Plasma GFAP is an early marker of amyloid-β but not tau pathology in Alzheimer's disease

Abstract

Although recent clinical trials targeting amyloid-β in Alzheimer's disease have shown promising results, there is increasing evidence suggesting that understanding alternative disease pathways that interact with amyloid-β metabolism and amyloid pathology might be important to halt the clinical deterioration. In particular, there is evidence supporting a critical role of astroglial activation and astrocytosis in Alzheimer's disease. However, so far, no studies have assessed whether astrocytosis is independently related to either amyloid-β or tau pathology in vivo. To address this question, we determined the levels of the astrocytic marker GFAP in plasma and CSF of 217 amyloid-β-negative cognitively unimpaired individuals, 71 amyloid-β-positive cognitively unimpaired individuals, 78 amyloid-β-positive cognitively impaired individuals, 63 amyloid-β-negative cognitively impaired individuals and 75 patients with a non-Alzheimer's disease neurodegenerative disorder from the Swedish BioFINDER-2 study. Participants underwent longitudinal amyloid-β (18F-flutemetamol) and tau (18F-RO948) PET as well as cognitive testing. We found that plasma GFAP concentration was significantly increased in all amyloid-β-positive groups compared with participants without amyloid-β pathology (P < 0.01). In addition, there were significant associations between plasma GFAP with higher amyloid-β-PET signal in all amyloid-β-positive groups, but also in cognitively normal individuals with normal amyloid-β values (P < 0.001), which remained significant after controlling for tau-PET signal. Furthermore, plasma GFAP could predict amyloid-β-PET positivity with an area under the curve of 0.76, which was greater than the performance achieved by CSF GFAP (0.69) and other glial markers (CSF YKL-40: 0.64, soluble TREM2: 0.71). Although correlations were also observed between tau-PET and plasma GFAP, these were no longer significant after controlling for amyloid-β-PET. In contrast to plasma GFAP, CSF GFAP concentration was significantly increased in non-Alzheimer's disease patients compared to other groups (P < 0.05) and correlated with amyloid-β-PET only in amyloid-β-positive cognitively impaired individuals (P = 0.005). Finally, plasma GFAP was associated with both longitudinal amyloid-β-PET and cognitive decline, and mediated the effect of amyloid-β-PET on tau-PET burden, suggesting that astrocytosis secondary to amyloid-β aggregation might promote tau accumulation. Altogether, these findings indicate that plasma GFAP is an early marker associated with brain amyloid-β pathology but not tau aggregation, even in cognitively normal individuals with a normal amyloid-β status. This suggests that plasma GFAP should be incorporated in current hypothetical models of Alzheimer's disease pathogenesis and be used as a non-invasive and accessible tool to detect early astrocytosis secondary to amyloid-β pathology.

Keywords: Aβ-PET; GFAP; astrocytosis; cognition; tau-PET.

Figure 1

Plasma and CSF GFAP concentrations are increased in amyloid-β-positive groups. Violin plots with median values for plasma and CSF GFAP (z-scores) in amyloid-β-negative cognitively unimpaired individuals (CU Aβ−), amyloid-β-positive cognitively unimpaired individuals (CU Aβ+), amyloid-β-positive cognitively impaired individuals (CI Aβ+), amyloid-β-negative cognitively impaired individuals (CI Aβ−) and non-Alzheimer’s disease disorders, after adjusting for age and sex. *Significant group differences after adjusting for multiple comparisons with FDR corrections (q < 0.05).

Figure 2

Plasma and CSF GFAP concentrations are associated with amyloid-β-PET independently of tau-PET burden. Results of the linear regression analyses showing a significant relationship between amyloid-β burden measured on PET (Aβ-PET) (z-scores) and plasma GFAP (z-scores) in (A) all cognitively unimpaired individuals (CU), (B) amyloid-β-negative cognitively unimpaired individuals (CU Aβ−), (C) amyloid-β-positive cognitively unimpaired individuals (CU Aβ+), and (D) amyloid-β-positive cognitively impaired individuals (CI Aβ+), after adjusting for age and sex. In addition, a significant relationship between amyloid-β-PET and CSF GFAP (z-scores) was also found in (E) amyloid-β-positive cognitively unimpaired individuals (CU Aβ+). The top panel shows correlation plots between amyloid-β-PET and GFAP markers, whereas the bottom panel shows box plots depicting how amyloid-β-PET values vary according to GFAP quartiles. All associations remained significant after controlling for tau-PET burden.

Figure 3

Voxel-wise associations between plasma GFAP and amyloid-β-PET. Results of the voxel-wise regression analyses showing a significant relationship between amyloid-β burden measured on PET images and plasma GFAP in (A) all cognitively unimpaired individuals (CU) and (B) amyloid-β-positive cognitively unimpaired individuals (CU Aβ+), and (D) amyloid-β-positive cognitively impaired individuals (CI Aβ+), after adjusting for age and sex. All results were adjusted for multiple comparisons using FDR (q < 0.05).

Figure 4

Plasma GFAP shows early increases with amyloid-β-PET burden. Spline models showing the trajectories for (A) plasma GFAP and (B) CSF GFAP using global amyloid-β-PET SUVR as a proxy for time. Both models were significant; however, when the splines of plasma and CSF GFAP were compared, plasma GFAP showed steeper initial increases, overcoming CSF GFAP levels even before amyloid-β-PET positivity (C). Aβ = amyloid-β.

Figure 5

Plasma GFAP has a greater diagnostic accuracy in identifying an amyloid-β-positive status compared to other glial markers. Results of the receiver-operating curve analyses showing that plasma GFAP showed a better classification performance in distinguishing amyloid-β-PET-positive from amyloid-β-PET-negative individuals in (A) the whole sample, (B) all cognitively unimpaired individuals (CU) and (C) all amyloid-β-positive cognitively impaired individuals (CI). Moreover, plasma GFAP also showed a better classification performance in distinguishing patients with abnormal and normal CSF amyloid-β42/40 levels in a group of patients with non-Alzheimer’s disease disorders (D). AD = Alzheimer's disease; AUC = area under the curve.

Figure 6

Relationship between plasma and CSF GFAP with longitudinal amyloid-β accumulation and cognitive decline. Predicted trajectories for longitudinal amyloid-β (Aβ) accumulation determined by PET and MMSE scores (z-scores) in relation to plasma and CSF GFAP in the whole sample, after adjusting for covariates. The models were fit using continuous GFAP values but for illustration purposes the plots show the trajectories for individuals with high and low plasma GFAP for longitudinal amyloid-β-PET (A) and longitudinal MMSE (B) as well as for individuals with high and low CSF GFAP for longitudinal MMSE (C). All results were adjusted for multiple comparisons using FDR (q < 0.05).