Identification of a Simple and Novel Cut-Point Based Cerebrospinal Fluid and MRI Signature for Predicting Alzheimer’s Disease Progression that Reinforces the 2018 NIA-AA Research Framework
Bibliographic record
Abstract
The 2018 NIA-AA research framework proposes a classification system with Amyloid-β deposition, pathologic Tau, and Neurodegeneration (ATN) for diagnosis and staging of Alzheimer's disease (AD). Data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database can be utilized to identify diagnostic signatures for predicting AD progression, and to determine the utility of this NIA-AA research framework. Profiles of 320 peptides from baseline cerebrospinal fluid (CSF) samples of 287 normal, mild cognitive impairment (MCI), and AD subjects followed over a 3-10-year period were measured via multiple reaction monitoring mass spectrometry. CSF Aβ42, total-Tau (tTau), phosphorylated-Tau (pTau-181), and hippocampal volume were also measured. From these candidate markers, optimal signatures with decision thresholds to separate AD and normal subjects were first identified via unbiased regression and tree-based algorithms. The best performing signature determined via cross-validation was then tested in an independent group of MCI subjects to predict future progression. This multivariate analysis yielded a simple diagnostic signature comprising CSF pTau-181 to Aβ42 ratio, MRI hippocampal volume, and low CSF levels of a novel PTPRN peptide, with a decision threshold on each marker. When applied to a separate MCI group at baseline, subjects meeting these signature criteria experience 4.3-fold faster progression to AD compared to a 2.2-fold faster progression using only conventional markers. This novel 4-marker signature represents an advance over the current diagnostics based on widely used markers, and is easier to use in practice than recently published complex signatures. This signature also reinforces the ATN construct from the 2018 NIA-AA research framework.
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 | 0.005 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".