A simple classification framework for predicting Alzheimer’s disease from region-based grey matter volume and APOE genotype status
Bibliographic record
Abstract
Alzheimer’s Disease (AD) is a prevalent neurodegenerative disease currently affecting more than 47 million people in the world. There are now many complex classifiers that can accurately distinguish AD patients from healthy controls, based on the subject’s structural magnetic resonance imaging (MRI) brain scan. Most such automated diagnostic systems are blackboxes: While their predictions are accurate, it is difficult for clinicians to interpret those predictions, due to the large number of features used by the classifier, and/or by the complexity of that classifier. This work demonstrates that an automated learning algorithm can produce a simple classifier that can correctly distinguish AD patients from healthy controls (HC) similar to its more-complex counterparts. Here we buildthis classifier from the data in the Alzheimer’s Disease Neuroimaging Initiative database, using a fairly small set of features, including grey matter volumes of 33 regions of interest derived from structural MRI, as well as the APOE genotype. We first considered three simple base-learners that each produce a classifier that is simple and interpretable. Running our overall learner, involving standard feature selection processes and these simple base-learners, on these features, produced a 7-feature elastic net model, EN7, that achieved accuracy of 89.28% on the test set. Next, we ran the same overall learner using two more-complex base-learners over the same initial dataset. The accuracy of the best model here was 90.47%, which was not statistically different from the performance of our much simpler EN7 model.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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) | 0.000 | 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 teacher head, 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".