Heparin-Binding Protein (HBP), Neutrophil Gelatinase-Associated Lipocalin (NGAL) and S100 Calcium-Binding Protein B (S100B) Can Confirm Bacterial Meningitis and Inform Adequate Antibiotic Treatment

Abstract

The empirical administration of antibiotics for suspected bacterial meningitis denotes a poor bacterial stewardship. In this context, the use of biomarkers can distinguish between bacterial and viral infections before deciding treatment. Our study assesses how levels of heparin-binding protein (HBP), neutrophil gelatinase-associated lipocalin (NGAL), S100 calcium-binding protein B (S100B), and neuron-specific enolase (NSE) in cerebrospinal fluid (CSF) and in blood can promptly confirm bacterial etiology and the need for antibiotic treatment. The CSF and blood levels of HBP, NGAL, S100B, and NSE of 81 patients with meningitis were measured and analyzed comparatively. Statistical sensitivity, specificity, and positive and negative predictive values were evaluated. CSF levels of HBP and NGAL and the blood level of S100B in the bacterial meningitis group were significantly higher (p < 0.05). The area under curve (AUC) for predicting bacterial meningitis was excellent for the CSF level of HBP (0.808 with 93.54% sensitivity and 80.64% specificity), good for the CSF level of NGAL (0.685 with 75.00% sensitivity and 65.62% specificity), and good for the blood level of S100B (0.652 with 65.90% sensitivity and 57.14% specificity). CSF levels of HBP and NGAL, as well as the blood level of S100B, could help discriminate between bacterial and viral meningitis before considering antibiotic treatment.

Keywords: HBP; NGAL; NSE; S100B; bacterial meningitis; biomarkers.

Figure 1

ROC curves for various associations of biomarkers. Model 1 comprises the values of HBP and NGAL in CSF and S100B in blood, model 2 comprises the values of HBP in CSF and S100B in blood, while model 3 relies on the significant biomarkers identified during the paraclinical blood tests (WBC, PMN, Ly, CRP, ESR, Fib, creatinine). The AUC values > 0.9 define an outstanding discrimination, while the AUC values between 0.8 and 0.9 denote an excellent capacity for the prediction models [24].