Listening for Alzheimer’s clues: machine learning analysis of multidomain speech features for cognitive impairment screening
File(s)
Published version
Author(s)
Blazquez-Folch, Josep
Calm, Berta
Hinojosa-Calleja, Adrián
García-Gutiérrez, Fernando
Alegret, Montserrat
Type
Journal Article
Abstract
Introduction: Early detection of Alzheimer’s disease (AD) is critical for timely intervention, particularly during the mild cognitive impairment (MCI) stage. This study aimed to develop and evaluate a multidomain speech analysis framework to support cognitive screening, biomarker prediction within the amyloid, tau and neurodegeneration (ATN) framework, and estimation of cognitive function across the AD continuum.
Methods: This study analyzed speech from 2,320 individuals spanning the cognitive spectrum-including those with subjective cognitive decline (SCD), MCI, and Alzheimer’s disease dementia (ADD)-using three spoken tasks (∼3 min) and extracted multidomain features including acoustic, lexical, syntactic, and semantic features. Machine learning models were trained to classify cognitive status, predict amyloid, tau and neurodegeneration (ATN) biomarker positivity, and estimate scores across six neuropsychological domains.
Results: Multidomain speech models achieved high performance in differentiating cognitive stages, with AUC values of up to 0.94 for SCD vs. ADD and 0.82 for SCD vs. MCI classifications. In biomarker prediction, the models yielded AUCs of 0.71, 0.74, and 0.73 for ATN classification, respectively. Speech-based models also showed strong correlations (up to 0.83) with cognitive function scores. Feature importance analysis revealed that verbal fluency measures were the most predictive. Explainability analyses indicated minimal dependency on age, sex, or education, supporting model fairness.
Discussion: These findings show that multidomain speech features capture clinically and biologically relevant information across the AD continuum, enabling cognitive classification, biomarker prediction, and cognitive estimation. These results underscore the potential of speech analysis as a non-invasive, accessible tool for scalable cognitive screening and early detection of AD. These results underscore the potential of speech analysis as a non-invasive, accessible tool for scalable cognitive screening and early detection of AD.
Methods: This study analyzed speech from 2,320 individuals spanning the cognitive spectrum-including those with subjective cognitive decline (SCD), MCI, and Alzheimer’s disease dementia (ADD)-using three spoken tasks (∼3 min) and extracted multidomain features including acoustic, lexical, syntactic, and semantic features. Machine learning models were trained to classify cognitive status, predict amyloid, tau and neurodegeneration (ATN) biomarker positivity, and estimate scores across six neuropsychological domains.
Results: Multidomain speech models achieved high performance in differentiating cognitive stages, with AUC values of up to 0.94 for SCD vs. ADD and 0.82 for SCD vs. MCI classifications. In biomarker prediction, the models yielded AUCs of 0.71, 0.74, and 0.73 for ATN classification, respectively. Speech-based models also showed strong correlations (up to 0.83) with cognitive function scores. Feature importance analysis revealed that verbal fluency measures were the most predictive. Explainability analyses indicated minimal dependency on age, sex, or education, supporting model fairness.
Discussion: These findings show that multidomain speech features capture clinically and biologically relevant information across the AD continuum, enabling cognitive classification, biomarker prediction, and cognitive estimation. These results underscore the potential of speech analysis as a non-invasive, accessible tool for scalable cognitive screening and early detection of AD. These results underscore the potential of speech analysis as a non-invasive, accessible tool for scalable cognitive screening and early detection of AD.
Date Issued
2026-05-04
Date Acceptance
2026-04-07
Citation
Frontiers in Aging Neuroscience, 2026, 18
ISSN
1663-4365
Publisher
Frontiers Media S.A.
Journal / Book Title
Frontiers in Aging Neuroscience
Volume
18
Copyright Statement
© 2026 Blazquez-Folch, Calm, Hinojosa-Calleja, García-Gutiérrez, Alegret, Muñoz, Cano, Fernández, Miguel, Solivar, De Rojas, Valenzuela-Seba, García-González, Puerta, Olivé, Capdevila-Bayo, Muñoz-Morales, Bayón-Buján, Montrreal, Orellana, Ortega, Sanz-Cartagena, Rosende-Roca, Cantero-Fortiz, Gurruchaga, Tarraga, Butler, Montalban, Boada, Ruiz, Marquié and Valero. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/42157856
Subjects
Alzheimer’s disease
cerebrospinal fluid
early diagnosis
machine learning
mild cognitive impairment
neuropsychological tests
screening
Publication Status
Published
Coverage Spatial
Switzerland
Article Number
1816747
Date Publish Online
2026-05-04