A univariate and network analysis approach to studying connected speech in Subjective Cognitive Decline
Bibliographic record
Abstract
BACKGROUND: Widespread Connected Speech (CS) changes (e.g., slower speech rate, more word repetitions, lower lexical diversity, reduced syntactic complexity) have been documented in Mild Cognitive Impairment (MCI). Nevertheless, the CS profile of individuals with Subjective Cognitive Decline (SCD; who are often considered to be at an even earlier stage of Alzheimer's disease (AD)), potential relationships between CS features in SCD, and how CS samples produced by individuals with SCD compare to those produced by controls and individuals with MCI remain unclear. The aim of this study was to compare the CS features and relationships between these features in SCD to those of controls and individuals with MCI. METHOD: Thirty CS features, part of all CS domains (e.g., fluency (e.g., filled pauses), lexical (e.g., word frequency), syntactic (e.g., subordinate clauses)) were extracted using Natural Language Processing techniques from the CS samples of 156 controls, 109 individuals with SCD, and 239 individuals with MCI. Groups were compared using ANCOVA models on the extracted CS features. Gaussian Graphical Models were then used to construct a CS network for each group with the CS features. RESULT: The ANCOVA analyses showed an increased speech rate (versus controls and individuals with MCI) and a lower local coherence (versus controls) in SCD. Moreover, our network analysis revealed increased (e.g., proportion of nouns, semantic idea density), decreased (e.g., proportions of pronouns and verbs), or intermediate (e.g., word valence) standardized node strength centralities in the SCD network compared to the Control and MCI networks. Examination of prominent edges in the SCD network revealed a similar pattern, with some increased (e.g., word frequency - noun valence), decreased (e.g., number of words - efficiency), and intermediate weights (e.g., word frequency - noun frequency) compared to the other networks. CONCLUSION: Our results suggest subtle CS changes in SCD, mainly in the lexical and semantic domains. Furthermore, our network analysis demonstrates that SCD represents an intermediate stage between healthy aging and MCI. Finally, we show that network analysis helps gain a different and more in-depth understanding of CS in the early stages of the AD continuum.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.004 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".