The Problem Dementia affects over 55 million people worldwide and is a growing public health crisis. Early signs often go undetected and current diagnostic methods are costly, timeconsuming and not scalable. Many tools lack cultural and linguistic inclusivity, causing disparities in diagnosis and care. There is a critical need for accessible, noninvasive and explainable methods to detect early motor-cognitive changes before clinical dementia develops. The Approach To address these challenges, this project will use an adaptable research approach to: Collect data from adults 50+ on fine motor control, pen pressure, rhythm and visuospatial skills via handwriting, drawing and touchscreen tasks. Develop interpretable machine learning models using explainable AI to detect early cognitive decline. Create data-driven protocols that account for handwriting, education and writing system variations to ensure generalizability and effectiveness for diverse community screening. Towards Early Dementia Detection Using Biomarkers “Detecting the signs of neurodegeneration early, affordably and understandably is not just a technological milestone, it is a public health imperative.” Gideon K. Gogovi, PhD Short Term Impact Advance early detection protocols using motorcognitive signals. Provide clinicians with interpretable tools for dementia risk assessment. Generate an open-access dataset of annotated motor-cognitive behaviors from diverse adults 50+. Longer Term Impact Establish new digital motor-cognitive biomarkers for early dementia detection. Guide proactive, targeted interventions to delay or reduce cognitive decline. Foster interdisciplinary collaboration. Societal Impact Funding for this research will support the advancement of resourceful tools for the early detection of cognitive decline using motor-cognitive signals. The project combines data-driven modeling and explainable AI to improve dementia risk assessment and inform targeted interventions. This work offers societal benefits in the following areas: For more information visit https://health.lehigh.edu/research-partners or email INRSRCH@lehigh.edu 11 Data Driven Innovation: Integrates interpretable machine learning in AI-based cognitive health. Community/Culture: Advances inclusive protocols for early dementia detection across diverse populations.
RkJQdWJsaXNoZXIy MTA0OTQ5OA==