Introduction

Cerebrospinal fluid (CSF) biomarkers provide evidence of Alzheimer’s disease (AD) pathology, yet their relationship to cognitive change captured by digital tools remains unclear. Speech-based digital cognitive measures are sensitive to early impairment1. Yet, whether they capture distinct longitudinal trajectories in biomarker- positive versus biomarker-negative individuals is unknown. Here, we examined whether a speech- based global cognitive composite (SB-C) and its domain scores captures longitudinal change as a function of CSF biomarker status.

 

Methods

Participants: N = 50 participants at baseline divided into biomarker positive (N = 15) and biomarker negative (N = 35) based on CSF Aβ42/P-tau 181.

Statistics: Linear mixed-effects models examined longitudinal SB-C trajectories adjusting for covariates and participant-specific random effects. Estimated slopes and marginal means changes from baseline were derived. CSF was collected prior to speech; all biomarker-positive participants were included, while biomarker-negative participants were restricted to a CSF-to-baseline-speech gap ≤2.5 years.

 

Results

Longitudinally, there was a significant interaction between CSF-biomarker status x time for the SB-C global (p= 0.03) and memory scores (p= 0.05). Biomarker-negative individuals improved faster over time indicating learning-related gains (Fig.1). No significant interaction was found for the SB-C executive function (p= 0.16) and processing speed scores (p= 0.10).

 

Conclusion

Despite modest sample size and temporal separation between CSF collection and speech, SB-C captured longitudinal patterns by CSF biomarker status. Improvement confined to biomarker-negative individuals, potentially reflecting preserved learning/practice-related gains. Findings highlight the potential of speech- based markers in complementing biomarker- informed stratification and improving longitudinal monitoring.

Contact

Sofia.ALEXOPOULOU@univ-cotedazur.fr

 

Acknowledgements

The work of ZS Alexopoulou is funded by the European Union’s HORIZON-MSCA Doctoral Networks 2021 program. The PROSPECT-AD study is funded by the Alzheimer’s Drug Discovery Foundation Diagnostic Accelerator program.

 

References

1. König, A., Tröger, J., Mallick, E., et al. Speech-based digital cognitive assessment for clinical trials: Detecting cognitive impairment stages and AD biomarker relations across European cohorts. Alzheimer’s & Dementia. 2026; 22(5), e71462. doi: https://doi.org/10.1002/alz.71462

2. König A, Linz N, Baykara E, et al. Screening over Speech in Unselected Populations for Clinical Trials in AD (PROSPECT- AD): Study Design and Protocol. J Prev Alzheimers Dis. 2023;10(2):314-321. doi:10.14283/jpad.2023.11