CSF biomarkers of neuroinflammation in distinct forms and subtypes of neurodegenerative dementia

Abstract

Background: In neurodegenerative dementias (NDs) such as prion disease, Alzheimer's disease (AD), and frontotemporal lobar degeneration (FTLD), protein misfolding leads to the tissue deposition of protein aggregates which, in turn, trigger neuroinflammation and neurodegeneration. Cerebrospinal fluid (CSF) biomarkers have the potential to reflect different aspects of these phenomena across distinct clinicopathological subtypes and disease stages.

Methods: We investigated CSF glial markers, namely chitotriosidase 1 (CHIT1), chitinase-3-like protein 1 (YKL-40) and glial fibrillary acidic protein (GFAP) in prion disease subtypes (n = 101), AD (n = 40), clinicopathological subgroups of FTLD (n = 72), and controls (n = 40) using validated, commercially available ELISA assays. We explored glial biomarker levels' associations with disease variables and neurodegenerative CSF biomarkers and evaluated their diagnostic accuracy. The genotype of the CHIT1 rs3831317 polymorphic site was also analyzed.

Results: Each ND group showed increased levels of CHIT1, YKL-40, and GFAP compared to controls with a difference between prion disease and AD or FTLD limited to YKL-40, which showed higher values in the former group. CHIT1 levels were reduced in both heterozygotes and homozygotes for the CHIT1 24-bp duplication (rs3831317) in FTLD and controls, but this effect was less significant in AD and prion disease. After stratification according to molecular subgroups, we demonstrated (i) an upregulation of all glial markers in Creutzfeldt-Jakob disease VV2 compared to other disease subtypes, (ii) a difference in CHIT1 levels between FTLD with TAU and TDP43 pathology, and (iii) a marked increase of YKL-40 in FTLD with amyotrophic lateral sclerosis (ALS) in comparison with FTLD without ALS. In prion disease, glial markers correlated with disease stage and were already elevated in one pre-symptomatic case of Gerstmann-Sträussler-Scheinker disease. Regarding the diagnostic value, YKL-40 was the only glial marker that showed a moderate accuracy in the distinction between controls and NDs.

Conclusions: NDs share a CSF profile characterized by increased levels of CSF CHIT1, YKL-40, and GFAP, which likely reflects a common neuroinflammatory response to protein misfolding and aggregation. CSF glial markers of neuroinflammation demonstrate limited diagnostic value but have some potential for monitoring the clinical and, possibly, preclinical phases of NDs.

Keywords: Alzheimer’s disease; Amyloid-beta; Amyotrophic lateral sclerosis; Corticobasal syndrome; Creutzfeldt-Jakob disease; Frontotemporal dementia; Human prion disease; Neurofilament light; Progressive supranuclear palsy; Tau protein.

Fig. 1

CSF markers of neuroinflammation and neurodegeneration across diagnostic groups. a CSF CHIT1, b CHIT1 according to genotype (WT: wild type for CHIT1 24-bp duplication; Het: heterozygotes for CHIT1 24-bp duplication), c YKL-40, d GFAP, e t-tau, and f NfL levels in prion disease (PRION), Alzheimer’s disease (AD), frontotemporal dementia (FTD), and controls (CTRLS). Horizontal lines represent medians. CHIT1,GFAP, t-tau and NfL values are expressed in logarithmic scale. Only statistically significant differences are displayed (Kruskal-Wallis test followed by Dunn-Bonferroni post hoc test)

Fig. 2

Glial markers in distinct sCJD molecular subtypes. a CSF CHIT1 (all cases), b CSF CHIT1 (after the exclusion of the homozygotes for CHIT1 24-bp duplication), c YKL-40, and d GFAP in sCJD MM(V)1, VV2, and MV2K subtypes. Horizontal lines represent medians. CHIT1 and GFAP values are expressed in logarithmic scale. Only statistically significant differences are displayed (Kruskal-Wallis test followed by Dunn-Bonferroni post hoc test)

Fig. 3

CHIT1 in distinct FTD clinical syndromes and molecular subtypes. a CSF CHIT1 (all cases) in FTD clinical groups. b CSF CHIT1 (after the exclusion of the homozygotes for CHIT1 24-bp duplication) in FTD clinical groups. c CSF CHIT1 in FTLD-TAU, FTLD-TDP without ALS, and FTLD-TDP with ALS (all cases). d CSF CHIT1 in FTLD-TAU, FTLD-TDP without ALS, and FTLD-TDP with ALS (after the exclusion of the homozygotes for CHIT1 24-bp duplication). Horizontal lines represent medians. CHIT1 values are expressed in logarithmic scale. Only statistically significant differences are displayed (Kruskal-Wallis test followed by Dunn-Bonferroni post hoc test)

Fig. 4

YKL-40 and GFAP in distinct FTD clinical syndromes and molecular subtypes. a CSF YKL-40 in FTD clinical groups. b CSF YKL-40 in FTLD-TAU, FTLD-TDP without ALS, and FTLD-TDP with ALS. c CSF GFAP in FTD clinical groups. d CSF GFAP in FTLD-TAU, FTLD-TDP without ALS, and FTLD-TDP with ALS. Horizontal lines represent medians. GFAP values are expressed in logarithmic scale. Only statistically significant differences are displayed (Kruskal-Wallis test followed by Dunn-Bonferroni post hoc test)