Discovery of novel metabolic biomarkers in blood serum for diagnosis of Alzheimer's disease.

Abstract

Background: Blood metabolites have emerged as promising candidates in the search for biomarkers for Alzheimer's disease (AD), as evidence shows that various metabolic derangements contribute to neurodegeneration in AD.

Objective: We aim to identify metabolic biomarkers for AD diagnosis.

Methods: We conducted an in-depth analysis of the serum metabolome of AD patients and age, sex-matched cognitively unimpaired older adults using ultra-high-performance liquid chromatography-high resolution mass spectrometry. The biomarkers associated with AD were identified using machine learning algorithms.

Results: Using the discovery dataset and support vector machine (SVM) algorithm, we identified a panel of 14 metabolites predicting AD with a 1.00 area under the curve (AUC) of receiver operating characteristic (ROC). The SVM model was tested against the verification dataset using an independent cohort and retained high predictive accuracy with a 0.97 AUC. Using the random forest (RF) algorithm, we identified a panel of 13 metabolites that predicted AD with a 0.96 AUC when tested against the verification dataset.

Conclusions: These findings pave the way for an efficient, blood-based diagnostic test for AD, holding promise for clinical screenings and diagnostic procedures.