A - 18 Predicting Incident Amnestic Mild Cognitive Impairment and Alzheimer’s Disease with a Computerized Neuropsychological Assessment Device: Comparative Clinical Utility
Bibliographic record
Abstract
Abstract Objective Computerized neuropsychological assessment devices (CNADs) offer improved accessibility to screen for neurodegeneration, although their clinical utility is yet to be established. We evaluated the efficacy of a CNAD to predict incident amnestic mild cognitive impairment and Alzheimer’s disease (aMCI/ad) compared to a conventional paper-and-pencil screening tool and PET amyloid beta (AB). Method Data were collected from the longitudinal observational Alzheimer’s Disease Neuroimaging Initiative 3. Participants were cognitively normal at baseline (N = 315, mean age = 72.9 +/− 7.1, 59.4% female, 16.8 +/− 2.3 years of education, 91.4% White, 33.7% APOE4+). Over four years, 26 (8.3%) participants converted to aMCI and 3 (1.0%) individuals developed ad. Prognostic validity was compared between three measures assessed at baseline. Computerized visual episodic memory scores were evaluated using the One Card Learning (OCL) test. Conventional screening was conducted using the Montreal Cognitive Assessment (MoCA). PET AB+ was quantified as ≥2 SD whole cerebellum referenced region standardized uptake value ratios. Results Area under the curve (AUC) analyses using logistic regression were adjusted for age, sex, education, race, and APOE4+ status. OCL accuracy yielded AUC = 0.67, p = 0.003, 95% CI [0.58, 0.76]. Total MoCA score demonstrated AUC = 0.75, p < 0.001, 95% CI [0.67, 0.83]. PET AB+ produced AUC = 0.68, p = 0.001, 95% CI [0.58, 0.79]. Conclusions When assessed at baseline, the MoCA provided the greatest clinical utility to predict incident aMCI/ad. Baseline OCL accuracy and PET AB+ were similarly effective for determining future cognitive decline. Further research is needed to examine the utility of CNADs before they are integrated into clinical practice.
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 | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 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) | 0.001 | 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".