Automatic speech analysis for the assessment of patients with predementia and Alzheimer's disease
Open accessAbstract
Background: To evaluate the interest of using automatic speech analyses for the assessment of mild cognitive impairment (MCI) and early‐stage Alzheimer's disease (AD). Methods: Healthy elderly control (HC) subjects and patients with MCI or AD were recorded while performing several short cognitive vocal tasks. The voice recordings were processed, and the first vocal markers were extracted using speech signal processing techniques. Second, the vocal markers were tested to assess their “power” to distinguish among HC, MCI, and AD. The second step included training automatic classifiers for detecting MCI and AD, using machine learning methods and testing the detection accuracy. Results: The classification accuracy of automatic audio analyses were as follows: between HCs and those with MCI, 79% ± 5%; between HCs and those with AD, 87% ± 3%; and between those with MCI and those with AD, 80% ± 5%, demonstrating its assessment utility. Conclusion: Automatic speech analyses could be an additional objective assessment tool for elderly with cognitive decline.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Konig et al. (2015) achieved 80% accuracy in differentiating MCI and AD, 87% between AD and healthy controls, and 79% between MCI and healthy controls using four short vocal tasks.
“The method showed an accuracy of 80% in differentiating people suffering from MCI and AD, 87% between AD and HC and 79% between MCI and HC [133].”
From Recent Advancements in Pathogenesis, Diagnostics and Treatment of Alzheimer’s Disease (2020) · cites this paper as [133]
Clinically relevant metrics such as AUC and EER are reported in less than half of the reviewed studies.
“Clinically relevant metrics such as AUC and EER (e.g., [61, 102]), which summarize the rates of false alarms and false negatives, are reported in less than half of the reviewed studies.”
From Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review (2020) · cites this paper as [102]
The remaining studies work on disease progression by including SCI participants, predicting within-subject change, or discriminating between HC, MCI, and AD stages.
“The remaining studies work on disease progression by including SCI participants [59], predicting within-subject change [68] or discriminating between HC, MCI, and AD stages (e.g., [102]).”
From Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review (2020) · cites this paper as [102]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 55 · Cited by 380
Research works printed but not linked: 1
- [37]Roark B. Automatically derived spoken language markers for detecting mild cognitive impairment. Presented at the Second International Conference on Technology and Aging (ICTA), Toronto, Canada, 2007.
- Authors
- König, A., Satt, A., Sorin, A., Hoory, R., Toledo‐Ronen, O., Derreumaux, A., Manera, V., Verhey, F., Aalten, P., Robert, P. H., & David, R.
- Affiliations
- Maastricht University Medical Centre (NL)
- IBM Research - Haifa (IL)
- Speech Technologies IBM Research Haifa Israel
- Cognition Behaviour Technology (FR)
- Research Unit CoBTeK ‐ Cognition Behaviour Technology Edmond & Lily Safra Research Center, University of Nice Sophia Antipolis Nice France
- Centre Hospitalier Universitaire de Nice (FR)
- Corresponding author
- König, Alexandra
- Venue
- Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
- Publisher
- Wiley
- Published
- 2015-03
- Volume
- 1
- Issue
- 1
- Pages
- 112-124
- ISSN
- 2352-8729 (ISSN-L)
- PMC
- PMC4876915
- OpenAlex
- W2089109585
- Cited by
- 380
- References
- 55
- Citations by year
- 2026: 29 · 2025: 34 · 2024: 23 · 2023: 52 · 2022: 49 · 2021: 60 · 2020: 51 · 2019: 31 · 2018: 20 · 2017: 18 · 2016: 9 · 2015: 2 · 2014: 1
- FWCI
- 13.24
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring (publishedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Université Nice Sophia Antipolis
- Canadian Institute of Ukranian Studies, University of Alberta
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Physiology › Voice and Speech Disorders
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Keywords
- automated speech analysis, mild cognitive impairment, Alzheimer's disease, pre-dementia, early detection, speech processing, cognitive decline, older adults
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
