Integrating large-scale serum metabolomics and <i>APOE</i> ε4 genotype status for the non-invasive detection of Alzheimer’s disease in the ADNI cohort
Bibliographic record
Abstract
Abstract INTRODUCTION Accurate Alzheimer’s disease (AD) detection remains challenging and often requires invasive or costly procedures. Blood-based metabolomic signatures offer a promising non-invasive approach. This study aimed to identify a serum metabolite panel and evaluate its performance alone and in combination with apolipoprotein E ( APOE ) ε4 genotype status for distinguishing AD from cognitively normal (CN) individuals. METHODS Baseline data from 594 participants in the Alzheimer’s Disease Neuroimaging Initiative (237 AD, 357 CN) were analyzed. High-resolution serum metabolomics (Biocrates MxP® Quant 500) and APOE genotype data were used for LASSO-based feature selection, followed by machine learning model training and evaluation on a held-out test set. RESULTS A panel of 151 metabolites distinguished AD from CN with high accuracy (test-set AUC=0.90). Adding APOE to the panel further improved model performance (AUC=0.91 versus AUC=0.75 for APOE alone; p <0.001), achieving strong sensitivity (0.92), specificity (0.84), and negative predictive value (0.94). Key predictive metabolites included bile acids, ether-linked phosphatidylcholines, and acylcarnitines, which are associated with pathways related to lipid metabolism, mitochondrial function, and the gut–liver–brain axis. CONCLUSION Integrating serum metabolomics with APOE enables accurate, non-invasive AD detection and offers a scalable screening approach with strong potential to rule out AD in primary care. ClinicalTrials.gov Identifier NCT00106899 and related ADNI phases.
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 | 0.003 |
| 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 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".