AI-driven language biomarkers for early detection and progression of cognitive decline

Language is a cognitive function often impacted in early cognitive decline, potentially signalling earlystage dementia. Yet, despite extensive research, subtle linguistic markers in at-risk individuals remain poorly understood, highlighting the need for new investigative approaches. We propose integrating speech and language analysis with neuropsychological tests and biomarkers, using largescale, clinically validated datasets for robust, scalable analysis.

We aim to answer the following research questions:

Which speech, language, cognitive, and behavioral markers best distinguish early-stage cognitive impairment, and how do they correlate with neuropsychological test scores in a large-scale population study?

Does combining linguistic markers with behavioral, cognitive, and traditional biomarkers improve diagnostic accuracy for early cognitive decline compared to single-modality measures?

What measurable linguistic changes over time can speech and language analysis detect, and how do they relate to cognitive decline, disease progression, and prognosis?

The questions are addressed through state-of-the-art AI technologies: natural language processing, machine & deep learning, including algorithms for data preprocessing, feature selection, classification, and clustering. The project spans four years: one year for finalizing follow-up data collection; followed by three years of model development, validation, and analysis.