Explainable artificial intelligence identifies an AQP4 polymorphism-based risk score associated with brain amyloid burden

Abstract

Aquaporin-4 (AQP4) is an integral component of the glymphatic system, today considered a crucial pathway for removing brain interstitial solutes like amyloid-β (Aβ). Evidence exists that genetic variation of AQP4 impacts Aβ clearance, clinical outcome in Alzheimer’s disease as well as sleep measures. We examined whether a risk score calculated from several AQP4 single-nucleotide polymorphisms (SNPs) is related to Aβ neuropathology in older cognitively unimpaired individuals. We used a machine learning approach with decision tree ensembles and explainable artificial intelligence (AI) to extract information on synergistic effects of AQP4 SNPs on brain amyloid burden from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort. From this information, we formulated a sex-specific AQP4 SNP-based risk score and evaluated it on the basis of data from the screening process of the Anti-Amyloid Treatment in Asymptomatic Alzheimer’s (A4) study. We found in both cohorts significant associations of the risk score with brain amyloid burden as well as amyloid positivity. The results support the hypothesis of an involvement of the glymphatic system, and particularly AQP4, in brain amyloid aggregation pathology. They suggest also that different AQP4 SNPs exert a synergistic effect on the build-up of brain amyloid burden.