Supplementary Material for: Use of the Montreal Cognitive Assessment Thai Version to Discriminate Amnestic Mild Cognitive Impairment from Alzheimer’s Disease and Healthy Controls: Machine Learning Results
Bibliographic record
Abstract
Background: The Montreal Cognitive Assessment (MoCA) is an effective and applicable screening instrument to confirm the diagnosis of amnestic mild cognitive impairment (aMCI) from patients with Alzheimer’s disease (AD) and healthy controls (HCs). Objectives: This study aimed to determine the reliability and validity of the following: (a) Thai translation of the MoCA (MoCA-Thai) and (b) delineate the key features of aMCI based on the MoCA subdomains. Methods: This study included 60 HCs, 61 aMCI patients, and 60 AD patients. The MoCA-Thai shows adequate psychometric properties including internal consistency, concurrent validity, test-retest validity, and inter-rater reliability. Results: The MoCA-Thai may be employed as a diagnostic criterion to make the diagnosis of aMCI, whereby aMCI patients are discriminated from HC with an area under the receiver-operating characteristic (AUC-ROC) curve of 0.813 and from AD patients with an AUC-ROC curve of 0.938. The best cutoff scores of the MoCA-Thai to discriminate aMCI from HC is ≤24 and from AD > 16. Neural network analysis showed that (a) aberrations in recall was the most important feature of aMCI versus HC with impairments in language and orientation being the second and third most important features and (b) aberrations in visuospatial skills and executive functions were the most important features of AD versus aMCI and that impairments in recall, language, and orientation but not attention, concentration, and working memory, further discriminated AD from aMCI. Conclusions: The MoCA-Thai is an appropriate cognitive assessment tool to be used in the Thai population for the diagnosis of aMCI and AD.
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 | 0.002 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.732 | 0.230 |
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".