Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Sep;107(1):154-169.
doi: 10.1177/13872877251359967. Epub 2025 Jul 20.

Associations between digital speech features of automated cognitive tasks and trajectories of brain atrophy and cognitive decline in early Alzheimer's disease

Qingyue Li  1 , Stefanie Koehler  2 , Alexandra Koenig  3   4 , Martin Dyrba  2 , Elisa Mallik  4 , Nicklas Linz  4 , Josef Priller  5   6   7   8 , Eike Spruth  5   6 , Slawek Altenstein  5   6 , Jens Wiltfang  9   10   11 , Inga Zerr  9   12 , Claudia Bartels  10 , Franziska Maier  13 , Ayda Rostamzadeh  13 , Emrah Duezel  14   15 , Wenzel Glanz  14   15 , Enise I Incesoy  14 , Michaela Butryn  14   15 , Christoph Laske  16   17 , Sebastian Sodenkamp  16   18 , Matthias Hj Munk  16   18 , Bjoern Falkenburger  19   20 , Antje Osterrath  19   20 , Ingo Kilimann  1   2 , Melina Stark  21   22 , Luca Kleineidam  21   22 , Michael T Heneka  23 , Annika Spottke  21   24 , Michael Wagner  21   22 , Frank Jessen  13   21   25 , Gabor C Petzold  21   26 , Fedor Levin  2 , Stefan Teipel  1   2
Affiliations

Associations between digital speech features of automated cognitive tasks and trajectories of brain atrophy and cognitive decline in early Alzheimer's disease

Qingyue Li et al. J Alzheimers Dis. 2025 Sep.

Abstract

BackgroundSpeech-based features extracted from telephone-based cognitive tasks show promise for detecting cognitive decline in prodromal and manifest dementia. Little is known about the cerebral underpinnings of these speech features.ObjectiveTo examine associations between speech features, brain atrophy, and longitudinal cognitive decline in individuals at risk for Alzheimer's disease (AD).MethodsHealthy volunteers, individuals with subjective cognitive decline, and those with mild cognitive impairment completed phonebot-guided semantic verbal fluency (SVF) and 15-word verbal learning task (VLT). Speech features were automatically extracted, and a global cognitive score (SB-C score) was computed. We analyzed data from 161 participants for cognitive trajectories, 141 for cross-sectional brain atrophy, and 102 for longitudinal brain changes. Analyses were conducted using multiple linear regressions, mixed-effects models, and voxel-based morphometry.ResultsThe SB-C score was associated with bilateral hippocampal volumes, SVF features were primarily associated with left hemisphere regions, including the inferior frontal, parahippocampal, and superior/middle temporal gyri (puncorr < 0.001). SB-C score, SVF correct counts, and VLT delayed recall were associated with atrophy rates in the hippocampal/parahippocampal gyrus and left middle/inferior temporal gyri (pFDR < 0.05). These features were also associated with cognitive decline assessed via Preclinical Alzheimer's Cognitive Composite 5, SVF, and Wordlist learning delayed recall (pFDR < 0.01). Word frequency and temporal cluster switches showed varying associations with cognitive trajectories. Other features did not show robust associations.ConclusionsIn this study, we highlight the potential of digital speech features for identifying brain atrophy and cognitive decline over time in at-risk AD populations.

Keywords: Alzheimer's disease; atrophy; cognition; cognitive decline; early diagnosis; natural language processing; speech.

PubMed Disclaimer

Conflict of interest statement

Declaration of conflicting interestsThe authors declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: Stefanie Koehler has received funding from the Alzheimer Drug Discovery Foundation and Lilly Deutschland GmbH, as well as lecture fees from Eisai. Martin Dyrba has received research funding from the Deutsche Forschungsgemeinschaft and lecture fees from Europäische Fernhochschule Hamburg GmbH. Alexandra Koenig, Nicklas Linz, and Elisa Mallick are employed by the company ki: elements, which developed the application for the automatic phone assessment and calculated the speech biomarkers. Nicklas Linz owns shares in the ki: elements company. Claudia Bartels received funding from the German Alzheimer's Association and lecture fees from Lilly, Boehringer Ingelheim, and Eisai. Franziska Maier participated in scientific advisory boards of Lilly and Johnson & Johnson, and received lecture fees from Novo Nordisk. Jens Wiltfang has received funding from the BMBF, consulting fees from Immunogenetics, Noselab, Roboscreen, and lecture fees from Beijing Yibai Science and Technology Ltd, Gloryren, Janssen Cilag, Pfizer, Med Update GmbH, Roche Pharma, and Lilly. Jens Wiltfang participated in a Data Safety Monitoring Board or Advisory Board of Biogen, Abbott, Boehringer Ingelheim, Lilly, MSD Sharp & Dohme, and Roche. Bjoern Falkenburger has received funding from the Deutsche Forschungsgemeinschaft. Ingo Kilimann has received an unrestricted research grant from Lilly Germany. Stefan Teipel participated in scientific advisory boards of Roche Pharma AG, Biogen, Lilly, and Eisai, and received lecture fees from Lilly and Eisai. Stefan Teipel is a senior editor in 2025, Alexandra Koenig, Inga Zerr, and Ayda Rostamzadeh are editorial Board members, but were not involved in the peer-review process of this article, nor had access to any information regarding its peer review. The other authors declared no potential conflicts of interest concerning the research, authorship, and/or publication of this article.

Figures

Figure 1.
Figure 1.
Data overview of the ongoing prospect-AD study.
Figure 2.
Figure 2.
VBM-based associations between digital speech features and regional GM volumes.
Figure 3.
Figure 3.
ROI-based associations between regional brain atrophy rate and SB-C cognition score.
Figure 4.
Figure 4.
Associations between longitudinal cognitive trajectories via traditional neurocognitive assessments and digital speech features.
See this image and copyright information in PMC

References

    1. Vigo I, Coelho L, Reis S. Speech- and language-based classification of Alzheimer’s disease: a systematic review. Bioengineering (Basel) 2022; 9: 27. - PMC - PubMed
    1. Taler V, Phillips NA. Language performance in Alzheimer’s disease and mild cognitive impairment: a comparative review. J Clin Exp Neuropsychol 2008; 30: 501–556. - PubMed
    1. Pastoriza-Domínguez P, Torre IG, Diéguez-Vide F, et al. Speech pause distribution as an early marker for Alzheimer’s disease. Speech Commun 2022; 136: 107–117.
    1. Vita MG, Marra C, Spinelli P, et al. Typicality of words produced on a semantic fluency task in amnesic mild cognitive impairment: linguistic analysis and risk of conversion to dementia. J Alzheimers Dis 2014; 42: 1171–1178. - PubMed
    1. Verfaillie SCJ, Witteman J, Slot RER, et al. High amyloid burden is associated with fewer specific words during spontaneous speech in individuals with subjective cognitive decline. Neuropsychologia 2019; 131: 184–192. - PubMed

MeSH terms

LinkOut - more resources