P4‐295: Multivariate Data Analysis Of Regional MRI Volumes and Cortical Thickness Measures To Distinguish Between Alzheimer's Disease, Mild Cognitive Impairment And Healthy Controls
Bibliographic record
Abstract
Previous studies have investigated the use of hippocampal volumes for diagnosis in Alzheimer's disease. Combinations of multiple regional volumes and cortical thicknesses may provide better discrimination between AD, MCI and controls however. To compare hippocampal volumes alone to a combination of hippocampal volumes, regional volumes and regional cortical thickness measures for discriminating between patients with Alzheimer's disease, subjects with mild cognitive impairment and healthy age-matched controls. A total of 345 subjects were included in the study (117 AD, 118 MCI and 110 Controls). High resolution sagital MR images compatible with the ADNI study were acquired on six 1.5T scanners as part of the AddNeuroMed project, a European programme designed to make drug discovery more efficient. Automated regional volumes were determined with the ANIMAL algorithm, automated regional cortical thickness measures were performed using the approach of Fischl and Dale and hippocampal volumes were manually outlined by an experienced radiologist. A total of 75 MRI measures were analysed by the orthogonal partial least squares (OPMS) multivariate approach to distinguish between AD, MCI and Controls. Sensitivity, specificity and likelihood ratios (LR+) were calculated for each comparison. Using leave-one-out cross validation the OPLS model for AD v Controls for all measures (sensitivity=88%, specificity=95%, LR=18) gave better results than hippocampal volumes alone (sensitivity=86%, specificity=90%, LR=9). Comparing AD v MCI, all measures (sensitivity=76%, specificity=77%, LR=3) again gave better discrimination than hippocampal volumes alone (sensitivity=68%, specificity=66%, LR=2). Finally the performance for MCI v controls was higher for all measures (sensitivity=67%, specificity=81%, LR=4) than for hippocampal volumes alone (sensitivity=67%, specificity=76%, LR=3). Variables of particular importance for separation of the groups were manual hippocampal volumes, temporal grey matter volumes and entorhinal cortical thickness. Multivariate data analysis is a powerful tool for distinguishing between different patient groups. Combining regional volumes and regional cortical thickness measures with hippocampal volumes doubled the likelihood ratio when comparing AD and controls compared to hippocampal volumes alone. The approach described here shows strong promise for distinguishing between groups on the basis of regional disease related atrophy patterns and may prove to have high diagnostic value.
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 | 0.004 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| 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 | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 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".