Examination of the accuracy of Cogniciti’s self‐administered, online, Brain Health Assessment in detecting amnestic mild cognitive impairment
Bibliographic record
Abstract
Abstract Background Our need for easily administered online assessments sensitive to mild cognitive difficulties is increasing as our population ages. Our team has recently presented data indicating the accuracy of an online, publicly available, self‐administered screening measure, Cogniciti’s Brain Health Assessment (BHA), in the detection of amnestic mild cognitive impairment (aMCI) in a sample of community dwelling older adults. This current work extends those findings by further examining diagnostic accuracy of this measure. Method Using a cross‐sectional design, community‐dwelling older adults aged 60‐89 completed a gold standard neuropsychological assessment to determine a diagnosis of normal cognition (NC) or aMCI (by consensus of 3 staff neuropsychologists). Each participant also completed the BHA. Penalized logistic regression (PLR) analyses were used to examine which specific BHA tasks and measured demographic variables contributed to this test’s predictive utility in detecting aMCI. Diagnostic accuracy of the PLR model was compared with a logistic regression (LR) model examining BHA total score accuracy. Result 91 participants met inclusion criteria (51 aMCI, 40 NC). PLR modelling for the BHA indicated that of the tasks and variables measured by the BHA, the Face‐Name Association and Spatial Working Memory tasks predicted aMCI, with age also accounted for in the model (ROC‐AUC = 0.76; 95%CI: 0.66, 0.86). Based on this model, optimal performance cut‐points were determined, which resulted in 21% of the sample being classified as aMCI (positive), 23% as negative, and 56% as inconclusive. Projected general population classification rates are also presented to provide an estimate of how the BHA may perform in the broader population. Conclusion Results support that validity of the BHA as a screening measure for aMCI, and provide indication of the tasks within this measure that contribute to its utility in screening for this specific type of cognitive decline. Given the BHA is an online, self‐administered task, this measure has the potential to not only decrease unnecessary referrals for comprehensive assessment to determine presence of aMCI, but also to save practitioners time over commonly used paper and pencil screeners.
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 | 0.014 | 0.042 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 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 | 0.001 |
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".