IC‐P‐205: DOES THE STRATIFICATION OF AMCI PATIENTS BY THEIR COGNITIVE STATUS HELP IN THEIR OUTCOME PROGNOSIS BASED ON MRI IMAGING?
Bibliographic record
Abstract
The cognitive status of aMCI subjects is correlated to the extent of the underlying pathological process. It therefore constitutes a good starting point for the prognostic of their progression to clinical Alzheimer's disease (AD). We wished to test the hypothesis that the combination of clinically obtainable information on cardiovascular risk factors (CRF) and brain volumetry via MRI in a stratum of aMCI subjects with low cognitive integrity would increase the quality of their prognosis. We conducted this case-control study on 195 aMCI ADNI subjects with baseline MMSE in the [24-27] range, and for which complete baseline CRF and MRI were available. We first created a prognostic model for AD within 36 months based on MRI volumetric results (FreeSurfer) and CRF (blood glucose levels, arterial tension, cholesterol and triglycerides). We then proceeded with a stratification based on cardiovascular risk, calculated by categorizing each CRF (expressed as 0 - normative level, 1 - moderate increase, 2 - considerable increase), summing, and dichotomizing all scores (0-2 for low risk, 3 and higher for high risk). The best-obtained model, with area under ROC curve of 80.1, contained the following variables: hypertension, triglycerides, cholesterol, glucose, right hippocampus, right inferior lateral ventricle, right middle temporal, and parahippocampal left-right difference. Stratification by cardiovascular risk provided two models: (a) low cardiovascular risk and right middle temporal and parahippocampal left-right difference resulted in ROC 72,6%, accuracy 65,8%, sensibility 57,5% and specificity 70,1%, positive likelihood ratio 1,9 and negative likelihood 0,6 at the probability level of 0.6; (b) high cardiovascular riskand right hippocampus and right inferior lateral ventricle resulted in ROC 81,5%, accuracy 71,4%, sensibility 86.0% specificity 44,4%, and positive/negative likelihood ratios of 1.55 and 0.32 respectively at the probability level of 0.5. The results from our models to predict progression in those aMCI with low global cognition using CRF and volumetric data have comparable positive/negative likelihood ratios than those described for MRI alone in the general aMCI population (LR+: 2.6;LR-: 0.46-0.5). Thus, in this dataset, the impact of cardiovascular factors on aMCI progression to AD is considerable, and stratification by cardiovascular status could have clinical sense.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 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) | 0.002 | 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; 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".