Neural-linguistic analysis for Alzheimer's detection: A deep learning approach informed by cognitive neuroscience

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that disrupts cognitive function across multiple domains, particularly affecting language networks and speech production pathways in the brain. Patients demonstrate symptoms including aphasia, reduced syntactic complexity, and diminished verbal fluency that reflects underlying neural pathology in language-related cortical areas. Current detection methods rely on resource-intensive neuroimaging, invasive biomarker sampling, and extensive neuropsychological testing, creating substantial barriers to early diagnosis. While researchers have explored using acoustic features, paralinguistic markers, and text-based features for AD detection, existing approaches face fundamental limitations: traditional acoustic methods fail to capture semantic-cognitive content, text transcription is labor-intensive, and automatic speech recognition quality suffers due to pronunciation variations and cognitive impairments in elderly populations. This paper introduces cognitive acoustic symbolic transformation for ALzheimer's (COASTAL), a neurobiologically-inspired framework that models hierarchical speech processing pathways. COASTAL transforms acoustic patterns into discrete symbolic elements through a specialized transformation module before applying contextual analysis that mirrors prefrontal-temporal language networks. Evaluated on the ADReSSo corpus, COASTAL achieved 70.42% accuracy, outperforming established baselines by 5.63%. Integration with complementary self-supervised approaches through hierarchical fusion improved performance to 77.46%. Analysis revealed that preserving fine-grained temporal features through shallower transformation architecture significantly enhanced diagnostic accuracy, aligning with neuropsychological evidence that subtle timing patterns in speech provide sensitive markers of cognitive decline.