Soluble P-tau217 reflects amyloid and tau pathology and mediates the association of amyloid with tau

Abstract

Alzheimer's disease is characterized by β-amyloid plaques and tau tangles. Plasma levels of phospho-tau217 (P-tau217) accurately differentiate Alzheimer's disease dementia from other dementias, but it is unclear to what degree this reflects β-amyloid plaque accumulation, tau tangle accumulation, or both. In a cohort with post-mortem neuropathological data (N = 88), both plaque and tangle density contributed independently to higher P-tau217, but P-tau217 was not elevated in patients with non-Alzheimer's disease tauopathies (N = 9). Several findings were replicated in a cohort with PET imaging ("BioFINDER-2", N = 426), where β-amyloid and tau PET were independently associated with P-tau217. P-tau217 concentrations correlated with β-amyloid PET (but not tau PET) in early disease stages and with both β-amyloid and (more strongly) tau PET in late disease stages. Finally, P-tau217 mediated the association between β-amyloid and tau in both cohorts, especially for tau outside of the medial temporal lobe. These findings support the hypothesis that plasma P-tau217 concentration is increased by both β-amyloid plaques and tau tangles and is congruent with the hypothesis that P-tau is involved in β-amyloid-dependent formation of neocortical tau tangles.

Keywords: Alzheimer’s disease; amyloid; phosphorylated tau; plasma; tau.

Figure 1. Independent effects of plaque and tangle density on plasma P‐tau217

1. R ² and AIC for different regression models, using either only amyloid plaque density (“P”), only tangle density (“T”), both plaque and tangle density (“P + T”), or both plaque and tangle density including their interaction term (“PxT”). All models included age and sex as covariates. The panel shows adjusted R ², together with AIC (above the bars) for each model. We compared R ² between the models using a bootstrap procedure (N = 1,000 iterations), which showed that the R ² for the “PxT” model was marginally higher than for the “P + T” model (ΔR ² = 0.027, 95% CI −0.0034‐0.087) and significantly higher than for the “T” model (ΔR ² = 0.12, 95% CI 0.04‐0.24) and the “P” model (ΔR ² = 0.18, 95% CI 0.055‐0.31).

2. Associations between plasma P‐tau217 and plaque density (stratified by tertiles [T1‐3] of tangle density).

3. Associations between plasma P‐tau217 and tangle density (stratified by tertiles [T1‐3] of plaque density).

Data information: Tertiles were chosen to visualize the data in panels (B, C), but the regression models used continuous density data as predictors. The solid lines represent mean effects from regression models. The shaded areas are 95% confidence intervals for the mean effects. Samples were analyzed in duplicates.

Figure 2. Plasma P‐tau217 mediates effects of plaques on tangles

1. A–C

   Three different mediation models are shown, testing plasma P‐tau217 as a statistical mediator of plaque density on tangle density. Panel (A) shows the mediation of total tangle density (significant mediation, 60% of the direct effect of plaque density on tangle density was explained by plasma P‐tau217). Panel (B) shows the mediation of medial temporal lobe (MTL, entorhinal cortex and hippocampus) tangle density (no mediation). Panel (C) shows the mediation of tangle density in all regions except the MTL (strongest mediation, 77%). The P‐values are from linear regression models used to estimate the mediation effects.

Figure 3. Associations between plasma P‐tau217, Aβ plaque density, and medial temporal lobe (MTL) tangle density in people with limited tau pathology

1. A–C

   Individuals in the neuropathology cohort without tangles in the parietal or frontal lobe and no more than minimal tangle load in the temporal lobe were included in this analysis (N = 42). MTL tangles were defined as tangles in entorhinal cortex plus hippocampus. Relationships between variables were tested in linear regression models, adjusted for age and sex. In these models, plasma P‐tau217 was significantly associated with Aβ plaques (β = 1.64, P < 0.0001) (panel A) but not with MTL tangles (panel B). MTL tangles were not associated with Aβ plaques (panel C). The solid line in panel (A) is the mean effect from the regression model, and the shaded area is the 95% confidence interval of the mean.

