Longitudinal validation of Cognigram<sup>™</sup> in mild cognitive impairment (MCI): First year of data
Bibliographic record
Abstract
Abstract Background It is estimated that 10‐16% of patients with mild cognitive impairment (MCI) transition to dementia each year[1], though it has been difficult to predict which patients are at highest risk of deterioration[2]. CognigramTM is a computerized card game that measures cognition, with results relatively unaffected by language, educational level, and cultural background[3]. Our three‐year longitudinal study aims to assess the capacity of Cognigram to predict future cognitive decline in MCI and cognitively normal (CN) subjects. Method One year data is presented here for the first 7 MCI (mean age 76.0, mean MoCA 21.0) and first 6 CN (mean age 69.5, mean MoCA 27.5) participants. Cognigram testing was performed at baseline, 3, 6, 9, and 12 months. Cognigram captured performance scores related to card detection, identification, one‐back, and card learning. Clinical change was assessed using blinded neuropsychological evaluations performed at baseline and 12 months. Result Based on the neuropsychological testing, MCI and CN participants were classified as either clinically “stable” (4 MCI and 5 CN) or “declining” (3 MCI, 1 CN). On Cognigram card learning accuracy, clinically declining participants showed an accuracy drop of ‐0.14 (0.89 to 0.75) compared to clinically stable participants who showed an accuracy increase of +0.05 (0.89 to 0.94) (p=0.013). There were no clear patterns in the other Cognigram sub‐tests. Conclusion The Cognigram card learning accuracy test may distinguish between clinically stable and declining participants. The stable participants’ improvement may be explained by a learning effect, which is absent in the decliners. This analysis is limited by the small number, and data will be reviewed with more participants over three years. At the conclusion of our longitudinal study, we hope to determine if Cognigram can identify early cognitive changes in CN and MCI which predict which patients eventually convert to dementia. References: (1) Moon Y, Oh‐Park M, Lee J.(2013). http://www.sciencedirect.com/science/article/pii/B9780323544542000133 ; (2) Brooks, L.G., Loewenstein, D.A. Alz Res Therapy 2, 28 (2010); (3) Cogstate Healthcare, LLC (2017). https://www.cognigram.us/cognigram/about/index/index0 .
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| 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".