can independently predict postoperative infection.