Machine Learning to Assess Language Impairments in Older Adults
Bibliographic record
Abstract
Abstract Objectives: The main objective of this paper is to propose a methodology based on machine learning classifiers for assessing language impairments associated with dementia in older adults. To do so, we compare the impact of different types of language tasks, features, and recording media on our ML-based methodology’s efficiency. Methodology: The methodology encompasses the following steps: 1) Extracting linguistic and acoustic features from subjects’ speeches which have been collected from subjects with dementia ( N =9) and subjects without dementia ( N =13); 2) Employing feature selection methods to rank informative features; 3) Training ML classifiers using extracted features to recognize subjects with dementia from subjects without dementia; 4) Evaluating the classifiers; 5) Selecting the most accurate classifiers to develop the languages assessment tools. Results: Our results indicate that 1) we can find more predictive linguistic markers to distinguish language impairment associated with dementia from participants’ speech produced during the picture description language task than the story recall task. 2) a phone-based recording interface provides a more high-quality language dataset than the web-based recording systems; 3) classifiers trained with selected features from acoustic features or linguistic features show higher performance than the classifiers trained with pure features. Conclusion: Our results show that the tree-based classifiers that have been trained using the PD dataset can be used to develop an ML-based language assessment tool that can detect language impairment associated with dementia as quickly as possible.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.011 | 0.025 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.004 | 0.010 |
| Research integrity | 0.001 | 0.017 |
| Insufficient payload (model declined to judge) | 0.001 | 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; both teacher heads agree on what is shown here.
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".