Dynamic changes of angiopoietins and endothelial nitric oxide supply during fluid resuscitation for major gyn-oncological surgery: a prospective observation

Abstract

Background: Despite goal-directed hemodynamic therapy, vascular function may deteriorate during surgery for advanced abdominal tumor masses. Fluid administration has been shown to be associated with distinct changes in serum levels of functional proteins. We sought to determine how serum total protein and angiopoietin (ANG) levels change during major abdominal tumor surgery. In addition, ex vivo endothelial nitric oxide synthase (eNOS) activation as well as NO bioavailability in vivo were assessed.

Methods: 30 patients scheduled for laparotomy for late-stage ovarian or uterine cancer were prospectively included. Advanced hemodynamic monitoring as well as protocol-driven goal-directed fluid optimization were performed. Total serum protein, ANG-1, -2, and soluble TIE2 were determined pre-, intra-, and postoperatively. Phosphorylation of eNOS was assessed in microvascular endothelial cells after incubation with patient serum, and microvascular reactivity was determined in vivo by near-infrared spectroscopy and arterial vascular occlusion.

Results: Cardiac output as well as preload gradually decreased during surgery and were associated with a median total fluid intake of 12.8 (9.7-15.4) mL/kg*h and a postoperative fluid balance of 6710 (4113-9271) mL. Total serum protein decreased significantly from baseline (66.5 (56.4-73.3) mg/mL) by almost half intraoperatively (42.7 (36.8-51.5) mg/mL, p < 0.0001) and remained at low level. While ANG-1 showed no significant dilutional change (baseline: 12.7 (11.9-13.9) ng/mL, postop.: 11.6 (10.8 -13.5) ng/mL, p = 0.06), serum levels of ANG-2 were even increased postoperatively (baseline: 2.2 (1.6-2.6) ng/mL vs. postop.: 3.4 (2.3-3.8) ng/mL, p < 0.0001), resulting in a significant shift in ANG-2 to ANG-1 ratio. Ex vivo phosphorylation of eNOS was decreased depending on increased ANG-2 levels and ANG-2/1 ratio (Spearman r = - 0.37, p = 0.007). In vivo, increased ANG-2 levels were associated with impaired capillary recruitment and NO bioavailability (Spearman r = - 0.83, p = 0.01).

Conclusions: Fluid resuscitation-associated changes in serum vascular mediator profile during abdominal tumor surgery were accompanied by impaired eNOS activity ex vivo as well as reduced NO bioavailability in vivo. Our results may explain disturbed microvascular function in major surgery despite goal-directed hemodynamic optimization.

Keywords: Angiopoietins; Fluid resuscitation; Microvascular reactivity; Nitric oxide; eNOS.

Fig. 1

Changes in advanced hemodynamic monitoring during major gynecological abdominal tumor surgery. Advanced hemodynamic monitoring was established after induction of anesthesia and before beginning of surgery. Cardiac index (CI), stroke volume index (SVI), stroke volume variation (SVV), and systemic vascular resistance index (SVRI) were measured continuously by pulse contour analysis. Baseline values before beginning of surgery are plotted on left Y axis (median values indicated by black bar). Intraoperative values were normalized to the baseline and are given as percentage change (plotted on right Y axis, median indicated by red bar) Figure shows absolute values with the respective median, the thin line indicates the level of baseline value (100%). HR heart rate, MAP mean arterial blood pressure

Fig. 2

Changes in total serum protein, angiopoietins, and soluble TIE2 during major gynecological abdominal tumor surgery. Serum was sampled before beginning of surgery (baseline), intraoperatively every 5 L of administered fluids, and postoperatively. In samples, total serum protein as well as levels of ANG-1, -2, and soluble TIE2 were determined. Figure shows absolute values for baseline, 5 L, and postoperative time point. a Changes in total serum protein are given on the left panel. Middle panel shows the distribution of percentage total serum protein decrease in the whole cohort after 5 L of fluid administration. On the right panel, the association between individual percentage total serum protein decrease after 5 L of fluid administration and the postoperative fluid balance is shown (Spearman rank correlation, dashed lines indicate the 95% confidence interval). b Graphs show changes in ANG-1, -2, the ratio between ANG-2 and -1, and sTIE2. Wilcoxon signed-rank test, *** p < 0.001. Changes of serum parameters over time are shown as absolute values with median

Fig. 3

Influence of patient serum on endothelial nitric oxide synthase (eNOS) phosphorylation. a Human dermal microvascular endothelial cells (hdMVEC) were incubated with diluted serum samples collected from different patients at the various time points (baseline, after 5 L of fluid administration, and postoperatively), and eNOS phosphorylation was determined fluorometrically. b Graph shows association between individually increased serum ANG-2 levels and a reduction in eNOS phosphorylation ex vivo (Spearman rank correlation, dashed lines indicate the 95% confidence interval)

Fig. 4

Assessment of dynamic microvascular reactivity and nitric oxide bioavailability during major gynecological abdominal tumor surgery. Dynamic microvascular reactivity was assessed before beginning of and every 30 min during surgery by measuring tissue oxygenation by near-infrared spectroscopy (NIRS) combined with an arterial vascular occlusion maneuver (VOT). a Image illustrates general setup of assessment. A NIRS sensor is placed on the left forearm and connected to the NIRS monitor. A blood pressure cuff is placed around the ipsilateral upper arm. For VOT maneuver, the cuff is inflated to 50 mmHg above the systolic arterial blood pressure, and the pressure is maintained for 4 min before the cuff is rapidly and completely deflated. b Muscle tissue oxygen saturation (S_tO₂) during VOT maneuver. The following parameters can be derived from the VOT curve: baseline S_tO₂ before VOT maneuver (PreVOT), slope of tissue desaturation during VOT maneuver (DesatVOT), time to recover to baseline S_tO₂ following deflation of the cuff (RecovVOT), and size of reactive hyperemic area following VOT (HyperemicVOT). c Changes of VOT parameters over time during major gynecological abdominal tumor surgery. Values were compared with the respective baseline using the Friedman test in case of complete data sets from all included patients. In case of missing values at various time points, Friedman test is inappropriate and Wilcoxon signed-rank test was used instead