IC‐P‐163: Predicitng Alzheimer's disease–related cognition with cortical thickness correlations: A GLMNET approach
Bibliographic record
Abstract
Alzheimer's disease (AD) has been proposed to be primarily a “disconnection syndrome”, whereby the progression of neurodegeneration propagates along cortical networks. Previously, we have introduced methods by which cognitive performance can be predicted from group-wise correlations in cortical thickness, derived from T1-weighted MRI. Here, we extend this basic approach using GLMNET, which allows all network edges to be analyzed in a single multivariate regression model, to yield a small set of edges which best predict the individual behavioural outcome. Cortical thickness estimates were obtained from T1-weighted images obtained from the ADNI-1 cohort. For each pair of regions (ROIs), a linear model was fitted for Normal Control (NC) subjects only. Residual error was computed from this model for all subjects. Using GLMNET, the resulting residuals were regressed against cognitive performance scores in a general linear model (GLM) including residuals from all pairs of ROIs i and j (Figure 1A). Cross-validation was performed by using different subsets of the NC group to fit and test the GLM. We demonstrate the approach using the Alzheimer's Disease Assessment Scale (ADAS-cog). GLMNET predicted ∼40% of the variance using residuals from ∼150 ROI pairs (Figure 1B). As shown in Figure 1C, the strongest coefficients were found for ROI pairs including entorhinal cortex (EC), middle temporal gyrus (MTG), superior parietal gyrus (SPG), precuneus (PCUN), postcentral lobule (PCL), and superior frontal gyrus (SFG).
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".