A Large-Scale Serum Metabolite Panel for Baseline Detection of Alzheimer’s Disease

Blood-based metabolomic signatures offer promising, non-invasive avenues for Alzheimer’s disease (AD) detection. We aimed to identify a serum metabolite panel integrated with APOE ε4 status for distinguishing AD from cognitively normal (CN) individuals. Baseline data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) were analyzed for 594 participants (237 AD, 357 CN). High-resolution serum metabolomics (Biocrates MxP® Quant 500) and APOE data were used for LASSO-based feature selection, followed by machine learning model training and performance evaluation on a held-out test set. A panel of 151 metabolites distinguished AD from CN with high accuracy (test-set AUC=0.90). Adding APOE to the panel further improved the 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). 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. NCT00106899 and related ADNI phases