Home › Research › Cognitive tests and assessment
Automated Speech Markers of Alzheimer Dementia: Test of Cross-Linguistic Generalizability
Paula Andrea Pérez-Toro, Franco Javier Ferrante, Gonzalo Nicolás Pérez, Boon Lead Tee, Jessica Deleon, Elmar Nöth, Maria Elke Schuster, Andreas Maier et al.. Journal of Medical Internet Research, 2025-10-15
Topic: Amyloid, tau and blood-test diagnosis
Plain-language summary
In the within-language condition, combined speech timing and lexico-semantic features yielded maximal classification (area under the receiver operating characteristic curve [AUC]=0.88), outperforming single-feature models (AUC=0.79 for timing features; AUC=0.80 for lexico-semantic features). Timing features showed the strongest MMSE prediction (R=0.43, P<.001). In the between-language condition, speech timing features generalized well to Spanish speakers (AUC=0.75) and predicted Spanish-speaking patients' MMSE scores (R=0.39, P<.001). Lexico-semantic features showed lower performance (AUC=0.64) and no significant MMSE prediction (R=-0.31, P=.05). The combined model did not improve results (AUC=0.65; R=0.04, P=.79). These results suggest that while both timing and lexico-semantic features are informative within the same language, only speech timing features demonstrate consistent performance across languages. By focusing on clinically interpretable features, this approach supports the development of clinically usable ASLA tools.
What this study adds
Evidence grade: Low
The record lists 211 participants. This study tested automated speech analysis for distinguishing Alzheimer dementia and found that speech timing features worked well within one language and also generalized to Spanish speakers, while lexico-semantic features performed less well across languages. Reported effect size: AUC=0.79; AUC=0.80; AUC=0.75.
Taken from this record’s own fields, not from reading the paper. The grade is assigned from the abstract’s wording; what that means.
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
APA 7th
Pérez-Toro, P. A., Ferrante, F. J., Pérez, G. N., Tee, B. L., Deleon, J., Nöth, E., et al. (2025). Automated Speech Markers of Alzheimer Dementia: Test of Cross-Linguistic Generalizability. Journal of Medical Internet Research. https://doi.org/10.2196/74200
Vancouver
Pérez-Toro PA, Ferrante FJ, Pérez GN, Tee BL, Deleon J, Nöth E, et al. Automated Speech Markers of Alzheimer Dementia: Test of Cross-Linguistic Generalizability. Journal of Medical Internet Research. 2025. doi:10.2196/74200. PMID: 41091545.
BibTeX
@article{pereztoro2025-41091545,
author = {Pérez-Toro, Paula Andrea and Ferrante, Franco Javier and Pérez, Gonzalo Nicolás and Tee, Boon Lead and Deleon, Jessica and Nöth, Elmar and Schuster, Maria Elke and Maier, Andreas and others},
title = {{Automated Speech Markers of Alzheimer Dementia: Test of Cross-Linguistic Generalizability}},
journal = {Journal of Medical Internet Research},
year = {2025},
doi = {10.2196/74200},
pmid = {41091545},
url = {https://doi.org/10.2196/74200}
}
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
Key findings
- In the within-language condition, combined speech timing and lexico-semantic features yielded maximal classification (area under the receiver operating characteristic curve [AUC]=0.88), outperforming single-feature models (AUC=0.79 for timing features; AUC=0.80 for lexico-semantic features).
- Timing features showed the strongest MMSE prediction (R=0.43, P<.001).
- In the between-language condition, speech timing features generalized well to Spanish speakers (AUC=0.75) and predicted Spanish-speaking patients' MMSE scores (R=0.39, P<.001).
- Lexico-semantic features showed lower performance (AUC=0.64) and no significant MMSE prediction (R=-0.31, P=.05).
- The combined model did not improve results (AUC=0.65; R=0.04, P=.79).
Why it matters
This study tested automated speech analysis for distinguishing Alzheimer dementia and found that speech timing features worked well within one language and also generalized to Spanish speakers, while lexico-semantic features performed less well across languages. The authors say this supports developing clinically usable automated speech and language analysis tools, but it is a marker study, not a treatment or cure.
Study details
- Participants211
- Effect sizeAUC=0.79; AUC=0.80; AUC=0.75
- Evidence strengthLow
How this study scored 52/100
Published in a peer-reviewed journal. Scored zero for study design and randomized / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Journal of Medical Internet Research) |
| Journal's citation record | 3 / 4 | Journal of Medical Internet Research: journal h-index 286 (OpenAlex, 2026-10-29) |
| Study design | 0 / 12 | No study design recorded — scores zero, not guessed (not stated in the record — scored 0) |
| Strength of evidence | 1 / 5 | Rated “low” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 4 / 5 | 2025 — within 3 year(s) of the newest study here |
| Sample size | 2 / 4 | 211 participants |
| Effect reported | 3 / 3 | Effect reported with a statistic (interval, p-value, ratio or similar) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomized / blinded | 0 / 2 | No randomization or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 2 / 7 | Cited 6 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 2.0 citations a year over 3 year(s) since 2025 |
| Impact for its field and year | 3 / 6 | Cited 3.8× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 1 / 4 | Cited 6 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 3 / 4 | Last-listed author Adolfo M. García: h-index 55 (OpenAlex, whole career) |
| Institution's track record | 2 / 3 | Massachusetts General Hospital: institution h-index 2,057 (OpenAlex) |
| Multicenter collaboration | 3 / 3 | OpenAlex lists 15 institution(s) in 6 countries |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41091545) |
| Free to read | 2 / 2 | Free to read |
| Total | 52 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.2196/74200
- PubMed: 41091545
- Original source →
- Free full text: Journal of Medical Internet Research →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Related
Studies in the library that share something with this one. The line above each title says what.
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Related studies in Cognitive tests and assessment from nearby years
Also tagged “machine”
834 studies in the library carry the topic tag “machine”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 834 tagged studies.