Cerebrospinal fluid proteomics for predictive assessment of Alzheimer’s Disease risk
Bibliographic record
Abstract
Alzheimer's disease (AD) involves early molecular changes beyond amyloid-β (Aβ) and tau, that create heterogeneous disease biology, giving rise to variable disease initiation and highly variable longitudinal trajectories. Accurately predicting trajectories is vital for design of clinical trials and for clinical care, yet current CSF and PET biomarkers provide limited predictive capabilities despite their excellent diagnostic value. We performed CSF proteomics using tandem-mass-tag mass spectrometry in 1,104 ADNI participants with extensive longitudinal assessments. Machine learning-derived protein panels accurately predicted two classes of outcomes. First, they identified several key inflection points along the disease trajectory, including onset of 1) amyloid plaque pathology (Aβ- to Aβ+; AUC=0.88), 2) symptoms (asymptomatic to symptomatic; AUC=0.89), and 3) functional decline (MCI [due-to-AD] to AD Dementia; AUC=0.88). Second, protein panels forecast longitudinal trajectories of decline, spanning both clinical domains (cognition and function) and pathological process, including tau accumulation measured by tau-PET neocortical standardized uptake value ratio (SUVR) and neurodegeneration indexed by hippocampal volume and FDG-PET SUVR. Proteomics panels outperformed conventional CSF- and PET-based Aβ and tau markers. Importantly, these predictions were driven by novel mechanisms, spanning synaptic signaling, proteostasis, metabolic stress, vascular remodeling, and immune dysregulation, that anchor distinct inflection points and shape long-term trajectories. Together, these findings position CSF proteomics as a powerful approach for anticipating disease onset and progression, with direct implications for patient stratification and personalized intervention.
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) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".