Predicting brain health in older adults through automated language measures
Bibliographic record
Abstract
Abstract Background With increasing life expectancy, aging‐related neurocognitive challenges are becoming more prevalent worldwide. A continuum of severity, from subjective cognitive decline (SCD) to mild cognitive impairment (MCI) and Alzheimer's disease dementia (ADD), is measurable through cognitive and neuroimaging assessments. However, these approaches are costly, subject to scheduling delays, and reliant on specialized personnel or resources, which are scarce in many regions. Automated speech and language analysis (ASLA) offers an affordable, scalable solution for detecting neurocognitive compromise in underserved areas. Yet, no prior study has employed ASLA to predict neuropsychological and brain measures across this continuum in Spanish‐speaking Latinos. Our study addresses this gap. Method We recruited 150 Chilean individuals with diverse cognitive profiles: 17 healthy controls, 55 with SCD, 57 with MCI, and 21 with ADD. Participants completed 1‐minute phonemic and semantic fluency tasks, alongside cognitive (Addenbrooke's Cognitive Examination‐III [ACE‐III], Montreal Cognitive Assessment [MoCA]) and executive function (INECO Frontal Screening [IFS]) tests and MRI scans. Machine learning models were trained with word‐property and speech‐timing features from fluency responses (both separate and combined), derived via the TELL app, to predict cognitive test outcomes, total gray matter (GM) and white matter volumes, hippocampal GM volume, and a mask encompassing ADD‐sensitive regions. The best regressors were selected based on the 95% confidence intervals of R 2 scores. Pearson's partial correlations between actual and predicted values were computed, controlling for age, sex, and education (and MoCA scores for brain‐related measures). Analyses were repeated for each fluency task, their combination, and their average. Results Significant partial Pearson correlations were obtained for ACE‐III ( r = .55, p < .001), MoCA ( r = .39, p < .001), and IFS ( r = .31, p = .001) scores, as well as for normalized GM volume ( r = .34, p = .006). All results correspond to word‐property features, with combined fluency tasks. Conclusion A fully automated, multivariate pipeline captures cognitive and MRI measures of brain health based on brief fluency tasks. Unlike gold‐standard tests, this approach is examiner‐independent, objective, time‐efficient, and affordable. This approach represents a scalable resource to favor equity in the global fight against dementia and cognitive decline.
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) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| 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".