Benchmarking speech biomarkers of Alzheimer’s against cognitive and neural measures

Caro, I., Pérez, G., Valdés Bize, J., Ponferrada, J., Ferrante, F. J., Sosa Welford, A., Gauder, L., Olavarría, L., Henríquez, F., Ramos, T., Besnier, C., Ferrer, L., Gorno-Tempini, M. L., Slachevsky, A., Ibañez, A. & García, A. M. (2026). Benchmarking speech biomarkers of Alzheimer’s against cognitive and neural measures. Alzheimer’s & Dementia 22, e71365.

Introducción: Los biomarcadores del habla digital (BAD) facilitan la detección y el seguimiento de la enfermedad de Alzheimer (EA) en la población latina. Sin embargo, aún no se han comparado con medidas cognitivas y de neuroimagen estándar, por lo que falta un hito fundamental en su validación.

Methods: Thirty-three AD patients and 33 healthy controls completed verbal fluency tasks, episodic memory and executive tests, and magnetic resonance imaging (MRI) (volume) and functional MRI (fMRI) (connectivity) scans. Between-group machine learning classification was compared among fluency-derived DSBs, episodic and executive test scores, MRI, and fMRI measures.

Métodos: 33 pacientes con EA y 33 sujetos sanos del grupo de control realizaron pruebas de fluencia verbal, de memoria episódica y de funciones ejecutivas, y se les realizaron exploraciones por resonancia magnética (RM) (volumen) y resonancia magnética funcional (RMf) (conectividad). Se comparó la clasificación mediante aprendizaje automático entre grupos a partir de los DSB derivados de la fluencia, las puntuaciones de las pruebas de memoria episódica y de funciones ejecutivas, y las medidas de RM y RMf.
Discusión: Los BAD parecen no ser inferiores a las medidas cognitivas y de imagen estándar, lo que respalda la viabilidad de evaluaciones escalables de la EA en la población latina.

Para acceder al artículo, hacé click aquí.

Benchmarking speech biomarkers of Alzheimer’s against cognitive and neural measures

Caro, I., Pérez, G., Valdés Bize, J., Ponferrada, J., Ferrante, F. J., Sosa Welford, A., Gauder, L., Olavarría, L., Henríquez, F., Ramos, T., Besnier, C., Ferrer, L., Gorno-Tempini, M. L., Slachevsky, A., Ibañez, A. & García, A. M. (2026). Benchmarking speech biomarkers of Alzheimer’s against cognitive and neural measures. Alzheimer’s & Dementia 22, e71365.

Introduction: Digital speech biomarkers (DSBs) support the detection and monitoring of Alzheimer’s disease (AD) in Latinos. However, they have not been benchmarked against standard cognitive and neuroimaging measures, missing a critical validation milestone.

Methods: Thirty-three AD patients and 33 healthy controls completed verbal fluency tasks, episodic memory and executive tests, and magnetic resonance imaging (MRI) (volume) and functional MRI (fMRI) (connectivity) scans. Between-group machine learning classification was compared among fluency-derived DSBs, episodic and executive test scores, MRI, and fMRI measures.

Results: The fluency classifier’s performance (area under the curve [AUC] = 0.84) was comparable (p > 0.14) to the episodic (AUC = 0.90), executive (AUC = 0.79), and structural (AUC = 0.90) classifiers and superior to the functional classifier (AUC = 0.65, p = 0.002). Top discriminating features were word length and frequency, both associated with right (pre)frontal volume upon adjusting for sociodemographic factors.

Discussion: DSBs appear non-inferior to standard cognitive and imaging measures, supporting scalable AD assessments in Latinos.

To access the full paper, please click here.