Profiling biomarker signatures that contribute to conversion from mild cognitive impairment to Alzheimer's disease
Bibliographic record
Abstract
Selecting individuals who will develop dementia within the time frame of a clinical trial constitutes an important challenge for disease modifying trials. Population enrichment is crucial for testing interventions capable to modify the clinical progression from mild cognitive impairment (MCI) to dementia stages of Alzheimer's disease. Here we propose to assess the signatures of progression to dementia in MCI individuals based on PET amyloid imaging and to validate these signatures in an independent dataset. We hypothesize that a network of regions rather than a global amyloid assessment will constitute the signature of disease progression in MCI stages. In this study, we used voxel-wise logistic regression to identify the signatures of disease progression. Subsequently, we tested whether these signatures accurately identify individuals who will progress to dementia in the subsequent 24 months using machine learning. Data used in this study were acquired from the Alzheimer's Disease Neuroimaging Initiative database. 15.8% of the MCI population progressed to AD dementia in 24 months. We used advanced data sampling techniques to overcome the imbalance of proportions between progressive and stable MCI individuals and used Random Forest for classification. Our method achieved an overall accuracy of 84% and an area under the receiver operating characteristic value of 0.906 for classification. This is the first study evaluating the ability of amyloid imaging to be used as an early diagnostic marker using an independent testing dataset. The present study has achieved higher performance measures than previous studies using non-amyloid biomarkers and can be considered to be used in a clinical environment for early diagnosis of Alzheimer's dementia. In conclusion, these results allow for the enrichment of clinical populations by implementing better inclusion and exclusion criteria for the investigation of therapeutics specific for Alzheimer's disease and reducing false positives.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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; both teacher heads agree on what is shown here.
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".