Connected speech assessment in the early detection of Alzheimer’s disease and mild cognitive impairment: a scoping review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Background: Connected speech (CS) deterioration appears early in the progression to Alzheimer’s disease (AD) and in mild cognitive impairment (MCI). As such, CS assessment may prove a quick, clinical speech tool and contribute to the early detection of subtle, yet significant speech changes pointing to pathological cognitive ageing.Aims: We performed a scoping review to extensively map the methodology used to assess CS in AD and MCI populations in the literature.Methods & Procedures:Outcomes & Results: The scoping review revealed the majority of articles on CS in AD and MCI populations studied relatively small samples of English-speaking patients, most of which were in the early to moderate stages of AD and relied mostly on descriptive methods (namely, single-picture description tasks) and manual analysis to collect and analyse CS data. The review also highlighted the diversity of outcome measures of CS studied, with semantic and fluency outcome measures being most common across included articles, and a synthesis of the key findings revealed these outcomes measures to be most relevant in identifying early changes to CS in pathological ageing.Conclusions: This scoping review identifies a considerable heterogeneity across articles on the assessment of CS in AD and MCI, in terms of populations (sample size, disease severity, diagnosis criteria used, etc.) and methods (tasks used to assess CS, outcome measures of interest, etc.). It also provides recommendations for future research on CS and highlights the potential of interesting research avenues, such as unstructured tasks and automatic speech analysis to obtain and analyse CS data.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it