Speech Biomarkers Offer New Insights into Brain and Epigenetic Aging
Researchers have developed a machine learning 'speech clock' that can estimate a person's biological age based on hundreds of acoustic and linguistic features. This innovative tool, developed by Trinity College Dublin, analyzes elements such as speech rate, pauses, pitch, emotional expression, vocabulary, and semantic precision. The study, published in Science Advances, involved 2,928 Spanish-speaking participants, including healthy adults and individuals with mild cognitive impairment, Alzheimer’s disease, and various forms of frontotemporal dementia. The 'speech age gap'—the difference between a person's chronological age and their estimated biological age from speech—was found to correlate with multiple independent markers of biological aging, brain health, cognition, social adversity, and dementia. Individuals whose speech appeared older than their chronological age exhibited signs of aging in structural and functional neuroimaging, as well as epigenetic aging based on DNA methylation changes. Larger s...