Comparative Analysis of Machine Learning Algorithms for Identifying Genetic Markers Linked to Alzheimer's Disease

The identification of genetic markers for complex diseases like Alzheimer's Disease (AD) is pivotal in medical genomics. This study aims to identify genetic markers associated with AD by introducing a novel approach that exclusively utilizes genetic data. Our primary goals are to benchmark explainable machine learning models against BLUPF90, an advanced mixed linear model approach, and to uncover single nucleotide polymorphisms (SNPs) crucial for AD. We analyze SNPs to achieve these goals, focusing on the genetic heritability rate of 58-79% for AD [12]. Our methodology focuses solely on genetic data to uncover SNPs crucial for AD, employing transparent computational models to ensure interpretability alongside predictive power. The findings demonstrate the efficacy of a purely genomic approach combined with Machine Learning to advance our understanding of AD. Our methodology successfully identified a robust set of SNPs associated with AD, encompassing both previously recognized and novel SNPs. The Machine Learning models employed delineated distinct SNP profiles, highlighting the complexity and heterogeneity of AD. These results not only deepen our understanding of AD's genetic underpinnings but also facilitate the development of targeted therapeutic and diagnostic strategies, showcasing the potential of computational techniques in medical genomics.