Net albumin leakage in patients in the ICU with suspected sepsis. A prospective analysis using mass balance calculations

Abstract

Introduction: Albumin kinetics in septic shock have been extensively studied, but clinical recommendations remain weak. An increased transcapillary escape rate (TER) of albumin has been demonstrated, though TER does not account for lymphatic return. Mass balance calculations, considering lymphatic return, have been used to assess net albumin leakage (NAL) in major surgery but not in sepsis.

Objectives: This study aimed to evaluate NAL in ten ICU patients with suspected sepsis, hypothesizing a net positive leakage. Secondary aims included investigating associations between NAL and fluid overload, glycocalyx shedding products, and cytokines, as well as identifying factors associated with it.

Methods: This prospective, observational study included ten patients within twelve hours of ICU admission for suspected sepsis at Karolinska University Hospital Huddinge. Albumin, hematocrit, and hemoglobin levels were sampled at 0, 1, 2, 4, 8, and 24 h. NAL was estimated using mass balance calculations, comparing proportional changes in albumin and hemoglobin concentrations over time, adjusted for albumin and hemoglobin infusions and losses. A proportionally greater decrease or smaller increase in albumin compared to hemoglobin indicated NAL, representing the net leakage from the circulation to the interstitium minus lymphatic return.

Results: Over 24 h, patients exhibited a net positive albumin leakage to the interstitium of 8 ± 10 g (p = 0.029). NAL showed no correlation with glycocalyx shedding products or fluid overload but had a weak correlation with interleukin-6 and interleukin-8 in the first 4 h. Albumin infusions appeared to increase net leakage.

Conclusion: This study demonstrated a net positive albumin leakage of 8 ± 10 g over 24 h in ICU patients with suspected sepsis, with a weak early correlation to pro-inflammatory cytokines but no significant link to fluid balance or glycocalyx shedding. Notably, albumin infusions were associated with increased net leakage.

Fig. 1

Albumin turnover and metabolism in a healthy adult. This overview illustrates albumin turnover between the intravascular albumin mass (IAM = 120 g) and the interstitial pool (180 g). Transcapillary escape rate (TER = 144 g/day) is balanced by lymphatic return (144 g/day). Synthesis (13 g/day), elimination (13 g/day), infusions (e.g., albumin, platelets, FFP), and losses (e.g., bleeding, urinary albumin, drains) dynamically influence IAM. Synthesis and elimination are not included in the mass balance calculations but are unlikely to affect results over the 24-h study period. IAM = Intravascular Albumin Mass; MHb = Intravascular Hemoglobin mass; FFP = Fresh Frozen Plasma

Fig. 2

Temporal pattern of NAL a syndecan-1 b, hyaluronan c, interleukin-6 d, interleukin-8 e, tumor necrosis factor-α f. Bold red line denotes the mean in 10 patients. ^a repeated measures analysis of variance, ^b mixed effects model

Fig. 3

Correlation matrix (Pearson’s coefficient) in 9 patients between net albumin leakage (NAL) and the area under the curve of interleukin-6 (IL-6), interleukin-8 (IL-8), tumor necrosis factor-α (TNF-α), syndecan-1, hyaluronan, and fluid balance levels in the time period 0–4 h in the ICU a and 4–24 h in the ICU b. Data from one patient are missing due to incomplete sampling. To achieve a p-value of < 0.05, the Pearson correlation coefficient needs to be ≥ 0.66

Fig. 4

a Temporal pattern of the Δ albumin gained versus Δ NAL in 8 patients at 27 different timepoints in the first 82 h of ICU stay. Each patient is represented with its own color and each dot represents the amount of albumin gained by a patient (x-axis) and the subsequent corresponding change in NAL (Δ NAL) between 4 (1–46) hours later (Y = 0,3859*X + 3,567, r² = 0.25, p = 0.0075) b the mean change in Δ albumin versus mean Δ NAL in the same patients, represented by the same color as in a (Y = 0.6180*X—0.5863, r.² = 0.85, p = 0.0012)