Does it irk you when a friend or family member takes several pauses while telling you a story, struggles to find the right word or fills every other sentence with an ‘um’ or an ‘uh’? Well, before you lose your patience, there may be more to these little speech habits than meets the ear.Scientists have developed a new tool called a speech clock, which analyses subtle characteristics of a person’s speech to estimate how quickly they are aging. In a study involving 2,928 Spanish-speaking participants across five Latin American countries, researchers found that differences between a person’s actual age and their speech-predicted age were associated with cognitive impairment and dementia. The research, published in Science Advances, suggests that the way we speak could offer valuable clues about what is happening inside our brains.What is biological age?Most of us are familiar with chronological age, which is simply the number of years we have been alive. Biological age, however, is a little more complicated. It refers to how old our bodies and biological systems appear to be based on factors such as cellular damage, changes in organs and the effects of aging. The two do not always go hand in hand. Someone who is 60 years old, for instance, may have a biological age considerably younger or older than 60, depending on how their body has aged.Scientists use different kinds of biological clocks to estimate this gap. Some rely on blood samples, DNA changes and molecular markers, while others use brain scans to examine changes in brain structure and functioning.The new research introduces another possibility: using speech as an indicator of biological aging. The researchers call the difference between a person’s chronological age and their speech-predicted age the ‘speech age gap’ (SAG). A positive gap suggests that their speech displays characteristics associated with an older age than their actual age.What did the researchers do?The research team analysed speech recordings from 2,928 participants in Argentina, Chile, Colombia, Mexico and Peru. The group included 1,504 healthy individuals and 1,424 people with different forms of cognitive impairment, including mild cognitive impairment, Alzheimer’s disease and frontotemporal dementia.Using machine-learning models, the researchers examined hundreds of acoustic and linguistic characteristics in the recordings. These included speech timing, pitch, vocabulary, word choice, the complexity of language, 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. Researchers compared this predicted age with the participant’s actual age to calculate their speech age gap.They also compared the results with existing measures of brain ageing, blood-based biomarkers and cognitive assessments to understand whether the speech clock was picking up meaningful signs of ageing.Main findings of the researchThe results revealed a noticeable difference between healthy participants and those living with cognitive impairment. Healthy individuals generally had smaller speech age gaps, while participants with mild cognitive impairment and dementia tended to have larger ones.The differences were particularly pronounced among people with frontotemporal dementia, especially those whose condition affected language-related abilities. Participants with Alzheimer’s disease also showed larger gaps than those with mild cognitive impairment.The researchers further found that larger speech age gaps were associated with poorer performance in several cognitive assessments, including tests measuring executive functioning, memory and overall cognitive ability.There was another interesting finding. Among participants with Alzheimer’s disease, larger speech age gaps were associated with higher levels of p-tau217, a protein in the blood linked to Alzheimer’s-related brain changes. This suggests that speech patterns may reflect biological changes associated with the disease, rather than simply differences in how people communicate.Interestingly, pitch and emotional content were among the strongest contributors to speech profiles predicted to be older. Meanwhile, speech timing and the number of words used were important in identifying profiles associated with younger predicted ages.What does this mean for future testing?Using a speech clock could offer a relatively low-cost, low-effort way of monitoring aspects of cognitive ageing. Many existing biological ageing models require complicated procedures such as MRI scans, blood samples, molecular tests or specialised clinical assessments.Speech analysis, on the other hand, could be considerably easier to carry out. Recordings can potentially be collected in different settings, processed remotely and repeated over time to monitor changes. It is also non-invasive, making it a potentially more comfortable option for individuals undergoing repeated assessments.This could be particularly useful in regions where advanced diagnostic facilities are difficult to access. A speech-based tool may eventually help researchers identify people who could benefit from further cognitive assessments, without requiring expensive equipment at the first stage.However, it is important to remember that the technology is still being developed. Its purpose would be to complement existing diagnostic methods, not replace them.Limits of the studyHowever, this study, like any other, comes with its own limitations and needs further development. While the results are promising, the research was conducted at a single point in time. This means it cannot establish whether changes in speech appeared before cognitive decline or developed alongside an existing condition.Long-term studies will be needed to determine whether speech clocks can reliably predict future dementia or other age-related conditions.The study also focused on Spanish-speaking participants from five Latin American countries. There is no guarantee that the same model will work equally well across different languages, cultures, accents and speech patterns. Education, social background and recording conditions can also influence how people communicate.And last but not least, a speech clock cannot independently diagnose dementia. Its findings would need to be considered alongside clinical assessments, cognitive tests and, where appropriate, blood biomarkers and brain imaging.Your next long-winded conversation may require a little more patience. While a few awkward pauses are hardly cause for alarm, researchers are beginning to discover that the way we speak could tell us something about how our brains age.
Psychology says a few minutes of your speech may reveal how fast your brain is aging, after a model tested on 2,928 Spanish speakers linked bigger gaps between voice age and real age to dementia
RELATED ARTICLES
Recent Comments
on Hello world!
