[P1–295]: EARLY DETECTION OF COGNITIVE DISORDERS SUCH AS DEMENTIA ON THE BASIS OF SPEECH ANALYSIS: A CROSS‐LINGUISTIC COMPARISON OF SPEECH FEATURES
Bibliographic record
Abstract
The people best placed to spot early cognitive decline are carers, social workers, and family. But there is a clear lack of affordable, usable screening apps that people without medical training can use to validate these concerns and to provide actionable data for medical professionals. The study aims to validate a new tool for fully-automated, reliable, unobtrusive, self-managed screening for cognitive decline, in particular dementia, and other cognitive disorders based on automatic speech analysis. It will allow earlier detection and, through that, more effective interventions resulting in the reduction of overall costs associated with treatment and rehabilitation. For users it will offer the comfort of flexible usage without visiting professional physicians. At the moment there is an American English corpus of speech data used for training the algorithms of the system used by the tool for automatic detection of dementia in the USA and Canada. The main objective of the study will be the first experience in producing such corpus for another language, namely French. The corpus will contain ca. 250 samples of speech of patients with various levels of the syndrome, as well as other cognitive and behavioral disorders and ca. 50 samples of healthy people as a control group. All participants will be asked to perform a set of vocal tasks such as describing a series of images or perform verbal fluencies. Then, all speech samples will be transcribed and annotated by professional clinicians to make the corpus suitable for machine learning and identify which features transfer between languages. The processes, tools and experiences will be then presented in the blueprint for transferring the system into a new language. First results of the analysis and cross linguistic comparison of the speech features will be presented at the conference. The proposed solution may supplement neuropsychological assessment with sophisticated and unobtrusive natural biomarkers extracted from speech data that can be collected outside of medical consultations. It can provide rich information about cognitive and emotional characteristics and can be used to inform clinical judgment during consultations, saving time and money.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.017 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".