An Aging Clock Built on Speech Analysis Data
Any sufficiently complex set of biological data that changes with age can be used as the basis for an aging clock. Well established machine learning techniques can identify patterns and find optimal correlations between algorithmic combinations of measurements taken from the data and outcomes of interest, such as age, mortality risk, risk of age-related disease, and so forth. For all that we are now many years into the development of aging clocks as a technology, it still remains to determine how best to use them to accelerate research and development of therapies to treat aging. In principle, a rapid measure of the state of aging should allow better progress towards rejuvenation therapies. In practice, it is impossible to trust that any given clock will react in the right way to efforts to treat aging, and the only sure way to find out is to run long and expensive life span studies. Until this core challenge is solved, clocks cannot add much to the pace of development.
Biological aging clocks offer estimations of aging and dementia, yet scalability is limited. We introduce a large-scale, cross-national speech clock derived from 2928 individuals across five Latin American countries, spanning healthy controls (HCs), mild cognitive impairment (MCI), Alzheimer's disease (AD), and non-language/language-dominant frontotemporal dementia (nldFTD/ldFTD). Multimodal acoustic and linguistic features were trained with supervised models to estimate chronological age, generating speech age gaps (SAGs) as cross-sectional markers of deviations from chronological age, with positive values interpreted as relatively older-appearing speech profiles.
SAGs differentiated diagnostic groups (HCs < patient groups, with AD < nldFTD < ldFTD). This pattern was associated with clinical/cognitive domains. SAGs correlated with phosphorylated tau (p-Tau217) in AD and social exposome in HCs and AD. Brain clocks (structural/functional/combined) were associated with SAG in AD, nldFTD, and ldFTD. Epigenetic age correlated with SAGs in HCs and AD across Hannum, Retroclock, and OMICmAge, whereas ldFTD associations were limited to Retroclock and OMICmAge. These results indicate that SAGs capture cross-sectional multilevel aging-related variation and may offer a scalable, culturally adaptable, low-cost biomarker candidate for research in underrepresented global settings.