Investigation of Genome-Wide Association SNPs and Alzheimer’s Disease

The aim of this work is to measure the influence of genome-wide association study single nucleotide polymorphisms (SNPs) in Alzheimer’s disease (AD). Data mining methods were tested. Data used were obtained from ADNI database. Subjects were 214 normal controls (NCs), 364 subjects with mild cognitive impairment (MCI), and 179 subjects with early AD. Linear regression (LR), random forests (RF) and multifactor dimensionality reduction (MDR) models were used. The results demonstrate the effectiveness of using RF and MDR. The MDR model produced the best sensitivity in all comparisons using only 3 SNPs. Regarding specificity, LR resulted in the best specificity in two comparisons (NC vs. MCI and MCI vs. AD), while MDR produced the best specificity in comparison of NC vs. AD. Several significant polymorphisms associated with MCI and AD were identified. RF and MDR are alternatives to existing methods for detecting genetic interactions.