COGNOSPEAK: a feasibility pilot study of automated speech analysis to aid cognitive assessment post stroke
Bibliographic record
Abstract
Background Stroke survivors (SSs) often experience cognitive decline following initial stroke, necessitating repeat cognitive assessments. Current methods of assessment, such as Montreal Cognitive Assessment (MoCA), are time-consuming and rely on health-care professionals. Addressing these challenges, we introduce Cognospeak. Methods CognoSpeak is used initially in the acute post-stroke within the hospital and subsequently at home. CognoSpeak assesses cognitive decline via a user interface using a virtual agent. SS answer questions and complete cognitive tests. CognoSpeak uses Artificial intelligence methods to extract and process speech, language, and interactional cues for cognitive decline. Barriers to automated cognitive assessment in SS are also explored. Results In a cohort of 55 SS, a best regression result (Normalized Root Mean Squared Error) of 0.092 was achieved for predicting MOCA score. Identifying cognitive impairment (MoCA score cutoff of < 26) yields a Specificity of 0.73, Sensitivity of 0.75. Demonstrating the first evidence of the system’s robustness in SS. Conclusions CognoSpeak can be used successfully in the acute stroke setting to predict cognitive scores of SS, highlighting its use in streamlining and improving post-stroke cognitive assessment. Challenges of automated assessment on the stroke pathway include patient computer access, anxiety in using information technology resources and post-stroke apathy.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.002 |
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".