Cerebrospinal fluid neopterin as a biomarker of neuroinflammatory diseases

Abstract

The elevation of neopterin in cerebrospinal fluid (CSF) has been reported in several neuroinflammatory disorders. However, it is not expected that neopterin alone can discriminate among different neuroinflammatory etiologies. We conducted an observational retrospective and case-control study to analyze the CSF biomarkers neopterin, total proteins, and leukocytes in a large cohort of pediatric patients with neuroinflammatory disorders. CSF samples from 277 subjects were included and classified into four groups: Viral meningoencephalitis, bacterial meningitis, acquired immune-mediated disorders, and patients with no-immune diseases (control group). CSF neopterin was analyzed with high-performance liquid chromatography. Microbiological diagnosis included bacterial CSF cultures and several specific real-time polymerase chain reactions. Molecular testing for multiple respiratory pathogens was also included. Antibodies against neuronal and glial proteins were tested. Canonical discriminant analysis of the three biomarkers was conducted to establish the best discriminant functions for the classification of the different clinical groups. Model validation was done by biomarker analyses in a new cohort of 95 pediatric patients. CSF neopterin displayed the highest values in the viral and bacterial infection groups. By applying canonical discriminant analysis, it was possible to classify the patients into the different groups. Validation analyses displayed good results for neuropediatric patients with no-immune diseases and for viral meningitis patients, followed by the other groups. This study provides initial evidence of a more efficient approach to promote the timely classification of patients with viral and bacterial infections and acquired autoimmune disorders. Through canonical equations, we have validated a new tool that aids in the early and differential diagnosis of these neuroinflammatory conditions.

Figure 1

Box plot of log-transformed variables. (A) CSF neopterin values. (B) CSF leukocyte count. (C) CSF total protein values. (D) Patient’s age. Regarding neopterin and leukocytes, the highest values were observed in the bacterial and viral meningitis groups and showed significant differences when compared with the other groups (ANOVA with Bonferroni correction). For CSF proteins, the highest values were detected in the bacterial infection group, which showed significant differences when compared with all of the other groups. Finally, the acquired autoimmune group showed the highest values with regard to the patient’s age variable. The individual statistical differences among groups are stated in additional file 4. The length of the boxes indicates the interquartile space (p25–p75); the horizontal line into the box represents the median (p50); and the circles indicate outlier values.

Figure 2

Box plot representation of the two dimensions of Can₁ and Can₂. (A) Patients from bacterial and viral infection groups had higher Can₁ values, while the lower values corresponded to acquired autoimmune conditions and controls. (B) Patients with bacterial meningoencephalitis could be differentiated from the other groups since they exhibit the lowest Can₂ values. The length of the boxes indicates the interquartile space (p25–p75); the horizontal line into the box represents the median (p50); and the circles indicate outlier values.

Figure 3

Graphical representation of each group and individual patients according to Can 1 and Can 2 dimensions. Legend: With the combination of both Can1 and Can2 dimensions, patients with acquired immune diseases and controls are separated from the other groups (negative values in Can₁ dimension). The viral and bacterial meningitis disease groups are also differentiated in the second dimension. The points indicate each patient included in the study according to canonical discriminant analysis. The control group (green points) are positioned at the graph left part (low Can1 values caused by low values of the 3 biomarkers assessed), the viral meningitis group (red points) is positioned at the upper right part (high Can1 and Can2 values) and the bacterial meningitis group is positioned at the low right part of the graph (high Can1 and low2 values). The autoimmune acquired disease group was more randomly distributed around the central part of the graph.