TL;DR
Get comfort and care essentials delivered free — and shop member deals
- Fast, free delivery on millions of items
- Access to Prime Big Deal Days deals on October 6–7
- Prime Video, Amazon Music and more included
A study in Science Advances analyzed speech from 2,928 Spanish-speaking participants in five Latin American countries and found that speech age gaps differed across dementia groups and were associated with cognitive performance and some aging-related measures. The analysis was cross-sectional, so it does not show that speech can track how quickly a person ages or diagnose dementia.
The research team studied participants in the ReDLat consortium from Colombia, Chile, Argentina, Mexico and Peru. The cohort included 1,504 cognitively healthy controls, 24 people with mild cognitive impairment, 1,068 with Alzheimer’s disease, 255 with non-language-dominant frontotemporal dementia and 77 with language-dominant frontotemporal dementia. Participants completed standardized Spanish-language tasks, including describing a video, verbal fluency and retelling stories.
An automated system used acoustic and language features to estimate a participant’s speech age. Researchers compared that estimate with chronological age to calculate a speech age gap, or SAG. A positive gap meant a person’s speech appeared older than their chronological age; a negative gap indicated a younger-appearing profile. The largest gaps were observed in language-dominant frontotemporal dementia, followed by non-language-dominant frontotemporal dementia, Alzheimer’s disease and mild cognitive impairment.
Larger gaps were associated with poorer scores in memory, executive function and overall cognition. The memory relationship was particularly strong in Alzheimer’s disease and non-language-dominant frontotemporal dementia, and links were generally stronger for language measures than for nonlinguistic abilities. Larger gaps also accompanied higher blood levels of p-Tau217 across the cohort, though the association within diagnostic groups was statistically significant only for Alzheimer’s disease.
Speech Signals Across Dementia Groups
The findings add to research into aging measures that do not rely solely on chronological age. Existing approaches can use DNA methylation, brain imaging, blood tests or combinations of biological and behavioral measures. Those methods may require specialized equipment or costly collection, while speech recordings and transcripts could potentially be gathered at lower cost and analyzed automatically.
A speech-based measure could help researchers study cognitive aging at scale, including in places where access to specialized testing is limited. The study’s Latin American cohort offers evidence from populations that have been underrepresented in dementia research. That does not establish that the system is ready for routine clinical use: its value for screening, diagnosis or care decisions was not tested by these findings.
The results also suggest that speech may reflect more than a dementia label. Associations with cognition, tau and social exposures indicate that speech features could capture several influences on aging. Researchers would need to establish how specific those signals are and whether they can distinguish dementia-related changes from other causes before the measure could support individual assessments.
speech analysis device for cognitive health
As an affiliate, we earn on qualifying purchases.
As an affiliate, we earn on qualifying purchases.
How Researchers Built The Speech Clock
Aging clocks estimate differences between a person’s chronological age and patterns measured in the body or brain. Researchers use several types, including brain age gaps, epigenetic clocks based on DNA methylation, and biobehavioral measures linked to social and behavioral exposures. These approaches are designed to capture variation that a calendar age alone cannot describe.
Speech can change as cognition and motor control change. Researchers can measure timing, pauses, word retrieval, pitch and language use in recordings and transcripts. The study tested whether a speech age gap corresponded with dementia phenotypes and with cognitive, social, neuroimaging, molecular and epigenetic measures. The supplied study summary reports findings for cognition, plasma p-Tau217 and social exposures; it does not provide detailed results for every measure examined.
The cohort included a wide range of cognitive performance, but the study compared people at a point in time. Its speech age gaps describe how old or young participants’ speech appeared relative to their chronological age in that analysis. They are not direct measurements of a person’s rate of biological aging.
““objective, automated, affordable, noninvasive aging markers enabling timely, large-scale, equitable deployment in low-income, underrepresented regions with high dementia burden.””
— The study authors
Limits Of A Single Snapshot
The analysis was cross-sectional, meaning it assessed participants at a point in time rather than following changes in their speech over years. It therefore cannot show that people with a positive speech age gap are aging faster, or that the measure predicts future dementia. The observed associations also do not establish that speech changes caused, or uniquely identify, the cognitive and biological differences.
The study summary does not provide performance measures needed to judge how accurately the speech clock classifies individuals, how it performs across different languages or dialects, or whether it can separate dementia-related changes from other influences on speech. The cohort’s small mild cognitive impairment group—24 people—also means that results for that category require careful interpretation. The summary mentions links between the speech clock and social exposures but does not detail their direction or size.
Testing Speech Measures Over Time
Further research would need to test the speech clock in longitudinal studies that record participants repeatedly, to determine whether speech age gaps change as people age or their health changes. Validation in additional populations, languages and clinical settings would help show how well the approach generalizes beyond this Spanish-speaking cohort.
Researchers would also need to report how accurately the measure estimates age and distinguishes diagnostic groups, and whether it adds useful information alongside established clinical assessments and biomarkers. Until those questions are answered, the study supports speech as a candidate research measure rather than a stand-alone diagnostic tool.
Key Questions
What is a speech age gap?
A speech age gap compares estimated speech age with chronological age. In this study, a positive gap meant the participant’s speech appeared older than their chronological age; it did not measure how quickly they were aging.
Which groups had the largest speech age gaps?
The largest gaps were reported in people with language-dominant frontotemporal dementia, followed by non-language-dominant frontotemporal dementia, Alzheimer’s disease and mild cognitive impairment.
Does this study show that speech can diagnose dementia?
No. The study found associations between speech age gaps and diagnoses or other measures in a research cohort. The reported findings do not establish that the method can diagnose dementia in an individual.
Did the speech measure track aging over time?
No. The analysis was cross-sectional, so it compared participants at a point in time. Longitudinal research would be needed to determine whether speech age gaps change as individuals age.
Where did the participants come from?
The 2,928 participants were Spanish-speaking members of the ReDLat consortium in Colombia, Chile, Argentina, Mexico and Peru.
Source: rss
Cold & flu season Picks
humidifiers
As an affiliate, we earn on qualifying purchases.
