DTI measurements for Alzheimer’s classification
Bibliographic record
Abstract
Diffusion tensor imaging (DTI) is a promising imaging technique that provides insight into white matter microstructure integrity and it has greatly helped identifying white matter regions affected by Alzheimer's disease (AD) in its early stages. DTI can therefore be a valuable source of information when designing machine-learning strategies to discriminate between healthy control (HC) subjects, AD patients and subjects with mild cognitive impairment (MCI). Nonetheless, several studies have reported so far conflicting results, especially because of the adoption of biased feature selection strategies. In this paper we firstly analyzed DTI scans of 150 subjects from the Alzheimer's disease neuroimaging initiative (ADNI) database. We measured a significant effect of the feature selection bias on the classification performance (p-value < 0.01), leading to overoptimistic results (10% up to 30% relative increase in AUC). We observed that this effect is manifest regardless of the choice of diffusion index, specifically fractional anisotropy and mean diffusivity. Secondly, we performed a test on an independent mixed cohort consisting of 119 ADNI scans; thus, we evaluated the informative content provided by DTI measurements for AD classification. Classification performances and biological insight, concerning brain regions related to the disease, provided by cross-validation analysis were both confirmed on the independent test.
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 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".