Multiomics and artificial intelligence enabled peripheral blood-based prediction of amnestic mild cognitive impairment

Abstract

BackgroundSince dementia is preventable with early interventions, biomarkers that assist in diagnosing early stages of dementia, such as mild cognitive impairment (MCI), are urgently needed. MethodsMultiomics analysis of amnestic MCI (aMCI) peripheral blood (n = 25) was performed covering the transcriptome, microRNA, proteome, and metabolome. Validation analysis for microRNAs was conducted in an independent cohort (n = 12). Artificial intelligence was used to identify the most important features for predicting aMCI. FindingsWe found that hsa-miR-4455 is the best biomarker in all omics analyses. The diagnostic index taking a ratio of hsa-miR-4455 to hsa-let-7b-3p predicted aMCI patients against healthy subjects with 97% overall accuracy. An integrated review of multiomics data suggested that a subset of T cells and the GCN (general control nonderepressible) pathway are associated with aMCI. InterpretationThe multiomics approach has enabled aMCI biomarkers with high specificity and illuminated the accompanying changes in peripheral blood. Future large-scale studies are necessary to validate candidate biomarkers for clinical use.