IC‐P‐087: Multivariate Analysis of MRI Data to Discriminate between Groups and Predict Conversion in Alzheimer's Disease
Bibliographic record
Abstract
Alzheimer's disease (AD) is one of the most common forms of neurodegenerative disorders connected with gradual loss of cognitive functions such as episodic memory. We used multivariate data analysis, more specifically orthogonal partial least squares to latent structures (OPLS) , to discriminate between subjects with AD, mild cognitive impairment (MCI) and elderly control subjects (CTL) using global and regional MRI volumetric measures. 117 AD patients (mean (sd) age = 75(6) years, MMSE = 21(5)), 122 MCI patients (74(6) years, MMSE = 27(3)) and 112 CTL (73(7) years, MMSE = 29(1)) from the multi-centre European AddNeuroMed study were included. High resolution sagital 3D T1w MP-RAGE datasets were acquired. Automated regional segmentation and manual outlining of the hippocampus were applied. Altogether this yielded 24 different volumetric measures used for OPLS analyses comparing the different patient groups. 17 AD subjects, 12 CTL were randomly selected out of the cohort and the 22 MCI subjects which converted to AD at one year clinical follow-up were left out of the analysis. This was performed to acquire equal group size when creating the models and to have a small external test for validation. Using seven-fold-cross-validation we received a sensitivity of 87% and a specificity of 90% using hippocampal measures alone, comparing AD with CTL. Adding global and regional measures to the hippocampal measurements resulted in a sensitivity of 90% and a specificity of 94%. This increase in sensitivity and specificity resulted in an increase of the positive likelihood ratio from 9 to 15. The original model including all measures could predict 82% of the AD patients and 83% of the CTL correctly from the left out data. Finally, 72% of MCI converters were correctly predicted as AD. Hippocampal volumes, regional temporal gray matter volumes and total CSF volume were particularly important for separation of the groups. Multivariate analysis of regional MRI measures shows excellent potential for distinguishing between AD patients and CTL. Combining MRI measures together resulted in a significantly better classification than using them separately. OPLS also shows potential for predicting conversion from MCI to AD.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".