IC‐P‐204: PROGNOSTIC UTILITY OF MRI ATROPHY MEASURES IN AMCI PATIENTS WITH MINIMAL COGNITIVE DECLINE
Bibliographic record
Abstract
The utility of MRI atrophy measures for predicting progression of amnestic MCI (aMCI) to Alzheimer's disease (AD) is limited, as evidenced by proven prognostic likelihood ratios (LR; positive LR = 2,9; negative LR = 0,49-0,56)(Frisoni et al., Neurology 2013) that are outside the ranges usually required for clinical implementation (LR+ ≥ 5,0 and LR- ≤ 0,2). We tested the hypothesis that stratification of patients by global cognitive function could improve the prognostic value of MRI. 4502We selected 147 aMCI subjects from the ADNI-1 database with MMSE = [28-30] at baseline and 195 with MMSE = [24-27] for which we had complete MRI volumetric results (FreeSurfer) and general primary-level information. We created a prognostic model for progression to AD within 36 months based on these measures. The model that included left hippocampal volume and left mid-temporal cortical thickness, when adjusted for intracranial volume, age and sex, had a 87,4% area under ROC curve (AUC), 80.3% classification accuracy, 53,8% sensitivity, 88,2% specificity, LR+ = 4,81 and LR- = 0.49 (with classification cut-point of disease probability = 0.4). After excluding statistical outliers (three subjects; impact chi-square (dl 6)=12.59), the same model had AUC of 91,1%, 81.9% classification accuracy, 71.4% sensitivity, 85.3% specificity, LR+=4.9 and LR-=0.3 (with classification cut-point of 0.3). Applying the same model to the ADNI aMCI subjects with baseline MMSE in the [24-27]range gave a AUC of 64.5 %. In fact, simply adding a dichotomous variable in the MRI model for cognitive status (i.e. baseline MMSE in range [24-27] or [28-30]) gives a AUC of 73.3% for all aMCI in the ADNI-1 population. A clinically relevant prognostic significance for left hippocampal volume and left mid-temporal cortical thickness, when adjusted for intracranial volume, age and sex, has been observed in ADNI-1 aMCI subjects with baseline MMSE in the [28-30] range. The prognostic LR+ and LR- observed in these strata is higher than previously described for a more general population and reaches clinical applicability.
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 | 0.002 | 0.005 |
| 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) | 0.003 | 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".