Abstract
BACKGROUND: Digital language markers show promise in detecting early cognitive impairment related to Alzheimer's disease (AD), yet their relationship with cerebrospinal fluid (CSF) biomarkers of AD pathology remains unclear mainly due to the lack of data with both CSF and language markers. OBJECTIVE: This study aims to build links between digital language markers and fluid biomarkers through surrogate CSF biomarkers. METHODS: Using NACC clinical data as anchor variables, language makers in the I-CONECT study were linked to NACC CSF data. Surrogate CSF biomarkers were created for I-CONECT subjects using machine learning models from common NACC clinical variables. Correlations assessed associations between CSF and language markers. RESULTS: Lower predicted amyloid-β correlated significantly with reduced syntactic complexity and shorter speech responses. Higher predicted total tau and phosphorylated tau correlated with reduced syntactic complexity. CONCLUSIONS: This study demonstrates novel links between language markers and fluid biomarkers, highlighting conversational language as a potential accessible, non-invasive approach for early detection and monitoring of Alzheimer's pathology.