Home › Research › Cognitive tests and assessment
A 60-second interpretable voice model for early dementia screening
Kevin Mekulu, Faisal Aqlan, Hui Yong Yang. PLOS Digital Health, 2026-07-27
Topic: Risk, prevention and care in population studies
Abstract Early detection of cognitive impairment in assisted living is hindered by time-intensive tools like MMSE and MoCA. We present a 60-second voice-based screening model that analyzes picture descriptions to estimate dementia risk. Using transcripts from the DementiaBank corpus, our model integrates traditional linguistic features (pause rate, pronoun use, syntactic complexity) with latent semantic dimensions extracted from language model embeddings. These semantic axes, interpretable constructs like “Drift & Hesitation” or “Over-detailed Narration”, consistently emerged as top predictors and may represent novel linguistic biomarkers of early decline. The final ElasticNet classifier is sparse, interpretable, and outperforms known non–deep learning baselines (AUC = 0.858), exceeding MMSE. Its simplicity enables deployment in mobile apps or in-room monitors, offering scalable, low-burden screening for early dementia. This work supports a shift toward linguistically grounded, tech-enabled cognitive care in aging populations. Author summary Early-stage dementia often goes undetected in assisted living communities, where time constraints and staffing limitations make routine cognitive screening impractical. While standard tools like the MMSE and MoCA require trained administration and take 10–15 minutes, our research introduces a fast, interpretable alternative: a 60-second voice-based screening model using picture description tasks. We analyzed speech samples from individuals describing a common scene, extracting both traditional linguistic features (e.g., pauses, pronouns, sentence complexity) and deeper thematic patterns using modern language embeddings. Our model not only outperforms widely used tools in accuracy, but also reveals interpretable language patterns such as hesitation or over-description that may serve as early signs of cognitive decline. Lightweight and explainable, this approach is well suited for mobile apps or in-room monitors, enabling scalable, low-burden dementia screening in real-world care environments.
Key findings
- Author summary Early-stage dementia often goes undetected in assisted living communities, where time constraints and staffing limitations make routine cognitive screening impractical.
- While standard tools like the MMSE and MoCA require trained administration and take 10–15 minutes, our research introduces a fast, interpretable alternative: a 60-second voice-based screening model using picture description tasks.
- We analyzed speech samples from individuals describing a common scene, extracting both traditional linguistic features (e.g., pauses, pronouns, sentence complexity) and deeper thematic patterns using modern language embeddings.
- Our model not only outperforms widely used tools in accuracy, but also reveals interpretable language patterns such as hesitation or over-description that may serve as early signs of cognitive decline.
- Lightweight and explainable, this approach is well suited for mobile apps or in-room monitors, enabling scalable, low-burden dementia screening in real-world care environments.
Why it matters
This study describes a 60-second voice-based model using picture descriptions that estimated dementia risk with an AUC of 0.858, exceeding MMSE, and was designed to be simple enough for mobile apps or in-room monitors. It is a screening tool for early detection, not a treatment, cure, or prevention of Alzheimer's disease.
Study details
- Effect sizeAUC = 0.858
- Evidence strengthLow
How this study scored 38/100
Published in a peer-reviewed journal. Scored zero for study design, sample size, studied in people and randomised / blinded because the record does not state it.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (PLOS Digital Health) |
| Journal's citation record | 0 / 4 | PLOS Digital Health: journal h-index 54 (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 | 5 / 5 | 2026 — within 1 year(s) of the newest study here |
| Sample size | 0 / 4 | Participant count not stated — scores zero (not stated in the record — scored 0) |
| Effect reported | 3 / 3 | Effect reported with a statistic (interval, p-value, ratio or similar) |
| Studied in people | 0 / 3 | Not stated whether this was studied in people — scores zero (not stated in the record — scored 0) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 1 / 7 | Cited 3 times (OpenAlex, 2026-10-10) |
| Citations per year | 1 / 5 | 1.5 citations a year over 2 year(s) since 2026 |
| Impact for its field and year | 0 / 6 | Cited 0.0× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 1 / 6 | Cited by 1 other studies in this library |
| Still being cited | 1 / 4 | Cited 3 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | 2 / 4 | Last-listed author Hui Yong Yang: h-index 35 (OpenAlex, whole career) |
| Institution's track record | 1 / 3 | Pennsylvania State University: institution h-index 1,397 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 2 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 42507664) |
| Free to read | 2 / 2 | Free to read |
| Total | 38 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
- DOI: 10.1371/journal.pdig.0001552
- PubMed: 42507664
- Original source →
- Free full text: PLOS Digital Health →
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. Check the citation against the original before you use it.
APA 7th
Mekulu, K., Aqlan, F., & Yang, H. Y. (2026). A 60-second interpretable voice model for early dementia screening. PLOS Digital Health. https://doi.org/10.1371/journal.pdig.0001552
Vancouver
Mekulu K, Aqlan F, Yang HY. A 60-second interpretable voice model for early dementia screening. PLOS Digital Health. 2026. doi:10.1371/journal.pdig.0001552. PMID: 42507664.
BibTeX
@article{mekulu2026-42507664,
author = {Mekulu, Kevin and Aqlan, Faisal and Yang, Hui Yong},
title = {{A 60-second interpretable voice model for early dementia screening}},
journal = {PLOS Digital Health},
year = {2026},
doi = {10.1371/journal.pdig.0001552},
pmid = {42507664},
url = {https://doi.org/10.1371/journal.pdig.0001552}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Later studies that cite this one
1 study in the alzhub library lists this one in its references.
Related studies in Cognitive tests and assessment
Also tagged “prevalence”
1,224 studies in the library carry the topic tag “prevalence”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 1,224 tagged studies.