Speaker: Natasha Clarke, Ph.D., Postdoctoral Fellow, IUGM Research Center
Summary
Analysis of connected speech – spontaneous, continuous speech elicited through tasks such as picture description – is a fast, low-cost, non-invasive approach for the early detection of neurodegenerative diseases. In this talk, I will outline how natural language processing and machine learning techniques can be applied to connected speech in Alzheimer’s disease and related disorders, and present my research since joining the CRIUGM in 2021. I will focus on three main contributions : demonstrating the importance of sex differences in speech-based markers, using state-of-the-art automated transcription to improve scalability and reproducibility, and linking specific speech patterns to resting-state functional connectivity to better understand their neural underpinnings.
Biography
Natasha Clarke is a postdoctoral fellow in Professor Simona Brambati’s Lingua Lab at the CRIUGM, where she investigate language and neuroimaging biomarkers for the early detection of neurodegenerative diseases. Her research integrates natural language processing, machine learning and resting-state functional MRI to better understand cognitive and neural changes in Alzheimer’s disease and related disorders, with a particular focus on sex differences.
Registration link