Comparing longitudinal changes in speech‐based digital measures in cognitively healthy, possible cognitive impairment, and MCI/AD individuals
Bibliographic record
Abstract
Abstract Background In Alzheimer’s disease (AD), changes to speech and language differentiate individuals with AD from healthy controls and may be detectable years prior to clinical diagnosis. Speech‐based digital biomarkers are objective, naturalistic measures, which could detect early signs of mild cognitive impairment (MCI) and AD and track disease progression. The objective of this study was to compare speech‐based digital measures across older adults who were cognitively healthy, had possible cognitive impairment based on cognitive screening measures, or had diagnoses of MCI or AD. Method 103 community‐dwelling older adults and 27 individuals with MCI or AD were recruited for this study in North America. Participants completed a tablet‐based speech assessment at Baseline and 6 month timepoints. Verbal responses were recorded, transcribed and analyzed to produce 8 composite measures pertaining to different aspects of speech and language. Participants were divided into a cognitively healthy group (>25 on the MoCA at baseline and at 6‐months), a possible cognitive impairment group (≤25 at both timepoints), and the MCI/AD group. Two‐way mixed ANOVAs were used to compare language scores across groups and assess change over time. Result There was a significant effect of group on five of the eight language composite scores: information units, local and global coherence, word finding difficulty and syntactic complexity, with the cognitively healthy group performing the best in all cases. There were significant overall declines in information units, global coherence and discourse mapping over the 6‐month period, but the interactions of time and group did not reach significance. Phonemic and semantic fluency scores also had significant main effects of group and significant declines over time. MoCA scores did not change over 6 months. Conclusion This study demonstrates that speech‐based biomarkers are sensitive to detect differences in individuals based on cognitive status and MCI/AD diagnosis. A number of these measures declined over a 6 month period, unlike MoCA scores, but the rate of change did not differ significantly across groups. Ongoing work with larger samples and longer study periods will continue to examine which aspects of speech and language are most sensitive to cognitive status and disease progression and validate novel digital biomarkers.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".