Summarized by Masters of Longevity from Neuroscience News.
A feature article describing research that uses voice recordings and machine learning to estimate people’s biological brain aging. It invites readers to learn how speech-based models might serve as a scalable, noninvasive window into brain health and social influences on aging.
Key Takeaways
- A speech clock trained on 2,928 Spanish-speaking participants estimated vocal age and produced a speech age gap associated with clinical diagnosis.
- Higher speech age gaps correlated with brain atrophy on MRI and elevated plasma p-tau217 levels linked to Alzheimer’s disease.
- Lifelong social adversity, including lower education and food insecurity, was associated with accelerated speech aging across cohorts.
