IC‐P2‐090: Longitudinal progression of AD‐like patterns of brain atrophy in a normal elderly cohort and in MCI: A high‐imensinal pattern classification study
Bibliographic record
Abstract
MRI is an established AD biomarker. Methods for computational neuroanatomy, including high-dimensional pattern analysis and classification, have been demonstrated by several studies to achieve excellent classification of individuals, thereby offering the potential for diagnosis and prognosis. This study was based on two large neuroimaging studies of normal aging and AD: the Baltimore Longitudinal Study of Aging (BLSA) and the Alzheimer's Disease Neuroimaging Initiative (ADNI). We investigated longitudinal progression of AD-like patterns of atrophy, determined from ADNI, in the BLSA cohort of cognitively normal (CN) elderly and of MCI. A high-dimensional pattern classifier was trained on 66 CN and 56 AD ADNI patients, and was subsequently applied to 109 CN and 15 MCI individuals from the BLSA study over a period of 9 years. The longitudinal progression of AD-like patterns of atrophy was determined for different age brackets. 98.7% of all BLSA participants that remained CN were correctly classified as CN, thereby cross-validating the accuracy of ADNI-derived classification on datasets from a different study. CN subjects of ages above 80 progressively displayed AD-like patterns of brain atrophy. The rates of change of classification-derived abnormality scores of CN's were fairly well clustered around 0, except a small subgroup of them (especially older subjects), generally indicating lack of progression of CN towards AD-like phenotypes. In contrast, rates of change of individuals that developed MCI were more variable and positive, indicating gradual progression of many, but not all, to AD-like structure. Moreover, cognitive scores of CN and MCI that were determined to have AD-like classification scores were significantly lower than their counterparts classified as normal-like. A biomarker of structural abnormality distinguishing CN from AD was derived using sophisticated high-dimensional pattern classification, and was tested on longitudinal MRI scans from cognitively normal elderly and of MCI individuals. Although most CN's that remain cognitively stable display normal and stable patterns of atrophy, individuals that develop MCI show steady increases in AD-like atrophy patterns. Structural abnormality scores and their rates of change define subgroups of CN and MCI individuals whose cognitive scores differ significantly, further indicating the clinical relevance of this structural biomarker.
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 | 0.001 | 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".