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

Background: Since dementia is preventable with early interventions, biomarkers that assist in diagnosing early stages of dementia, such as mild cognitive impairment (MCI), are urgently needed. Methods: Multiomics analysis of amnestic MCI (aMCI) peripheral blood (n = 25) was performed covering the tran-scriptome, microRNA, proteome, and metabolome. Validation analysis for microRNAs was conducted in an inde-pendent cohort (n = 12). Artificial intelligence was used to identify the most important features for predicting aMCI. Findings: We found that hsa-miR-4455 is the best biomarker in all omics analyses. The diagnostic index tak-ing a ratio of hsa-miR-4455 to hsa-let-7b-3p predicted aMCI patients against healthy subjects with 97% over-all 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. Interpretation: The 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. (c) 2022 The Author(s). Published by Elsevier Masson SAS. This is an open access article under the CC BY-NC -ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Automated summary

Through multiomics analysis of peripheral blood in patients with mild cognitive impairment (MCI), it was found that hsa-miR-4455 is the best biomarker for predicting MCI. The study revealed the association of a subset of T cells and the GCN pathway with MCI. This multiomics approach improves the diagnostic accuracy for MCI and provides insights into changes in peripheral blood.