Figure 4. Plasma P‐tau217, Aβ plaque density, and tau tangle density by primary neuropathology

1. A–C

   Individuals in the neuropathology cohort were divided into groups of no significant primary pathology (N = 31), AD (N = 36), PD (N = 13), and others (N = 8) and analyzed together with N = 9 additional subjects with primary non‐AD tauopathies (PSP/CBD). Data are shown for plasma P‐tau217 (panel A), plaque density (panel B), and tangle density (panel C). Plasma P‐tau217 was not elevated in PSP/CBD compared to subjects without significant primary pathology. AD, Alzheimer’s disease; CBD, corticobasal degeneration; PSP, progressive supranuclear palsy; and PD, Parkinson’s disease. The central band of the boxes is medians, and the boxes show interquartile ranges. The whiskers are defined as the smallest (largest) observation greater (less) than or equal to the first (third) quartile minus (plus) 1.5 times the interquartile range.

Figure 5. Associations between plasma P‐tau217 with Aβ PET and tau PET

1. A

   R ² and AIC for different regression models, using either only Aβ PET (“A”), only tau PET (“T(I‐VI)”), both Aβ and tau PET (“A + T”), or both Aβ and tau PET including their interaction term (“AxT”). All models included age and sex as covariates. The panel shows adjusted R ², together with AIC (above the bars) for each model. We compared R ² between the models using a bootstrap procedure (N = 1,000 iterations), verifying that the R ² for the “AxT” model was higher than for the “A + T” model (ΔR ² = 0.026, 95% CI 0.010‐0.058), the “T(I‐VI)” model (ΔR ² = 0.17, 95% CI 0.11‐0.26), and the “A” model (ΔR ² = 0.14, 95% CI 0.060–0.22).

2. B

   Associations between plasma P‐tau217 and Aβ PET stratified by tertiles (T) of tau PET (T1: SUVR ≤ 1.05, T2: 1.05 < SUVR ≤ 1.11, T3: 1.11 < SUVR ≤ 3.03).

3. C

   Associations between plasma P‐tau217 and tau PET stratified by tertiles (T) of Aβ PET (T1: SUVR ≤ 0.468, T2: 0.468 < SUVR ≤ 0.579, T3: 0.579 < SUVR ≤ 1.08).

4. D–I

   Associations with P‐tau217 across groups of Aβ and tau PET positivity. Cut‐points for Aβ PET (> 0.533 SUVR) and tau PET (> 1.36 SUVR in a ROI corresponding to Braak stages I‐IV) were used to define the groups. Associations are shown for global cortical Aβ PET (panels D‐F) and global cortical tau PET (corresponding to Braak stages I‐VI) (panels G‐I) in individuals classified as negative for both Aβ and tau (N = 264, panels D and G), positive for Aβ only (N = 104, panels E and H), or positive for both Aβ and tau (N = 58, panels F and I). The plots show R ² and P‐values from linear regression models. No covariates were included in these models, in order to generate R ²‐values for the PET measures alone.

Data information: In panels (B, C), tertiles were chosen to visualize the data, but the regression models used continuous PET uptake as predictors. In panel (C), one outlier was beyond the range of the x‐axis (plasma P‐tau217 = 17.8 ng/L, tau PET = 3.03 SUVR, 3^rd Aβ PET tertile). The solid lines represent mean effects from regression models. The shaded areas are 95% confidence intervals for the mean effects. Samples were analyzed in duplicates.

Figure 6. Mediation analyses in BioFINDER‐2

1. A, B

   Plasma P‐tau217 partly mediated the effect of Aβ PET on tau PET, when using tau PET quantified in Braak stages I‐VI (A, “Tau PET global”, 66% of the direct effect of Aβ PET on tau PET was explained by plasma P‐tau217) or in the medial temporal lobe (B, MTL, entorhinal cortex and hippocampus, 29%). The P‐values are from linear regression models used to estimate the mediation effects.

Figure 7. Hypothetical integration of neuropathology, fluid biomarker, and PET imaging findings.

The figure shows hypothetical pathways, supported by our results, which link deposition of Aβ pathology to development of neocortical tangles through increased phosphorylation and/or release of soluble tau. We also include a hypothetical feedback loop, where tangle pathology also may drive increased levels of soluble P‐tau, possible due to tau propagation between affected neurons. We also acknowledge that other alternative explanations may be considered for our findings. One possibility is that lack of sensitivity of our methods to accurately quantify aggregated tau makes us unable to detect very early associations between aggregated tau and plasma P‐tau217.