The TabCAT Brain Health Assessment: A Highly Efficient and Sensitive Approach to Detecting Very Mild Cognitive Impairment (P5.197)
Bibliographic record
Abstract
Objective: To develop a tablet-based cognitive assessment tool (TabCAT) that efficiently and accurately detects mild cognitive impairment (MCI) for use in primary care and to compare its sensitivity to the Montreal Cognitive Assessment (MoCA). Background: Widely used paper and pencil screens have limited sensitivity to mild cognitive impairment. Further, standard administration requires training, scoring is not reliable or automated, and rich visual stimuli and accurate reaction time measurement are not possible. Methods: To maximize sensitivity and specificity to MCI, we determined the cognitive tests that would most efficiently separate 8,646 patients with MCI and 8,678 controls from the National Alzheimer’s Disease Coordinating Centers. We included tests of memory, language, executive function, and processing speed as predictors of diagnosis in a discriminant function analysis. Delayed memory (Logical Memory) and processing speed (Digit Symbol) best discriminated MCI patients from controls. All other tests accounted for < 1[percnt] of the variance. These results guided the design of the TabCAT memory recall and digit symbol tests that require 5 minutes of testing time. TabCAT tests were administered to 14 patients with MCI and 27 demographically matched controls. We included the MoCA and the TabCAT tests as predictors of diagnosis in separate discriminant function analyses. Patients in all analyses were mild with Clinical Dementia Rating scores = .5. Results: TabCAT tests correctly classified 79[percnt] of MCI patients and 89[percnt] of controls. In contrast, the MoCA classified only 36[percnt] of the MCI patients and 85[percnt] of the controls. Conclusions: Preliminary data indicates that the TabCAT Brain Health Assessment efficiently identifies very mild cognitive impairment with greater sensitivity and similar specificity to the MoCA and can be easily administered in primary care. Larger validation studies are planned. Study Supported By: Alzheimer’s Disease Research Center P50AG023501, The Larry L. Hillblom Foundation, Quest Diagnostics Inc., NIA K23AG037566
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) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.005 | 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; 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".