The definitive diagnosis of Alzheimer's Disease (AD) without the need for neuropathological confirmation remains a challenge in AD research today, despite efforts to uncover the molecular and biological underpinnings of the disease process. Furthermore, the potential for therapeutic intervention is limited upon the onset of symptoms, providing motivation for studying and treating the AD precursor mild cognitive impairment (MCI), the prodromal stage of AD instead. Applying machine learning classification to transcriptomic data of MCI, AD, and cognitively normal (CN) control patients, we identified differentially expressed genes that serve as biomarkers for the characterization and classification of subjects into MCI or AD groups. Predictive models employing these biomarker genes exhibited good classification performances for CN, MCI, and AD, significantly above random chance. The PI3K-Akt, IL-17, JAK-STAT, TNF, and Ras signaling pathways were also enriched in these biomarker genes, indicating their diagnostic potential and pathophysiological roles in MCI and AD. These findings could aid in the recognition of MCI and AD risk in clinical settings, allow for the tracking of disease progression over time in individuals as part of a therapeutic approach, and provide possible personalized drug targets for early intervention of MCI and AD.
Keywords: Alzheimer's Disease; biomarkers; gene expression; machine learning; mild cognitive impairment; neurodegeneration.
Copyright © 2022 Oh, Zhou, Chin, Amarnath, Cheah, Ng, Kandiah, Goh and Chiam.