In a groundbreaking study published in Science Advances, researchers have developed a new tool called the 'speech clock' that can estimate an individual's biological age based on subtle characteristics of their speech. By analyzing various acoustic and linguistic aspects of 2,928 Spanish-speaking participants across five Latin American countries, scientists found that differences between a person's actual age and their speech-predicted age were associated with cognitive impairment and dementia.

The study, conducted in Argentina, Chile, Colombia, Mexico, and Peru, involved both healthy individuals and those with various forms of cognitive impairment such as mild cognitive impairment, Alzheimer's disease, and frontotemporal dementia. Machine-learning models were used to examine hundreds of speech characteristics, including speech timing, pitch, vocabulary, word choice, language complexity, emotional expression, and the number of words used. The model was then trained to predict a person's chronological age based on these speech patterns, with larger gaps between predicted and actual ages indicating older biological ages.

Researchers found that healthy individuals generally had smaller speech age gaps, while those with cognitive impairment tended to have larger ones. This difference was particularly pronounced among people with frontotemporal dementia and Alzheimer's disease. Larger speech age gaps were also associated with poorer performance in several cognitive assessments. Furthermore, among participants with Alzheimer's disease, larger speech age gaps were linked to higher levels of p-tau217, a protein in the blood linked to Alzheimer's-related brain changes.

This new approach could potentially offer a low-cost, low-effort method for monitoring aspects of cognitive aging. Unlike existing biological aging models that require complicated procedures such as MRI scans, blood samples, molecular tests, or specialized clinical assessments, speech analysis could be considerably easier to carry out and repeated over time to monitor changes. This non-invasive method could provide a more comfortable option for individuals undergoing repeated assessments.