Predicting Alzheimer's disease development: a comparison of cognitive criteria and associated neuroimaging biomarkers
Bibliographic record
Abstract
INTRODUCTION: The definition of "objective cognitive impairment" in current criteria for mild cognitive impairment (MCI) varies considerably between research groups and clinics. This study aims to compare different methods of defining memory impairment to improve prediction models for the development of Alzheimer's disease (AD) from baseline to 24 months. METHODS: The sensitivity and specificity of six methods of defining episodic memory impairment (< -1, -1.5 or -2 standard deviations [SD] on one or two memory tests) were compared in 494 non-demented seniors from the Alzheimer's Disease Neuroimaging Initiative using the area under the curve (AUC) for receiver operating characteristic analysis. The added value of non-memory measures (language and executive function) and biomarkers (hippocampal and white-matter hyperintensity volume, brain parenchymal fraction [BPF], and APOEε4 status) was investigated using logistic regression. RESULTS: Baseline scores < -1 SD on two memory tests predicted AD with 75.91 % accuracy (AUC = 0.80). Only APOE ε4 status further improved prediction (B = 1.10, SE = 0.45, p = .016). A < -1.5 SD cut-off on one test had 66.60 % accuracy (AUC = 0.77). Prediction was further improved using Trails B/A ratio (B = 0.27, SE = 0.13, p = .033), BPF (B = -15.97, SE = 7.58, p = .035), and APOEε4 status (B = 1.08, SE = 0.45, p = .017). A cut-off of < -2 SD on one memory test (AUC = 0.77, SE = 0.03, 95 % CI 0.72-0.82) had 76.52 % accuracy in predicting AD. Trails B/A ratio (B = 0.31, SE = 0.13, p = .017) and APOE ε4 status (B = 1.07, SE = 0.46, p = .019) improved predictive accuracy. CONCLUSIONS: Episodic memory impairment in MCI should be defined as scores < -1 SD below normative references on at least two measures. Clinicians or researchers who administer a single test should opt for a more stringent cut-off and collect and analyze whole-brain volume. When feasible, ascertaining APOE ε4 status can further improve prediction.
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 | 0.003 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".