Brain natriuretic peptide (BNP) may play a major role in risk stratification based on cerebral oxygen saturation by near-infrared spectroscopy in patients undergoing major cardiovascular surgery

Abstract

Purpose: A previous study reported that low baseline cerebral oxygen saturation (ScO2) (≤50%) measured with near-infrared spectroscopy was predictive of poor clinical outcomes after cardiac surgery. However, such findings have not been reconfirmed by others. We conducted the current study to evaluate whether the previous findings would be reproducible, and to explore mechanisms underlying the ScO2-based outcome prediction.

Methods: We retrospectively investigated 573 consecutive patients, aged 20 to 91 (mean ± standard deviation, 67.1 ± 12.8) years, who underwent major cardiovascular surgery. Preanesthetic baseline ScO2, lowest intraoperative ScO2, various clinical variables, and hospital mortality were examined.

Results: Bivariate regression analyses revealed that baseline ScO2 correlated significantly with plasma brain natriuretic peptide concentration (BNP), hemoglobin concentration (Hgb), estimated glomerular filtration rate (eGFR), and left ventricular ejection fraction (LVEF) (p < 0.0001 for each). Baseline ScO2 correlated with BNP in an exponential manner, and BNP was the most significant factor influencing ScO2. Logistic regression analyses revealed that baseline and lowest intraoperative ScO2 values, but not relative ScO2 decrements, were significantly associated with hospital mortality (p < 0.05), independent of the EuroSCORE (p < 0.01). Receiver operating curve analysis of ScO2 values and hospital mortality revealed an area under the curve (AUC) of 0.715 (p < 0.01) and a cutoff value of ≤50.5% for the baseline and ScO2, and an AUC of 0.718 (p < 0.05) and a cutoff value of ≤35% for the lowest intraoperative ScO2. Low baseline ScO2 (≤50%) was associated with increases in intubation time, intensive care unit stay, hospital stay, and hospital mortality.

Conclusion: Baseline ScO2 was reflective of severity of systemic comorbidities and was predictive of clinical outcomes after major cardiovascular surgery. ScO2 correlated most significantly with BNP in an exponential manner, suggesting that BNP plays a major role in the ScO2-based outcome prediction.

Fig 1. Relationships of BNP, logarithmic BNP, EuroSCORE, and logarithmic EuroSCORE to baseline ScO₂.

Relationships between BNP and baseline ScO₂ (A), between logarithmic BNP and baseline ScO₂ (B), between EuroSCORE and baseline ScO₂ (C), and between logarithmic EuroSCORE and baseline ScO₂ (D) are shown. Pearson’s correlation coefficients (r) and p values are depicted in each panel. Exponential regression lines, in addition to linear regression lines, are depicted in left panels (A and C). BNP, brain natriuretic peptide; ScO₂, cerebral oxygen saturation.

Fig 2. Relationships of Hgb, eGFR, BSA, and LVEF to baseline ScO₂.

Relationships between Hgb and baseline ScO₂ (A), between eGFR and baseline ScO₂ (B), between BSA and baseline ScO₂ (C), and between LVEF and baseline ScO₂ (D) are shown. Pearson’s correlation coefficient (r) and a p value are depicted in each panel. Hgb, hemoglobin; eGFR, estimate glomerular filtration rate; BSA, body surface area; LVEF, left ventricular ejection fraction; ScO₂, cerebral oxygen saturation.

Fig 3. Results of ROC analyses of EuroSCORE, baseline ScO₂, and lowest intraoperative ScO₂ for predicting hospital mortality.

Areas under curves (AUCs) and p values were 0.883 (95% CI, 0.806–0.932; p < 0.0001) for the EuroSCORE, 0.715 (95% CI, 0.508–0.859; p < 0.01) for the baseline ScO₂, and 0.718 (95% CI, 0.577–0.826; p = 0.0160) for the lowest intraoperative ScO₂, respectively. ROC, receiver operating curve; ScO₂, cerebral oxygen saturation.