Speech clocks decode dementia phenotypes, social exposome, and biological aging

@article{hernandez2026speech,
  title = {{Speech clocks decode dementia phenotypes, social exposome, and biological aging}},
  author = {Hernan Hernandez and Lizeth Katherine Pedraza and Hernando Santamaria-Garcia and Sebastian Moguilner and Agustina Legaz and Pavel Prado and Jhosmary Cuadros and Lucía Amoruso and Liset Gonzalez and Damián Dellavale and Juan Pablo Espinoza–Puelles and Javier Palma Espinosa and Cecilia Jarne and Fabio Mattiussi and Matías Caccia and Alejandro Sosa Welford and Nicolás Pelella and Jeremías Inchauspe and Franco J. Ferrante and Gonzalo Pérez and Marcelo Adrián Maito and Guido Rocatti and Maria Eugenia Godoy and Joaquin Migeot and Paulina Orellana and Ariel Caviedes and Martin Bruno and Leonel Takada and Andrea Slachevsky and Maria I Behrens and Bárbara Bruna and David Aguillon and Lina Zapata and Jose Alberto Avila-Funes and Nilton Custodio and Bruce Miller and Maria Luisa Gorno-Tempini and Stefanie Pina Escudero and Pablo Reyes and Kun Hu and Maira Okada de Oliveira and Carlos Coronel-Oliveros and Josephine Cruzat and Juan Felipe Cardona and Michael Corley and Irene B. Meier and Vaibhav A. Narayan and Enzo Tagliazucchi and Sandra Baez and Claudia Duran-Aniotz and Adolfo M. García and Agustin Ibanez},
  journal = {Science Advances},
  year = {2026},
  month = oct,
  doi = {10.1126/sciadv.aef9864},
  url = {https://www.science.org/doi/10.1126/sciadv.aef9864},
  note = {CC BY},
}

TY  - JOUR
TI  - Speech clocks decode dementia phenotypes, social exposome, and biological aging
AU  - Hernan Hernandez
AU  - Lizeth Katherine Pedraza
AU  - Hernando Santamaria-Garcia
AU  - Sebastian Moguilner
AU  - Agustina Legaz
AU  - Pavel Prado
AU  - Jhosmary Cuadros
AU  - Lucía Amoruso
AU  - Liset Gonzalez
AU  - Damián Dellavale
AU  - Juan Pablo Espinoza–Puelles
AU  - Javier Palma Espinosa
AU  - Cecilia Jarne
AU  - Fabio Mattiussi
AU  - Matías Caccia
AU  - Alejandro Sosa Welford
AU  - Nicolás Pelella
AU  - Jeremías Inchauspe
AU  - Franco J. Ferrante
AU  - Gonzalo Pérez
AU  - Marcelo Adrián Maito
AU  - Guido Rocatti
AU  - Maria Eugenia Godoy
AU  - Joaquin Migeot
AU  - Paulina Orellana
AU  - Ariel Caviedes
AU  - Martin Bruno
AU  - Leonel Takada
AU  - Andrea Slachevsky
AU  - Maria I Behrens
AU  - Bárbara Bruna
AU  - David Aguillon
AU  - Lina Zapata
AU  - Jose Alberto Avila-Funes
AU  - Nilton Custodio
AU  - Bruce Miller
AU  - Maria Luisa Gorno-Tempini
AU  - Stefanie Pina Escudero
AU  - Pablo Reyes
AU  - Kun Hu
AU  - Maira Okada de Oliveira
AU  - Carlos Coronel-Oliveros
AU  - Josephine Cruzat
AU  - Juan Felipe Cardona
AU  - Michael Corley
AU  - Irene B. Meier
AU  - Vaibhav A. Narayan
AU  - Enzo Tagliazucchi
AU  - Sandra Baez
AU  - Claudia Duran-Aniotz
AU  - Adolfo M. García
AU  - Agustin Ibanez
PY  - 2026
DA  - 2026/10/02
JO  - Science Advances
DO  - 10.1126/sciadv.aef9864
UR  - https://www.science.org/doi/10.1126/sciadv.aef9864
AB  - 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.
SN  - 2375-2548
ER  -