CSF biomarker changes precede symptom onset of mild cognitive impairment

Abstract

Objective: This study evaluated longitudinal CSF biomarker measures collected when participants were cognitively normal to determine the magnitude and time course of biomarker changes before the onset of clinical symptoms in subjects with mild cognitive impairment (MCI).

Methods: Longitudinal CSF collection and cognitive assessments were performed on a cohort of 265 participants who were cognitively normal at their baseline assessment and subsequently developed MCI or dementia. CSF β-amyloid 1-42 (Aβ1-42), total tau (t-tau), and phosphorylated tau (p-tau) were determined longitudinally. Consensus diagnoses were completed annually. Cox regression analyses were performed, with baseline CSF values and time-dependent rate of change in CSF values as covariates (adjusted by baseline age, race, and education), in relation to time to onset of mild cognitive symptoms.

Results: The mean time from baseline to onset of mild cognitive symptoms was 5.41 years. Increased risk of progressing from normal cognition to onset of clinical symptoms was associated with baseline values of Aβ1-42, p-tau, and the ratios of p-tau/Aβ1-42 and t-tau/Aβ1-42 (p < 0.002). Additionally, the rate of change in the ratios of t-tau/Aβ1-42 (p < 0.004) and p-tau/Aβ1-42 (p < 0.02) was greater among participants who were subsequently diagnosed with MCI.

Conclusions: Baseline differences in CSF values were predictive of clinical symptoms that were a harbinger of a diagnosis of MCI more than 5 years before symptom onset, and continue to show longitudinal changes as cognitive symptoms develop, demonstrating that baseline and longitudinal changes in CSF biomarkers are evident during the preclinical phase of Alzheimer disease.

Figure 1. Kaplan-Meier plot for the value of CSF phosphorylated tau (p-tau), based on the Cox regression model

The black line represents values below the median at baseline and the red line represents values at or above the median at baseline. The y-axis represents the proportion of subjects remaining without symptoms. The plot starts at age 50 years and is truncated at 75 years because few cases remained unimpaired after this age, making those estimates unreliable. Note that the survival curves are not adjusted for age, education, or race.