Linguistic clusters in scoring semantic verbal fluency task in patients with pre‐dementia cognitive decline
Bibliographic record
Abstract
Abstract Background Previous works have shown that qualitative language characteristics of verbal fluency task may be useful in differentiating between different neurodegenerative states, such as: variants of frontotemporal dementia or primary progressive aphasia. There is only limited data on how qualitative parameters of verbal fluency are associated with pre‐dementia states, such as subjective cognitive decline (SCD) and mild cognitive impairment (MCI). Method Semantic verbal fluency (SVF) task was given to 40 patients with SCD (median age 72 years, 39 females) and 51 MCI patients (median age 73 years, 43 females). Montreal cognitive assessment (MoCA) scores were obtained for all 91 patients. Phonemic and semantic linguistic clusters were derived from patient's SVF response using computerized approach. Qualitative language characheristics of linguistic clusters were calculated: number of switches between clusters, number of clusters, mean cluster size, first cluster size. Statistical analysis was performed and linear models with mixed effects were generated with MoCA and diagnosis as dependant variables and (i) routine SVF task score only (base model) vs. (ii) qualitative language characheristics and SVF task score (full model). Both models included age, sex and education level as covariates. Result Patients with SCD and MCI had significant differences in SVF total score (14 [10; 16] vs. 10 [7; 12], p <0.001, ES=0.81 (0.45, 1.2)) as well as several cluster characteristics: phonemic number of switches (12 vs 9, p = 0.001), phonemic mean cluster size (2 vs 0, p = 0.006), semantic mean cluster size (4.8 vs 3.5, p = 0.007) and semantic first cluster size (5.0 vs 3.0, p = 0.003). ANOVA test demonstrated better prediction of MoCA score (AIC 812.76, BIC 847.88, χ 2 = 0.035) and diagnosis (AIC 178.81, BIC 210.74, χ 2 = 0.016) in the full model compared to the base model. Conclusion Using novel qualitative language characheristics in verbal fluency task assessment might be a promising tool to improve diagnostic algorithm using computerized approach and better understand underlying language difficulties in pre‐dementia states.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 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 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 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".