Machine-learning derived MRI-based atrophy biomarker predicts long-term cognitive decline in stroke or transient ischemic attack
Bibliographic record
Abstract
Alzheimer's disease-resemblance atrophy index (AD-RAI) is a machine-learning derived MRI-based brain atrophy biomarker that is valid in predicting cognitive decline in subjects with AD. We investigated the performance of AD-RAI in predicting long-term cognitive decline in subjects with stroke or transient ischemic attack (TIA). We recruited consecutive dementia-free stroke/TIA subjects who had brain MRI at baseline (i.e., within 3-6 months after the index event) and cognitive data at both baseline and 3 years. We defined cognitive decline as an increase in clinical dementia rating scale from 0 to 0.5 or above or from 0.5 to 1 or above at 3 years when compared with baseline. We investigated the association between AD-RAI, traditional brain atrophy biomarkers (hippocampus volume [HV], hippocampal fraction [HF], total brain volume [TBV], TBV/intracranial volume [ICV] ratio, ventricular-brain-ratio, presence of medial temporal lobe atrophy [MTLA]), and cerebral small vessel disease biomarkers (white matter hyperintensity [WMH]) volume, WMHV/ICV ratio presence of confluent WMH, presence of >/=3 lacunes) with cognitive decline. Of 231 participants (mean age 66.0 ± 10.9, 124 [53.7] male), 55(23.8) had cognitive decline at 3 years. Among all the imaging biomarkers, AD-RAI and HV were associated with cognitive decline in univariate regression. Such a relationship was still significant with AD-RAI after adjusted for age, gender, and education (aOR [95%CI] 3.900 [1.221-12.458]). Among all imaging biomarkers, only AD-RAI was associated with slope of Montreal cognitive assessment (MoCA) after adjusted to age, gender, education (β(SE) −0.742[0.242], p=0.002). AD-RAI predicted long term cognitive decline in subjects with stroke/TIA.
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 | 0.001 | 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) | 0.003 | 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".