Benchmarking speech biomarkers of Alzheimer's against cognitive and neural measures
Year: 2026
Type: article
Study design: Observational Study
Abstract: 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. HIGHLIGHTS: We examined digital speech biomarkers (DSBs) for detecting AD in Latinos. DSBs were benchmarked against cognitive and neuroimaging features. DSB-based classifiers matched or outperformed cognitive and brain classifiers. Top DSBs included word length, phonological neighborhood, and frequency. Word length and frequency correlated with right (pre)frontal brain volume.
Source: Alzheimer s & Dementia
DOI: 10.1002/alz.71365
Institutions: Consejo Nacional de Investigaciones Científicas y Técnicas, University of San Andrés, Universidad de Buenos Aires, Pontificia Universidad Católica de Chile, Clínica Las Condes, Hospital del Salvador, University of Chile, University of California, San Francisco, Universidad del Desarrollo, Clínica Alemana, Trinity College Dublin, Adolfo Ibáñez University, Istanbul Medipol University, Global Brain Health Institute, Universidad de Santiago de Chile
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: hybrid
Estimated APC paid: $4,200
Funders: Alzheimer's Association, Wellcome Trust, EU Joint Programme – Neurodegenerative Disease Research, Global Brain Health Institute, Rainwater Charitable Foundation, Agencia Nacional de Investigación y Desarrollo, National Institutes of Health, Tau Consortium, Agencia Nacional de Promoción Científica y Tecnológica, National Institute on Aging, Fogarty International Center, Fondo de Fomento al Desarrollo Científico y Tecnológico, Fondo de Financiamiento de Centros de Investigación en Áreas Prioritarias, H2020 Marie Skłodowska-Curie Actions
Awards: G103627852, G1581799926, G2118524674, G2363475639, MACHINE LEARNING FOR MENTAL HEALTH NEW DEVELOPMENTS AND APPLICATIONS USING MULTIMODAL DATA, G2822108074, BIOLOGIC EMBEDDING OF SOCIAL INEQUALITY AND LIFESTYLE IN AGING AND DEMENTIA, G294783571, G3628792472, CENTRO DE GEROCIENCIA SALUD MENTAL Y METABOLISMO (GERO), DIGITAL SPEECH AND LANGUAGE MARKERS OF EXTRASYLVIAN DYSFUNCTION IN NEURODEGENERATION, G4763556303, G4791335856, G4893384363, G5163463781, MACHINE LEARNING PARA EL DIAGNOSTICO PRECOZ Y PERFIL MULTIMODAL DE LA ENFERMEDAD DE ALZHEIMER BASADO EN MIRNA DE EXOSOMAS CIRCULANTES., G5881588278, G6619092739, G6838293017, G751033835, G7616641907, MAPPING AND MODELING THE HEALTHY AND PATHOLOGICAL AGING TRAJECTORIES OF THE HUMAN BRAIN, G883642430, G8845046930, US-South American Initiative for Genetic-Neural-Behavioral Interactions in Human Neurodegenerative Research, DATA-DRIVEN ASSESSMENT OF EVERYDAY FUNCTIONING IN DEMENTIA AN INTEGRATIVE APPROACH OF CLINICAL AND NEURAL PHENOTYPES, Frontotemporal Dementia: Genes, Images, and Emotions, An automated machine learning approach to language changes in Alzheimer’s disease and frontotemporal dementia across Latino and English-speaking populations, Circadian Disturbance and Dementia in Latin America
OpenAlex ID: W7154239291