Effect of hypoproteinemia on the mortality of sepsis patients in the ICU: a retrospective cohort study

The objective of the study was to evaluate the effect of hypoproteinemia on the prognosis of sepsis patients and the effectiveness of exogenous albumin supplementation. A retrospective cohort study was conducted in adult ICUs. The subjects were 1055 sepsis patients in MIMIC III database from June 2001 to October 2012. There were no interventions. A total of 1055 sepsis patients were enrolled and allocated into two groups based on the lowest in-hospital albumin level: 924 patients were in the hypoproteinemia group (the lowest in-hospital albumin ≤ 3.1 g/dL) and 131 patients were in the normal group (the lowest in-hospital albumin > 3.1 g/dL). A total of 378 patients [331 (35.8%) were in the hypoproteinemia group, and 47 (35.9%) were in the normal group] died at 28 days, and no statistically significant difference was found between the two groups (P = 0.99). The survival analysis of the 28-day mortality rate was performed using the Cox proportional risk model and it was found that the lowest in-hospital albumin level showed no significant effect on the 28-day mortality rate (P = 0.18, 95%CI). Patients in the hypoproteinemia group exhibited a longer length of stay in ICU and hospital and more complications with AKI than those in the normal group. However, multivariate regression analysis found that there was no statistical significance between the two groups. In addition, multivariate regression analysis showed that patients in the hypoproteinemia group had a shorter time without vasoactive drugs and time without mechanical ventilation than those in the normal group (P < 0.01). In the subgroup analysis, univariate analysis and multivariate regression analysis showed that there was no significant difference in the 28-day mortality rate (39.6% vs 37.5%, P = 0.80), the proportion of mechanical ventilation time (P = 0.57), and vasoactive drug time (P = 0.89) between patients with and without albumin supplementation. However, patients in the albumin supplementation group had a longer length of ICU stay and hospital stay than those in the non-supplementation group (P < 0.01). Albumin level may be an indicator of sepsis severity, but hypoproteinemia has no significant effect on the mortality of sepsis patients. Despite various physiological effects of albumin, the benefits of albumin supplementation in sepsis patients need to be evaluated with caution.