P1‐147: Cortical thickness analysis in Alzheimer's onset
Bibliographic record
Abstract
Neurodegenerative changes are known to begin well before clinical symptoms of Alzheimer's disease manifest. Early detection of these changes is crucial for successful treatment. Biomarkers such as cortical thickness can reveal locations of neurodegenerative effects. Standard approach of vertex-based analysis suffers from multiple comparison correction due to large number of measurements in each brain from a database of a small number of subjects. In this work we propose a patch-based approach to analyzing cortical thickness to overcome the limitations of vertex-based approach while retaining regional sensitivity; results show promise in better distinguishing between the MCI and MCI converter subject groups. We investigated 124 subjects with mild cognitive impairment (MCI), 54 subjects with mild cognitive impairment that later converted to Alzheimer's dementia (MCIconv). We computed cortical thickness of each subject by a method that is based on solving the potential equation between the gray and white matter surfaces, and integrating along the gradient field that runs perpendicular to each isosurface. Next, we parcellate each subject's cortical surface into n = 350 different cortical regions by a recursive zonal equal-area partitioning algorithm. We averaged the cortical thickness at each cortical patch for each subject and investigated the differences in thickness of cortical mantle across the two subject groups. Accounting for multiple comparison corrections, statistical analysis on the patch-wise cortical thickness data was able to localize regions, Fig. 1, where there are significant differences in thickness among the two subject groups. Patch-wise cortical thickness data was used as a biomarker in SVM-based classification with a classification accuracy of 71%. This is a significant improvements over using the conventional vertex-wise cortical thickness data, which is able to achieve a 62.4% accuracy. The regions on the cortical surface that contain significantly different (p values ≤ 0.05) measurements in cortical thickness between the MCI and the MCI Converters subject groups. The proposed method to analyze cortical data is a powerful form of dimensionality reduction that can significantly reduce the effects of multiple comparison corrections in subsequent statistical analysis. Using this method we were able to localize the regions on the cortex where there are significant differences in cortical thickness among the two subject groups. We also observed a significant advantage in terms of classification accuracy of using patch-wise cortical thickness data as opposed to vertex-wise data.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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".