P1‐281: NONLINEAR N‐SCORE ESTIMATION FOR ESTABLISHING COGNITIVE NORMS FROM THE NATIONAL ALZHEIMER'S COORDINATING CENTER (NACC) DATASET
Bibliographic record
Abstract
An important step in determining patients with possible dementia based on cognitive scores, is to estimate the distribution of scores in cognitively normal subjects; extreme scores relative to this control distribution may indicate dementia. To date, approaches have focused on determining the distribution of z-scores for a set of normal controls, and then compared the z-scores of new subjects with that distribution. The z-score approach was extended by Shirk et al. [1] to consider linear correction for age, sex, and education. Here this approach is further extended to consider non-linear relationships between predictors and cognitive score, as well as accounting for differing standard deviation of the cognitive scores with age. The same NACC database of normal controls was used as in [1] (data were used from 29 ADCs and considered UDS visits between September 2015 and May 2017). Nonlinear shape-constrained generalized additive models (SCAMs) [2] were fit to the data separately for each cognitive outcome. SCAM fits were generated with nonlinear corrections for age and education (constrained to be monotonic), and an additive term for sex. Another SCAM was then fitted to estimate change in the standard deviation of residuals with respect to age. A lookup table was generated based on these two SCAM fits. For each value of age, education level, and sex, an adjusted z-score (n-score) was generated, using the fitted mean and standard deviation for that age, education level, and sex. The figures display an example SCAM model fit for TRAIL B. There was a clear non-linear relationship between age and TRAIL B (Figure 1). The estimated relationship between education level and TRAIL B was linear (Figure 2). Increasing standard deviation was seen with age (Figure 3). Consistent improvements were seen across different neurocognitive outcomes by allowing for such non-linear adjustment.
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 | 0.007 | 0.024 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.004 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.011 | 0.013 |
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".