Predicting Cognitive Impairment in Cerebrovascular Disease Using Spoken Discourse Production
Bibliographic record
Abstract
Purpose: Dementia due to cerebrovascular disease (CVD) is common. Detecting early cognitive decline in CVD is critical because addressing risk factors may slow or prevent dementia. This study used a multidomain discourse analysis approach to determine the spoken language signature of CVD-related cognitive impairment. Method: Spoken language and neuropsychological assessment data were collected prospectively from 157 participants with CVD as part of the Ontario Neurodegenerative Disease Research Initiative, a longitudinal, observational study of neurodegenerative disease. Participants were categorized as impaired (n = 92) or cognitively normal for age (n = 65) based on neuropsychology criteria. Spoken language samples were transcribed orthographically and annotated for 13 discourse features, across five domains. Discriminant function analyses were used to determine a minimum set of discourse variables, and their estimated weights, for maximizing diagnostic group separation. Results: The optimal discriminant function that included 10 of 13 discourse measures correctly classified 78.3% of original cases (69.4% cross-validated cases) with a sensitivity of 77.2% and specificity of 80.0%. Conclusion: Spoken discourse appears to be a sensitive measure for detecting cognitive impairment in CVD with measures of productivity, information content, and information efficiency heavily weighted in the final algorithm.
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 | 0.002 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".